1{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T06:00:30.816Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","content":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop."}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T06:00:30.828Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}4{"parentUuid":null,"isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop."},"uuid":"f5b89391-3aff-4263-af02-f80bed3b977f","timestamp":"2026-10-30T06:00:30.833Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","timestamp":"2026-10-30T06:00:30.852Z","version":"2.1.314","shape":{"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude, running within the Claude Agent SDK."},{"type":"text","text":"CWD: /Users/simon-pierreboucher/wp29/runs/RT0026\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/<timestamp>.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n\nSEPARATE REVIEW (additional)\n- After the gate passes, a separate reviewer session that has not seen your work in progress will examine `TASK.md` and everything under `out/` and may return a list of issues (file `out/review/review.json`). You will then be resumed once to address them: fix what is justified, explain in `out/report.md` (Limitations and open issues) what you disagree with, re-run the gate, and update `out/claims.json` and `out/state/phases.json`. The reviewer has no reference answers; its role is to challenge unsupported claims, violated information rules, unverified computations, and inconsistencies between your report and your results.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"54a72cd5-d489-421e-92ea-d86231e1486d","timestamp":"2026-10-30T06:00:30.852Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["6c04ea332e967905c33c745fc622389d61d9c85bed742510c97f7f1aacb07760","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"62b173e5a5806a0cb655952bbfd73309b5d789a914f1c039bc9c71a4deec4439"}8{"parentUuid":"f5b89391-3aff-4263-af02-f80bed3b977f","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"5e3f5056-b7cb-457e-b5a6-866af41180b3","timestamp":"2026-10-30T06:00:30.840Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"5e3f5056-b7cb-457e-b5a6-866af41180b3","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"6a387b37-c3b8-46a5-b932-043f2d589b7e","timestamp":"2026-10-30T06:00:30.840Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"6a387b37-c3b8-46a5-b932-043f2d589b7e","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"2bf5f06f-b5f0-43e8-8986-b9a54360af3d","timestamp":"2026-10-30T06:00:30.841Z","rendered":[{"content":"<system-reminder>\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>\n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n</system-reminder>"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}12{"parentUuid":"2bf5f06f-b5f0-43e8-8986-b9a54360af3d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuqCWeoLRi2oCUvXf2Y","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSpAUKEAgTGAI4AUIIdGhpbmtpbmcSDOhmDjEGMP4eTgV0QBoMZA9/S2++OmfS//BNIjD5sAMnNksroICjlbtDsa7oKWkj74tWaLMMEsZ03bjN3bEsJ7iQRGQC3xW5FGdQ5jIqwQQ0x8e3/WYMaj8Yq2FgXLN0ET0SfnfHM61Pabj2IylLa/LkyQnf67vvIb8nQONxHWUBnDIc5YmDvugeWY8lq4F0VD1OmOR0P/RREJ3qR+ftfQ/tuMhMxKfiD4SLmKo6KaX7haO2sdsZg3uxaFgp/Z/cOSRaIfcQVvk9AKd44flSkOdDXJ6ykWYUojdqmvs4TjqCKxWTz+vZ4AOXznHCFj0CsXiMqzUw1LPzrAudJgQyvAhsiCk/IY7WD6T01uBqbaS6lKKyOr8mE+LyjNevbuxP5SsTlrGisOiX7p7IY6A5LJ9ifaxTGqH/KhEikr2pSKbq8qrbvK5aJV/Er1ksp9DEJy7dLzTZy+qm19bh/50XeslFevMsa/tsv+ffjf6W8WoP90L0yT7e1gkXIk/PD43S4WIkiNCtaVT++fSZbxYj6c63xvyno87+QaOS0vLzFMkMZvUtGlMpnWTGnpUKb4UlKe924Wzi37nkzmCcmFz8bHq46xjpsUmUBxgS6RYTSwCixEiLfwjQhjcS7uolNtEkXjYmCNHHqNVqlbskMUiU9Q7O8vav7AmGKZcpX59qLaI6lapk2yCFefSn3BnvkaEfyww+1Y8EoLx/Ri7dE87cFGf/X1hVl7fvQmzcq8uPwZXfjHmJzu1ZMCnnQUf2RW8K0ZMdtWHcWimYk+hLZ/GkPaOpDAVsVLwjoOkSmf9TPVezx7kslHLWbpYdA6hOjw6D+EZL3MEOZDgURBLBdVZk7xCc+G5l8Ngv+eQi3Ut9FbLqGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":4350,"cache_read_input_tokens":0,"output_tokens":129,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4350},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":458,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXuqCFGsTabDc2f4rXta","requestRef":"54a72cd5-d489-421e-92ea-d86231e1486d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"434f0ddb-7bf5-43c2-ab05-39f06cbf4bdc","timestamp":"2026-10-30T06:00:32.329Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"434f0ddb-7bf5-43c2-ab05-39f06cbf4bdc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuqCWeoLRi2oCUvXf2Y","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_014Mb9WsE2V4KGdCojQECZop","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":4350,"cache_read_input_tokens":0,"output_tokens":129,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4350},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXuqCFGsTabDc2f4rXta","requestRef":"54a72cd5-d489-421e-92ea-d86231e1486d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f3eff19a-20d0-4841-abff-ac36eb86581c","timestamp":"2026-10-30T06:00:32.948Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"f3eff19a-20d0-4841-abff-ac36eb86581c","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_014Mb9WsE2V4KGdCojQECZop","type":"tool_result","content":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 40\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 30 00:09 .\ndrwxr-xr-x 203 simon-pierreboucher staff 6496 oct. 30 02:00 ..\n-rw-r--r-- 1 simon-pierreboucher staff 3082 oct. 30 00:09 bundle.json\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 00:05 data\n-rw-r--r-- 1 simon-pierreboucher staff 3191 oct. 30 00:05 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 10330 oct. 30 00:05 TASK.md\ndata:\nfirst_release.csv\nREADME.md\nRSAFS_current.csv\nUMCSENT.csv\nvintages\n\ndata/vintages:\nPAYEMS_vintage_2025-10-31.csv\nPAYEMS_vintage_2025-11-30.csv\nPAYEMS_vintage_2025-12-31.csv\nPAYEMS_vintage_2026-01-31.csv\nPAYEMS_vintage_2026-02-28.csv\nPAYEMS_vintage_2026-03-31.csv\nPAYEMS_vintage_2026-04-30.csv\nPAYEMS_vintage_2026-05-31.csv\nPAYEMS_vintage_2026-06-30.csv\nPAYEMS_vintage_2026-07-31.csv\nRSAFS_vintage_2025-10-31.csv\nRSAFS_vintage_2025-11-30.csv\nRSAFS_vintage_2025-12-31.csv\nRSAFS_vintage_2026-01-31.csv\nRSAFS_vintage_2026-02-28.csv\nRSAFS_vintage_2026-03-31.csv\nRSAFS_vintage_2026-04-30.csv\nRSAFS_vintage_2026-05-31.csv\nRSAFS_vintage_2026-06-30.csv\nRSAFS_vintage_2026-07-31.csv","is_error":false}]},"uuid":"d695dea7-cc18-4e57-87d1-7799092ca2df","timestamp":"2026-10-30T06:00:33.079Z","toolUseResult":{"stdout":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 40\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 30 00:09 .\ndrwxr-xr-x 203 simon-pierreboucher staff 6496 oct. 30 02:00 ..\n-rw-r--r-- 1 simon-pierreboucher staff 3082 oct. 30 00:09 bundle.json\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 00:05 data\n-rw-r--r-- 1 simon-pierreboucher staff 3191 oct. 30 00:05 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 10330 oct. 30 00:05 TASK.md\ndata:\nfirst_release.csv\nREADME.md\nRSAFS_current.csv\nUMCSENT.csv\nvintages\n\ndata/vintages:\nPAYEMS_vintage_2025-10-31.csv\nPAYEMS_vintage_2025-11-30.csv\nPAYEMS_vintage_2025-12-31.csv\nPAYEMS_vintage_2026-01-31.csv\nPAYEMS_vintage_2026-02-28.csv\nPAYEMS_vintage_2026-03-31.csv\nPAYEMS_vintage_2026-04-30.csv\nPAYEMS_vintage_2026-05-31.csv\nPAYEMS_vintage_2026-06-30.csv\nPAYEMS_vintage_2026-07-31.csv\nRSAFS_vintage_2025-10-31.csv\nRSAFS_vintage_2025-11-30.csv\nRSAFS_vintage_2025-12-31.csv\nRSAFS_vintage_2026-01-31.csv\nRSAFS_vintage_2026-02-28.csv\nRSAFS_vintage_2026-03-31.csv\nRSAFS_vintage_2026-04-30.csv\nRSAFS_vintage_2026-05-31.csv\nRSAFS_vintage_2026-06-30.csv\nRSAFS_vintage_2026-07-31.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f3eff19a-20d0-4841-abff-ac36eb86581c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"440fd780c0a58aac92cd8b1da6d3a47540f825a83473a3075410b93e3d11895d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSpAUKEAgTGAI4AUIIdGhpbmtpbmcSDOhmDjEGMP4eTgV0QBoMZA9/S2++OmfS//BNIjD5sAMnNksroICjlbtDsa7oKWkj74tWaLMMEsZ03bjN3bEsJ7iQRGQC3xW5FGdQ5jIqwQQ0x8e3/WYMaj8Yq2FgXLN0ET0SfnfHM61Pabj2IylLa/LkyQnf67vvIb8nQONxHWUBnDIc5YmDvugeWY8lq4F0VD1OmOR0P/RREJ3qR+ftfQ/tuMhMxKfiD4SLmKo6KaX7haO2sdsZg3uxaFgp/Z/cOSRaIfcQVvk9AKd44flSkOdDXJ6ykWYUojdqmvs4TjqCKxWTz+vZ4AOXznHCFj0CsXiMqzUw1LPzrAudJgQyvAhsiCk/IY7WD6T01uBqbaS6lKKyOr8mE+LyjNevbuxP5SsTlrGisOiX7p7IY6A5LJ9ifaxTGqH/KhEikr2pSKbq8qrbvK5aJV/Er1ksp9DEJy7dLzTZy+qm19bh/50XeslFevMsa/tsv+ffjf6W8WoP90L0yT7e1gkXIk/PD43S4WIkiNCtaVT++fSZbxYj6c63xvyno87+QaOS0vLzFMkMZvUtGlMpnWTGnpUKb4UlKe924Wzi37nkzmCcmFz8bHq46xjpsUmUBxgS6RYTSwCixEiLfwjQhjcS7uolNtEkXjYmCNHHqNVqlbskMUiU9Q7O8vav7AmGKZcpX59qLaI6lapk2yCFefSn3BnvkaEfyww+1Y8EoLx/Ri7dE87cFGf/X1hVl7fvQmzcq8uPwZXfjHmJzu1ZMCnnQUf2RW8K0ZMdtWHcWimYk+hLZ/GkPaOpDAVsVLwjoOkSmf9TPVezx7kslHLWbpYdA6hOjw6D+EZL3MEOZDgURBLBdVZk7xCc+G5l8Ngv+eQi3Ut9FbLqGAE="},{"type":"tool_use","id":"toolu_014Mb9WsE2V4KGdCojQECZop","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"815b1cc9-b3e3-4373-b024-b4dfda4181fd","timestamp":"2026-10-30T06:00:33.086Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"54a72cd5-d489-421e-92ea-d86231e1486d","keep":2,"tail":["440fd780c0a58aac92cd8b1da6d3a47540f825a83473a3075410b93e3d11895d","f7923369558f68f3a36c4a818f7f9fb3d81f6253405c4ff5a27708ed8cf60ee5"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9396279b5c219653af9209fc3366ea28169a8c764e412fd78e8d4e1242dc8ea5"}17{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"d695dea7-cc18-4e57-87d1-7799092ca2df","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}18{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}19{"parentUuid":"d695dea7-cc18-4e57-87d1-7799092ca2df","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuqMjXsvmfY4oF4qw86","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Ne8TG4opcd4mfruyz7ousW","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json; cat bundle.json; cd data; for f in vintages/RSAFS*.csv; do echo $f $(wc -l <$f) $(head -1 $f) $(tail -1 $f); done; for f in vintages/PAYEMS*.csv; do echo $f $(wc -l <$f) $(tail -2 $f|tr '\\n' ' '); done; cat first_release.csv; tail -3 RSAFS_current.csv UMCSENT.csv; wc -l *.csv","description":"Inspect data files and specs"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4879,"cache_read_input_tokens":4350,"output_tokens":255,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4879},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXuqMTQex6QV44Z8K7jR","requestRef":"815b1cc9-b3e3-4373-b024-b4dfda4181fd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"803bbddf-b403-4780-ab75-ed420d0badc0","timestamp":"2026-10-30T06:00:38.347Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"803bbddf-b403-4780-ab75-ed420d0badc0","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Ne8TG4opcd4mfruyz7ousW","type":"tool_result","content":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\n{\n \"task_id\": \"T1-forecast\",\n \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/forecasts.csv\", \"out/table1.csv\", \"out/figure1.png\"],\n \"results_keys\": {\n \"task_id\": {\"type\": \"string\", \"nullable\": false},\n \"model_name\": {\"type\": \"string\", \"nullable\": false},\n \"model_description\": {\"type\": \"string\", \"nullable\": false},\n \"n_origins\": {\"type\": \"integer\", \"nullable\": false},\n \"first_origin\": {\"type\": \"string\", \"nullable\": false},\n \"last_origin\": {\"type\": \"string\", \"nullable\": false},\n \"rmse_naive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_naive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_snaive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_snaive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_ar1_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_ar1_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_model_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_model_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rel_improvement_rmse_h1\": {\"type\": \"number\", \"nullable\": false}, \"rel_improvement_rmse_h3\": {\"type\": \"number\", \"nullable\": false},\n \"dm_stat_h1\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h1\": {\"type\": \"number\", \"nullable\": false},\n \"dm_stat_h3\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h3\": {\"type\": \"number\", \"nullable\": false},\n \"conclusion_code_h1\": {\"type\": \"string\", \"nullable\": false}, \"conclusion_code_h3\": {\"type\": \"string\", \"nullable\": false},\n \"mean_abs_revision_h1_targets\": {\"type\": \"number\", \"nullable\": false},\n \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n \"n_analysed\": {\"type\": \"integer\", \"nullable\": true},\n \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n },\n \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n \"family_checks\": [\"chronology\", \"forecasts_csv_chronology\", \"positive_se\", \"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n \"ci_pairs\": [],\n \"positive_keys\": [\"rmse_naive_h1\", \"rmse_naive_h3\", \"rmse_snaive_h1\", \"rmse_snaive_h3\", \"rmse_ar1_h1\", \"rmse_ar1_h3\", \"rmse_model_h1\", \"rmse_model_h3\"],\n \"chronology_pairs\": [[\"first_origin\", \"last_origin\"]],\n \"forecasts_csv\": {\"path\": \"out/forecasts.csv\", \"origin_col\": \"origin_date\", \"target_col\": \"target_date\", \"vintage_col\": \"vintage_used\", \"rule\": \"vintage_used <= origin_date < target_date\", \"expected_rows\": 80},\n \"analysis_timeout_s\": 600,\n \"reproducibility_tolerance_rel\": 1e-6\n}\n{\n \"task_id\": \"T1-forecast\",\n \"family\": \"T1\",\n \"split\": \"transfer\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T04:09:07.391993+00:00\",\n \"files\": {\n \"TASK.md\": \"61cc57c0306ab4de71be29fc9e750be7f9ccd90b84a09c46af9ce71d01ac4faa\",\n \"data/README.md\": \"10d4c51e4318444b5599fb0c4ca8fe9ec611882c7609689b68ba09513841f069\",\n \"data/RSAFS_current.csv\": \"627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f\",\n \"data/UMCSENT.csv\": \"3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46\",\n \"data/first_release.csv\": \"1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4\",\n \"data/vintages/PAYEMS_vintage_2025-10-31.csv\": \"d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60\",\n \"data/vintages/PAYEMS_vintage_2025-11-30.csv\": \"a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77\",\n \"data/vintages/PAYEMS_vintage_2025-12-31.csv\": \"829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031\",\n \"data/vintages/PAYEMS_vintage_2026-01-31.csv\": \"8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7\",\n \"data/vintages/PAYEMS_vintage_2026-02-28.csv\": \"4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3\",\n \"data/vintages/PAYEMS_vintage_2026-03-31.csv\": \"919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e\",\n \"data/vintages/PAYEMS_vintage_2026-04-30.csv\": \"06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a\",\n \"data/vintages/PAYEMS_vintage_2026-05-31.csv\": \"e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d\",\n \"data/vintages/PAYEMS_vintage_2026-06-30.csv\": \"19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a\",\n \"data/vintages/PAYEMS_vintage_2026-07-31.csv\": \"3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41\",\n \"data/vintages/RSAFS_vintage_2025-10-31.csv\": \"3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36\",\n \"data/vintages/RSAFS_vintage_2025-11-30.csv\": \"4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4\",\n \"data/vintages/RSAFS_vintage_2025-12-31.csv\": \"436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd\",\n \"data/vintages/RSAFS_vintage_2026-01-31.csv\": \"b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e\",\n \"data/vintages/RSAFS_vintage_2026-02-28.csv\": \"2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77\",\n \"data/vintages/RSAFS_vintage_2026-03-31.csv\": \"0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f\",\n \"data/vintages/RSAFS_vintage_2026-04-30.csv\": \"02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f\",\n \"data/vintages/RSAFS_vintage_2026-05-31.csv\": \"8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b\",\n \"data/vintages/RSAFS_vintage_2026-06-30.csv\": \"2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524\",\n \"data/vintages/RSAFS_vintage_2026-07-31.csv\": \"52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2\",\n \"gate_spec.json\": \"460c09d75917d708aabc0aad9e6571175ca5180d698d7ab7f11c92827d727354\"\n }\n}vintages/RSAFS_vintage_2025-10-31.csv 405 observation_date,RSAFS_20251031 2025-08-01,732010\nvintages/RSAFS_vintage_2025-11-30.csv 406 observation_date,RSAFS_20251130 2025-09-01,733258\nvintages/RSAFS_vintage_2025-12-31.csv 407 observation_date,RSAFS_20251231 2025-10-01,732633\nvintages/RSAFS_vintage_2026-01-31.csv 408 observation_date,RSAFS_20260131 2025-11-01,735904\nvintages/RSAFS_vintage_2026-02-28.csv 409 observation_date,RSAFS_20260228 2025-12-01,734967\nvintages/RSAFS_vintage_2026-03-31.csv 410 observation_date,RSAFS_20260331 2026-01-01,733537\nvintages/RSAFS_vintage_2026-04-30.csv 412 observation_date,RSAFS_20260430 2026-03-01,752063\nvintages/RSAFS_vintage_2026-05-31.csv 413 observation_date,RSAFS_20260531 2026-04-01,757085\nvintages/RSAFS_vintage_2026-06-30.csv 414 observation_date,RSAFS_20260630 2026-05-01,763705\nvintages/RSAFS_vintage_2026-07-31.csv 415 observation_date,RSAFS_20260731 2026-06-01,768553\nvintages/PAYEMS_vintage_2025-10-31.csv 1041 2025-07-01,159518 2025-08-01,159540\nvintages/PAYEMS_vintage_2025-11-30.csv 1042 2025-08-01,159507 2025-09-01,159626\nvintages/PAYEMS_vintage_2025-12-31.csv 1044 2025-10-01,159488 2025-11-01,159552\nvintages/PAYEMS_vintage_2026-01-31.csv 1045 2025-11-01,159476 2025-12-01,159526\nvintages/PAYEMS_vintage_2026-02-28.csv 1046 2025-12-01,158497 2026-01-01,158627\nvintages/PAYEMS_vintage_2026-03-31.csv 1047 2026-01-01,158558 2026-02-01,158466\nvintages/PAYEMS_vintage_2026-04-30.csv 1048 2026-02-01,158459 2026-03-01,158637\nvintages/PAYEMS_vintage_2026-05-31.csv 1049 2026-03-01,158621 2026-04-01,158736\nvintages/PAYEMS_vintage_2026-06-30.csv 1050 2026-04-01,158829 2026-05-01,159001\nvintages/PAYEMS_vintage_2026-07-31.csv 1051 2026-05-01,158927 2026-06-01,158984\ntarget_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\n==> RSAFS_current.csv <==\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n\n==> UMCSENT.csv <==\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n 29 first_release.csv\n 418 RSAFS_current.csv\n 888 UMCSENT.csv\n 1335 total","is_error":false}]},"uuid":"3e0b064a-3cec-4eaa-b350-8896273639a6","timestamp":"2026-10-30T06:00:38.560Z","toolUseResult":{"stdout":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\n{\n \"task_id\": \"T1-forecast\",\n \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/forecasts.csv\", \"out/table1.csv\", \"out/figure1.png\"],\n \"results_keys\": {\n \"task_id\": {\"type\": \"string\", \"nullable\": false},\n \"model_name\": {\"type\": \"string\", \"nullable\": false},\n \"model_description\": {\"type\": \"string\", \"nullable\": false},\n \"n_origins\": {\"type\": \"integer\", \"nullable\": false},\n \"first_origin\": {\"type\": \"string\", \"nullable\": false},\n \"last_origin\": {\"type\": \"string\", \"nullable\": false},\n \"rmse_naive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_naive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_snaive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_snaive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_ar1_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_ar1_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_model_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h1\": {\"type\": \"number\", \"nullable\": false},\n \"rmse_model_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h3\": {\"type\": \"number\", \"nullable\": false},\n \"rel_improvement_rmse_h1\": {\"type\": \"number\", \"nullable\": false}, \"rel_improvement_rmse_h3\": {\"type\": \"number\", \"nullable\": false},\n \"dm_stat_h1\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h1\": {\"type\": \"number\", \"nullable\": false},\n \"dm_stat_h3\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h3\": {\"type\": \"number\", \"nullable\": false},\n \"conclusion_code_h1\": {\"type\": \"string\", \"nullable\": false}, \"conclusion_code_h3\": {\"type\": \"string\", \"nullable\": false},\n \"mean_abs_revision_h1_targets\": {\"type\": \"number\", \"nullable\": false},\n \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n \"n_analysed\": {\"type\": \"integer\", \"nullable\": true},\n \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n },\n \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n \"family_checks\": [\"chronology\", \"forecasts_csv_chronology\", \"positive_se\", \"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n \"ci_pairs\": [],\n \"positive_keys\": [\"rmse_naive_h1\", \"rmse_naive_h3\", \"rmse_snaive_h1\", \"rmse_snaive_h3\", \"rmse_ar1_h1\", \"rmse_ar1_h3\", \"rmse_model_h1\", \"rmse_model_h3\"],\n \"chronology_pairs\": [[\"first_origin\", \"last_origin\"]],\n \"forecasts_csv\": {\"path\": \"out/forecasts.csv\", \"origin_col\": \"origin_date\", \"target_col\": \"target_date\", \"vintage_col\": \"vintage_used\", \"rule\": \"vintage_used <= origin_date < target_date\", \"expected_rows\": 80},\n \"analysis_timeout_s\": 600,\n \"reproducibility_tolerance_rel\": 1e-6\n}\n{\n \"task_id\": \"T1-forecast\",\n \"family\": \"T1\",\n \"split\": \"transfer\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T04:09:07.391993+00:00\",\n \"files\": {\n \"TASK.md\": \"61cc57c0306ab4de71be29fc9e750be7f9ccd90b84a09c46af9ce71d01ac4faa\",\n \"data/README.md\": \"10d4c51e4318444b5599fb0c4ca8fe9ec611882c7609689b68ba09513841f069\",\n \"data/RSAFS_current.csv\": \"627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f\",\n \"data/UMCSENT.csv\": \"3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46\",\n \"data/first_release.csv\": \"1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4\",\n \"data/vintages/PAYEMS_vintage_2025-10-31.csv\": \"d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60\",\n \"data/vintages/PAYEMS_vintage_2025-11-30.csv\": \"a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77\",\n \"data/vintages/PAYEMS_vintage_2025-12-31.csv\": \"829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031\",\n \"data/vintages/PAYEMS_vintage_2026-01-31.csv\": \"8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7\",\n \"data/vintages/PAYEMS_vintage_2026-02-28.csv\": \"4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3\",\n \"data/vintages/PAYEMS_vintage_2026-03-31.csv\": \"919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e\",\n \"data/vintages/PAYEMS_vintage_2026-04-30.csv\": \"06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a\",\n \"data/vintages/PAYEMS_vintage_2026-05-31.csv\": \"e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d\",\n \"data/vintages/PAYEMS_vintage_2026-06-30.csv\": \"19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a\",\n \"data/vintages/PAYEMS_vintage_2026-07-31.csv\": \"3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41\",\n \"data/vintages/RSAFS_vintage_2025-10-31.csv\": \"3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36\",\n \"data/vintages/RSAFS_vintage_2025-11-30.csv\": \"4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4\",\n \"data/vintages/RSAFS_vintage_2025-12-31.csv\": \"436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd\",\n \"data/vintages/RSAFS_vintage_2026-01-31.csv\": \"b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e\",\n \"data/vintages/RSAFS_vintage_2026-02-28.csv\": \"2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77\",\n \"data/vintages/RSAFS_vintage_2026-03-31.csv\": \"0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f\",\n \"data/vintages/RSAFS_vintage_2026-04-30.csv\": \"02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f\",\n \"data/vintages/RSAFS_vintage_2026-05-31.csv\": \"8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b\",\n \"data/vintages/RSAFS_vintage_2026-06-30.csv\": \"2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524\",\n \"data/vintages/RSAFS_vintage_2026-07-31.csv\": \"52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2\",\n \"gate_spec.json\": \"460c09d75917d708aabc0aad9e6571175ca5180d698d7ab7f11c92827d727354\"\n }\n}vintages/RSAFS_vintage_2025-10-31.csv 405 observation_date,RSAFS_20251031 2025-08-01,732010\nvintages/RSAFS_vintage_2025-11-30.csv 406 observation_date,RSAFS_20251130 2025-09-01,733258\nvintages/RSAFS_vintage_2025-12-31.csv 407 observation_date,RSAFS_20251231 2025-10-01,732633\nvintages/RSAFS_vintage_2026-01-31.csv 408 observation_date,RSAFS_20260131 2025-11-01,735904\nvintages/RSAFS_vintage_2026-02-28.csv 409 observation_date,RSAFS_20260228 2025-12-01,734967\nvintages/RSAFS_vintage_2026-03-31.csv 410 observation_date,RSAFS_20260331 2026-01-01,733537\nvintages/RSAFS_vintage_2026-04-30.csv 412 observation_date,RSAFS_20260430 2026-03-01,752063\nvintages/RSAFS_vintage_2026-05-31.csv 413 observation_date,RSAFS_20260531 2026-04-01,757085\nvintages/RSAFS_vintage_2026-06-30.csv 414 observation_date,RSAFS_20260630 2026-05-01,763705\nvintages/RSAFS_vintage_2026-07-31.csv 415 observation_date,RSAFS_20260731 2026-06-01,768553\nvintages/PAYEMS_vintage_2025-10-31.csv 1041 2025-07-01,159518 2025-08-01,159540\nvintages/PAYEMS_vintage_2025-11-30.csv 1042 2025-08-01,159507 2025-09-01,159626\nvintages/PAYEMS_vintage_2025-12-31.csv 1044 2025-10-01,159488 2025-11-01,159552\nvintages/PAYEMS_vintage_2026-01-31.csv 1045 2025-11-01,159476 2025-12-01,159526\nvintages/PAYEMS_vintage_2026-02-28.csv 1046 2025-12-01,158497 2026-01-01,158627\nvintages/PAYEMS_vintage_2026-03-31.csv 1047 2026-01-01,158558 2026-02-01,158466\nvintages/PAYEMS_vintage_2026-04-30.csv 1048 2026-02-01,158459 2026-03-01,158637\nvintages/PAYEMS_vintage_2026-05-31.csv 1049 2026-03-01,158621 2026-04-01,158736\nvintages/PAYEMS_vintage_2026-06-30.csv 1050 2026-04-01,158829 2026-05-01,159001\nvintages/PAYEMS_vintage_2026-07-31.csv 1051 2026-05-01,158927 2026-06-01,158984\ntarget_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\n==> RSAFS_current.csv <==\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n\n==> UMCSENT.csv <==\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n 29 first_release.csv\n 418 RSAFS_current.csv\n 888 UMCSENT.csv\n 1335 total","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"803bbddf-b403-4780-ab75-ed420d0badc0","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026/data","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"bc6cb6081bc9b8cc6b837be8411352097d50a5c34e3a5d8704a889354381b551","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Ne8TG4opcd4mfruyz7ousW","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json; cat bundle.json; cd data; for f in vintages/RSAFS*.csv; do echo $f $(wc -l <$f) $(head -1 $f) $(tail -1 $f); done; for f in vintages/PAYEMS*.csv; do echo $f $(wc -l <$f) $(tail -2 $f|tr '\\n' ' '); done; cat first_release.csv; tail -3 RSAFS_current.csv UMCSENT.csv; wc -l *.csv","description":"Inspect data files and specs"}}]}}22{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"e41f8986-25e1-4276-881f-fd4a78e68844","timestamp":"2026-10-30T06:00:38.565Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"815b1cc9-b3e3-4373-b024-b4dfda4181fd","keep":4,"tail":["bc6cb6081bc9b8cc6b837be8411352097d50a5c34e3a5d8704a889354381b551","2f4eed6ac83970cc015598ea39dff0ca79cd58476b1718952fb47487b692544b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"461f46b6c22c385b373d94e0fb2a09aae817381693456c8081c0c3c2eff3724e"}23{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"3e0b064a-3cec-4eaa-b350-8896273639a6","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}24{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}25{"parentUuid":"3e0b064a-3cec-4eaa-b350-8896273639a6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuqmASLJ6SR9PBHm5NJ","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":10269,"cache_read_input_tokens":9229,"output_tokens":753,"output_tokens_details":{"thinking_tokens":307},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":10269},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2425,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXuqkuZMnAYjbXuBgbJB","requestRef":"e41f8986-25e1-4276-881f-fd4a78e68844","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5b8d1d7e-456d-4474-8bdf-c4ce2e05d292","timestamp":"2026-10-30T06:00:43.099Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026/data","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"5b8d1d7e-456d-4474-8bdf-c4ce2e05d292","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuqmASLJ6SR9PBHm5NJ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01X7wc9nMqsHftPK4qLEpyka","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob,hashlib\nfor f in sorted(glob.glob('vintages/*.csv'))+['RSAFS_current.csv','UMCSENT.csv','first_release.csv']:\n d=pd.read_csv(f); c=d.columns\n dt=pd.to_datetime(d.iloc[:,0])\n gaps=(dt.diff().dt.days>31).sum()\n print(f,d.shape,dt.min().date(),dt.max().date(),'na',d.isna().sum().to_dict(),'dup',dt.duplicated().sum(),'gaps',gaps, hashlib.sha256(open(f,'rb').read()).hexdigest()[:12])\n\"\ngrep -n ',$' vintages/RSAFS*.csv vintages/PAYEMS*.csv RSAFS_current.csv | head; grep -c ',$' UMCSENT.csv; awk -F, 'NR>1 && $2==\"\" ' UMCSENT.csv | tail -3\n","description":"Audit schema, missing, duplicates, gaps"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":10269,"cache_read_input_tokens":9229,"output_tokens":753,"output_tokens_details":{"thinking_tokens":307},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":10269},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXuqkuZMnAYjbXuBgbJB","requestRef":"e41f8986-25e1-4276-881f-fd4a78e68844","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"576e3adf-c849-4cc7-8ac1-d35e9ef72a4e","timestamp":"2026-10-30T06:00:46.488Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026/data","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}27{"parentUuid":"576e3adf-c849-4cc7-8ac1-d35e9ef72a4e","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01X7wc9nMqsHftPK4qLEpyka","type":"tool_result","content":"(eval):cd:1: no such file or directory: data\nvintages/PAYEMS_vintage_2025-10-31.csv (1040, 2) 1939-01-01 2025-08-01 na {'observation_date': 0, 'PAYEMS_20251031': 0} dup 0 gaps 0 d4b4c909ed32\nvintages/PAYEMS_vintage_2025-11-30.csv (1041, 2) 1939-01-01 2025-09-01 na {'observation_date': 0, 'PAYEMS_20251130': 0} dup 0 gaps 0 a05ef7fc50cf\nvintages/PAYEMS_vintage_2025-12-31.csv (1043, 2) 1939-01-01 2025-11-01 na {'observation_date': 0, 'PAYEMS_20251231': 0} dup 0 gaps 0 829dae087af6\nvintages/PAYEMS_vintage_2026-01-31.csv (1044, 2) 1939-01-01 2025-12-01 na {'observation_date': 0, 'PAYEMS_20260131': 0} dup 0 gaps 0 8fd01c5d2740\nvintages/PAYEMS_vintage_2026-02-28.csv (1045, 2) 1939-01-01 2026-01-01 na {'observation_date': 0, 'PAYEMS_20260228': 0} dup 0 gaps 0 4a913e67ac5f\nvintages/PAYEMS_vintage_2026-03-31.csv (1046, 2) 1939-01-01 2026-02-01 na {'observation_date': 0, 'PAYEMS_20260331': 0} dup 0 gaps 0 919de86b07be\nvintages/PAYEMS_vintage_2026-04-30.csv (1047, 2) 1939-01-01 2026-03-01 na {'observation_date': 0, 'PAYEMS_20260430': 0} dup 0 gaps 0 06a8d663d9aa\nvintages/PAYEMS_vintage_2026-05-31.csv (1048, 2) 1939-01-01 2026-04-01 na {'observation_date': 0, 'PAYEMS_20260531': 0} dup 0 gaps 0 e2a152e87413\nvintages/PAYEMS_vintage_2026-06-30.csv (1049, 2) 1939-01-01 2026-05-01 na {'observation_date': 0, 'PAYEMS_20260630': 0} dup 0 gaps 0 19fbc6cd3547\nvintages/PAYEMS_vintage_2026-07-31.csv (1050, 2) 1939-01-01 2026-06-01 na {'observation_date': 0, 'PAYEMS_20260731': 0} dup 0 gaps 0 3a3a6603fcc3\nvintages/RSAFS_vintage_2025-10-31.csv (404, 2) 1992-01-01 2025-08-01 na {'observation_date': 0, 'RSAFS_20251031': 0} dup 0 gaps 0 3ecb0832a391\nvintages/RSAFS_vintage_2025-11-30.csv (405, 2) 1992-01-01 2025-09-01 na {'observation_date': 0, 'RSAFS_20251130': 0} dup 0 gaps 0 4a683d853746\nvintages/RSAFS_vintage_2025-12-31.csv (406, 2) 1992-01-01 2025-10-01 na {'observation_date': 0, 'RSAFS_20251231': 0} dup 0 gaps 0 436df4b5509b\nvintages/RSAFS_vintage_2026-01-31.csv (407, 2) 1992-01-01 2025-11-01 na {'observation_date': 0, 'RSAFS_20260131': 0} dup 0 gaps 0 b92ab6a5c1db\nvintages/RSAFS_vintage_2026-02-28.csv (408, 2) 1992-01-01 2025-12-01 na {'observation_date': 0, 'RSAFS_20260228': 0} dup 0 gaps 0 2af0a3aaeeba\nvintages/RSAFS_vintage_2026-03-31.csv (409, 2) 1992-01-01 2026-01-01 na {'observation_date': 0, 'RSAFS_20260331': 0} dup 0 gaps 0 0316fdf238d5\nvintages/RSAFS_vintage_2026-04-30.csv (411, 2) 1992-01-01 2026-03-01 na {'observation_date': 0, 'RSAFS_20260430': 0} dup 0 gaps 0 02dcc697a1db\nvintages/RSAFS_vintage_2026-05-31.csv (412, 2) 1992-01-01 2026-04-01 na {'observation_date': 0, 'RSAFS_20260531': 0} dup 0 gaps 0 8c3fe3530213\nvintages/RSAFS_vintage_2026-06-30.csv (413, 2) 1992-01-01 2026-05-01 na {'observation_date': 0, 'RSAFS_20260630': 0} dup 0 gaps 0 2f103157f4a9\nvintages/RSAFS_vintage_2026-07-31.csv (414, 2) 1992-01-01 2026-06-01 na {'observation_date': 0, 'RSAFS_20260731': 0} dup 0 gaps 0 52c04a8fce2e\nRSAFS_current.csv (417, 2) 1992-01-01 2026-09-01 na {'observation_date': 0, 'RSAFS': 0} dup 0 gaps 0 627d8bb386ac\nUMCSENT.csv (887, 2) 1952-11-01 2026-09-01 na {'observation_date': 0, 'UMCSENT': 210} dup 0 gaps 0 3076277f9f21\nfirst_release.csv (28, 5) 2024-06-01 2026-09-01 na {'target_month': 0, 'first_release_vintage': 0, 'level_first_release': 0, 'level_prev_year_same_vintage': 0, 'yoy_first_release': 0} dup 0 gaps 0 1d1ae8b3cacf\n210\n1977-09-01,\n1977-10-01,\n1977-12-01,","is_error":false}]},"uuid":"cdcd133c-41ce-4ceb-b0ff-85f8906575d5","timestamp":"2026-10-30T06:00:46.872Z","toolUseResult":{"stdout":"(eval):cd:1: no such file or directory: data\nvintages/PAYEMS_vintage_2025-10-31.csv (1040, 2) 1939-01-01 2025-08-01 na {'observation_date': 0, 'PAYEMS_20251031': 0} dup 0 gaps 0 d4b4c909ed32\nvintages/PAYEMS_vintage_2025-11-30.csv (1041, 2) 1939-01-01 2025-09-01 na {'observation_date': 0, 'PAYEMS_20251130': 0} dup 0 gaps 0 a05ef7fc50cf\nvintages/PAYEMS_vintage_2025-12-31.csv (1043, 2) 1939-01-01 2025-11-01 na {'observation_date': 0, 'PAYEMS_20251231': 0} dup 0 gaps 0 829dae087af6\nvintages/PAYEMS_vintage_2026-01-31.csv (1044, 2) 1939-01-01 2025-12-01 na {'observation_date': 0, 'PAYEMS_20260131': 0} dup 0 gaps 0 8fd01c5d2740\nvintages/PAYEMS_vintage_2026-02-28.csv (1045, 2) 1939-01-01 2026-01-01 na {'observation_date': 0, 'PAYEMS_20260228': 0} dup 0 gaps 0 4a913e67ac5f\nvintages/PAYEMS_vintage_2026-03-31.csv (1046, 2) 1939-01-01 2026-02-01 na {'observation_date': 0, 'PAYEMS_20260331': 0} dup 0 gaps 0 919de86b07be\nvintages/PAYEMS_vintage_2026-04-30.csv (1047, 2) 1939-01-01 2026-03-01 na {'observation_date': 0, 'PAYEMS_20260430': 0} dup 0 gaps 0 06a8d663d9aa\nvintages/PAYEMS_vintage_2026-05-31.csv (1048, 2) 1939-01-01 2026-04-01 na {'observation_date': 0, 'PAYEMS_20260531': 0} dup 0 gaps 0 e2a152e87413\nvintages/PAYEMS_vintage_2026-06-30.csv (1049, 2) 1939-01-01 2026-05-01 na {'observation_date': 0, 'PAYEMS_20260630': 0} dup 0 gaps 0 19fbc6cd3547\nvintages/PAYEMS_vintage_2026-07-31.csv (1050, 2) 1939-01-01 2026-06-01 na {'observation_date': 0, 'PAYEMS_20260731': 0} dup 0 gaps 0 3a3a6603fcc3\nvintages/RSAFS_vintage_2025-10-31.csv (404, 2) 1992-01-01 2025-08-01 na {'observation_date': 0, 'RSAFS_20251031': 0} dup 0 gaps 0 3ecb0832a391\nvintages/RSAFS_vintage_2025-11-30.csv (405, 2) 1992-01-01 2025-09-01 na {'observation_date': 0, 'RSAFS_20251130': 0} dup 0 gaps 0 4a683d853746\nvintages/RSAFS_vintage_2025-12-31.csv (406, 2) 1992-01-01 2025-10-01 na {'observation_date': 0, 'RSAFS_20251231': 0} dup 0 gaps 0 436df4b5509b\nvintages/RSAFS_vintage_2026-01-31.csv (407, 2) 1992-01-01 2025-11-01 na {'observation_date': 0, 'RSAFS_20260131': 0} dup 0 gaps 0 b92ab6a5c1db\nvintages/RSAFS_vintage_2026-02-28.csv (408, 2) 1992-01-01 2025-12-01 na {'observation_date': 0, 'RSAFS_20260228': 0} dup 0 gaps 0 2af0a3aaeeba\nvintages/RSAFS_vintage_2026-03-31.csv (409, 2) 1992-01-01 2026-01-01 na {'observation_date': 0, 'RSAFS_20260331': 0} dup 0 gaps 0 0316fdf238d5\nvintages/RSAFS_vintage_2026-04-30.csv (411, 2) 1992-01-01 2026-03-01 na {'observation_date': 0, 'RSAFS_20260430': 0} dup 0 gaps 0 02dcc697a1db\nvintages/RSAFS_vintage_2026-05-31.csv (412, 2) 1992-01-01 2026-04-01 na {'observation_date': 0, 'RSAFS_20260531': 0} dup 0 gaps 0 8c3fe3530213\nvintages/RSAFS_vintage_2026-06-30.csv (413, 2) 1992-01-01 2026-05-01 na {'observation_date': 0, 'RSAFS_20260630': 0} dup 0 gaps 0 2f103157f4a9\nvintages/RSAFS_vintage_2026-07-31.csv (414, 2) 1992-01-01 2026-06-01 na {'observation_date': 0, 'RSAFS_20260731': 0} dup 0 gaps 0 52c04a8fce2e\nRSAFS_current.csv (417, 2) 1992-01-01 2026-09-01 na {'observation_date': 0, 'RSAFS': 0} dup 0 gaps 0 627d8bb386ac\nUMCSENT.csv (887, 2) 1952-11-01 2026-09-01 na {'observation_date': 0, 'UMCSENT': 210} dup 0 gaps 0 3076277f9f21\nfirst_release.csv (28, 5) 2024-06-01 2026-09-01 na {'target_month': 0, 'first_release_vintage': 0, 'level_first_release': 0, 'level_prev_year_same_vintage': 0, 'yoy_first_release': 0} dup 0 gaps 0 1d1ae8b3cacf\n210\n1977-09-01,\n1977-10-01,\n1977-12-01,","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"576e3adf-c849-4cc7-8ac1-d35e9ef72a4e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026/data","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}28{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"0d0ae56c2f010697b4c19bc91c1e08dc4310f036f2282037abcd7e5f97f15c35","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01X7wc9nMqsHftPK4qLEpyka","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob,hashlib\nfor f in sorted(glob.glob('vintages/*.csv'))+['RSAFS_current.csv','UMCSENT.csv','first_release.csv']:\n d=pd.read_csv(f); c=d.columns\n dt=pd.to_datetime(d.iloc[:,0])\n gaps=(dt.diff().dt.days>31).sum()\n print(f,d.shape,dt.min().date(),dt.max().date(),'na',d.isna().sum().to_dict(),'dup',dt.duplicated().sum(),'gaps',gaps, hashlib.sha256(open(f,'rb').read()).hexdigest()[:12])\n\"\ngrep -n ',$' vintages/RSAFS*.csv vintages/PAYEMS*.csv RSAFS_current.csv | head; grep -c ',$' UMCSENT.csv; awk -F, 'NR>1 && $2==\"\" ' UMCSENT.csv | tail -3\n","description":"Audit schema, missing, duplicates, gaps"}}]}}29{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"3ce505b5-15b3-49b6-84fb-888ea6a3b3e2","timestamp":"2026-10-30T06:00:46.879Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"e41f8986-25e1-4276-881f-fd4a78e68844","keep":6,"tail":["0d0ae56c2f010697b4c19bc91c1e08dc4310f036f2282037abcd7e5f97f15c35","8b86d1de7ac5ad6b44fd70efdae61390830960125fdeea60570b32406adc690c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c12b1476776aed5c16e9086f3ef678d5308f5d1e620e5d21441105e61c93ac4b"}30{"parentUuid":"cdcd133c-41ce-4ceb-b0ff-85f8906575d5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXurNjabmYhCK8sXt9wV","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2897,"cache_read_input_tokens":19498,"output_tokens":994,"output_tokens_details":{"thinking_tokens":454},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2897},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4505,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXurNSEFHH94g4usU4VH","requestRef":"3ce505b5-15b3-49b6-84fb-888ea6a3b3e2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7ac5cea2-8c6d-4825-904a-ae1200102091","timestamp":"2026-10-30T06:00:52.820Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026/data","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}31{"parentUuid":"7ac5cea2-8c6d-4825-904a-ae1200102091","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXurNjabmYhCK8sXt9wV","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FaQhxZ6BVS5mVzpyWHhVHV","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob,numpy as np\nvs={}\nfor f in sorted(glob.glob('data/vintages/RSAFS*.csv')):\n d=pd.read_csv(f,parse_dates=[0],index_col=0).iloc[:,0]; vs[f[-14:-4]]=d\ncur=pd.read_csv('data/RSAFS_current.csv',parse_dates=[0],index_col=0).iloc[:,0]\nvs['current']=cur\nD=pd.DataFrame(vs)\npd.set_option('display.width',250)\nprint(D.loc['2024-06':].to_string())\nfr=pd.read_csv('data/first_release.csv',parse_dates=[0,1])\n# check first_release against vintages\nfor _,r in fr.iterrows():\n v=r.first_release_vintage.strftime('%Y-%m-%d')\n if v in vs:\n s=vs[v]; print(r.target_month.date(),v,s.get(r.target_month),r.level_first_release, s.get(r.target_month-pd.DateOffset(years=1)), r.level_prev_year_same_vintage, round(100*np.log(r.level_first_release/r.level_prev_year_same_vintage),6), r.yoy_first_release)\n\"\n","description":"Compare vintages, current and first-release"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2897,"cache_read_input_tokens":19498,"output_tokens":994,"output_tokens_details":{"thinking_tokens":454},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2897},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXurNSEFHH94g4usU4VH","requestRef":"3ce505b5-15b3-49b6-84fb-888ea6a3b3e2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ad93ce44-b16c-493b-8b3e-371aa4a89e6b","timestamp":"2026-10-30T06:00:56.759Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026/data","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"ad93ce44-b16c-493b-8b3e-371aa4a89e6b","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01FaQhxZ6BVS5mVzpyWHhVHV","type":"tool_result","content":" 2025-10-31 2025-11-30 2025-12-31 2026-01-31 2026-02-28 2026-03-31 2026-04-30 2026-05-31 2026-06-30 2026-07-31 current\nobservation_date \n2024-06-01 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 666040\n2024-07-01 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 673662\n2024-08-01 697157.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 670668\n2024-09-01 703079.0 703285.0 703055.0 703055.0 703055.0 703055.0 703055.0 703055.0 703055.0 703055.0 676005\n2024-10-01 707613.0 707613.0 708070.0 708290.0 708290.0 708290.0 708290.0 708290.0 708290.0 708290.0 681808\n2024-11-01 712145.0 712145.0 712145.0 712175.0 711853.0 711853.0 711853.0 711853.0 711853.0 711853.0 685709\n2024-12-01 717662.0 717662.0 717662.0 717662.0 717547.0 717265.0 717265.0 717265.0 717265.0 717265.0 691794\n2025-01-01 711461.0 711461.0 711461.0 711461.0 711461.0 711095.0 711260.0 711260.0 711260.0 711260.0 687058\n2025-02-01 711757.0 711757.0 711757.0 711757.0 711757.0 711757.0 711575.0 711575.0 711575.0 711575.0 683772\n2025-03-01 722572.0 722572.0 722572.0 722572.0 722572.0 722572.0 723350.0 723339.0 723339.0 723339.0 694750\n2025-04-01 721789.0 721789.0 721789.0 721789.0 721789.0 721789.0 721789.0 721903.0 722442.0 722442.0 695464\n2025-05-01 716101.0 716101.0 716101.0 716101.0 716101.0 716101.0 716101.0 716101.0 714568.0 714513.0 685488\n2025-06-01 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 720164.0 691883\n2025-07-01 727414.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 698280\n2025-08-01 732010.0 732059.0 731700.0 731700.0 731700.0 731700.0 731700.0 731700.0 731700.0 731700.0 700407\n2025-09-01 NaN 733258.0 732444.0 732192.0 732192.0 732192.0 732192.0 732192.0 732192.0 732192.0 700948\n2025-10-01 NaN NaN 732633.0 731412.0 731051.0 731051.0 731051.0 731051.0 731051.0 731051.0 700790\n2025-11-01 NaN NaN NaN 735904.0 735085.0 734718.0 734718.0 734718.0 734718.0 734718.0 705453\n2025-12-01 NaN NaN NaN NaN 734967.0 734685.0 734717.0 734717.0 734717.0 734717.0 706264\n2026-01-01 NaN NaN NaN NaN NaN 733537.0 734503.0 734503.0 734503.0 734503.0 701860\n2026-02-01 NaN NaN NaN NaN NaN NaN 739772.0 741278.0 741278.0 741278.0 707959\n2026-03-01 NaN NaN NaN NaN NaN NaN 752063.0 753370.0 754013.0 754013.0 719700\n2026-04-01 NaN NaN NaN NaN NaN NaN NaN 757085.0 757036.0 759097.0 723921\n2026-05-01 NaN NaN NaN NaN NaN NaN NaN NaN 763705.0 766876.0 731415\n2026-06-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN 768553.0 732898\n2026-07-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 729915\n2026-08-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 739322\n2026-09-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 745021\n2025-09-01 2025-11-30 733258 733258 703285 703285 4.17354 4.17354\n2025-10-01 2025-12-31 732633 732633 708070 708070 3.410194 3.410194\n2025-11-01 2026-01-31 735904 735904 712175 712175 3.277601 3.277601\n2025-12-01 2026-02-28 734967 734967 717547 717547 2.398715 2.398715\n2026-01-01 2026-03-31 733537 733537 711095 711095 3.1072 3.1072\n2026-02-01 2026-04-30 739772 739772 711575 711575 3.886121 3.886121\n2026-03-01 2026-04-30 752063 752063 723350 723350 3.89269 3.89269\n2026-04-01 2026-05-31 757085 757085 721903 721903 4.758475 4.758475\n2026-05-01 2026-06-30 763705 763705 714568 714568 6.650342 6.650342\n2026-06-01 2026-07-31 768553 768553 720164 720164 6.503056 6.503056","is_error":false}]},"uuid":"da5423fd-eee4-417f-b922-384d041851e7","timestamp":"2026-10-30T06:00:57.084Z","toolUseResult":{"stdout":" 2025-10-31 2025-11-30 2025-12-31 2026-01-31 2026-02-28 2026-03-31 2026-04-30 2026-05-31 2026-06-30 2026-07-31 current\nobservation_date \n2024-06-01 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 692449.0 666040\n2024-07-01 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 698835.0 673662\n2024-08-01 697157.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 697039.0 670668\n2024-09-01 703079.0 703285.0 703055.0 703055.0 703055.0 703055.0 703055.0 703055.0 703055.0 703055.0 676005\n2024-10-01 707613.0 707613.0 708070.0 708290.0 708290.0 708290.0 708290.0 708290.0 708290.0 708290.0 681808\n2024-11-01 712145.0 712145.0 712145.0 712175.0 711853.0 711853.0 711853.0 711853.0 711853.0 711853.0 685709\n2024-12-01 717662.0 717662.0 717662.0 717662.0 717547.0 717265.0 717265.0 717265.0 717265.0 717265.0 691794\n2025-01-01 711461.0 711461.0 711461.0 711461.0 711461.0 711095.0 711260.0 711260.0 711260.0 711260.0 687058\n2025-02-01 711757.0 711757.0 711757.0 711757.0 711757.0 711757.0 711575.0 711575.0 711575.0 711575.0 683772\n2025-03-01 722572.0 722572.0 722572.0 722572.0 722572.0 722572.0 723350.0 723339.0 723339.0 723339.0 694750\n2025-04-01 721789.0 721789.0 721789.0 721789.0 721789.0 721789.0 721789.0 721903.0 722442.0 722442.0 695464\n2025-05-01 716101.0 716101.0 716101.0 716101.0 716101.0 716101.0 716101.0 716101.0 714568.0 714513.0 685488\n2025-06-01 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 723033.0 720164.0 691883\n2025-07-01 727414.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 727727.0 698280\n2025-08-01 732010.0 732059.0 731700.0 731700.0 731700.0 731700.0 731700.0 731700.0 731700.0 731700.0 700407\n2025-09-01 NaN 733258.0 732444.0 732192.0 732192.0 732192.0 732192.0 732192.0 732192.0 732192.0 700948\n2025-10-01 NaN NaN 732633.0 731412.0 731051.0 731051.0 731051.0 731051.0 731051.0 731051.0 700790\n2025-11-01 NaN NaN NaN 735904.0 735085.0 734718.0 734718.0 734718.0 734718.0 734718.0 705453\n2025-12-01 NaN NaN NaN NaN 734967.0 734685.0 734717.0 734717.0 734717.0 734717.0 706264\n2026-01-01 NaN NaN NaN NaN NaN 733537.0 734503.0 734503.0 734503.0 734503.0 701860\n2026-02-01 NaN NaN NaN NaN NaN NaN 739772.0 741278.0 741278.0 741278.0 707959\n2026-03-01 NaN NaN NaN NaN NaN NaN 752063.0 753370.0 754013.0 754013.0 719700\n2026-04-01 NaN NaN NaN NaN NaN NaN NaN 757085.0 757036.0 759097.0 723921\n2026-05-01 NaN NaN NaN NaN NaN NaN NaN NaN 763705.0 766876.0 731415\n2026-06-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN 768553.0 732898\n2026-07-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 729915\n2026-08-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 739322\n2026-09-01 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 745021\n2025-09-01 2025-11-30 733258 733258 703285 703285 4.17354 4.17354\n2025-10-01 2025-12-31 732633 732633 708070 708070 3.410194 3.410194\n2025-11-01 2026-01-31 735904 735904 712175 712175 3.277601 3.277601\n2025-12-01 2026-02-28 734967 734967 717547 717547 2.398715 2.398715\n2026-01-01 2026-03-31 733537 733537 711095 711095 3.1072 3.1072\n2026-02-01 2026-04-30 739772 739772 711575 711575 3.886121 3.886121\n2026-03-01 2026-04-30 752063 752063 723350 723350 3.89269 3.89269\n2026-04-01 2026-05-31 757085 757085 721903 721903 4.758475 4.758475\n2026-05-01 2026-06-30 763705 763705 714568 714568 6.650342 6.650342\n2026-06-01 2026-07-31 768553 768553 720164 720164 6.503056 6.503056","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ad93ce44-b16c-493b-8b3e-371aa4a89e6b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}33{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"1423c8a62d371bfee428cec26ce0f4ef27f720902187cbf3008ed0cc2031078d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01FaQhxZ6BVS5mVzpyWHhVHV","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob,numpy as np\nvs={}\nfor f in sorted(glob.glob('data/vintages/RSAFS*.csv')):\n d=pd.read_csv(f,parse_dates=[0],index_col=0).iloc[:,0]; vs[f[-14:-4]]=d\ncur=pd.read_csv('data/RSAFS_current.csv',parse_dates=[0],index_col=0).iloc[:,0]\nvs['current']=cur\nD=pd.DataFrame(vs)\npd.set_option('display.width',250)\nprint(D.loc['2024-06':].to_string())\nfr=pd.read_csv('data/first_release.csv',parse_dates=[0,1])\n# check first_release against vintages\nfor _,r in fr.iterrows():\n v=r.first_release_vintage.strftime('%Y-%m-%d')\n if v in vs:\n s=vs[v]; print(r.target_month.date(),v,s.get(r.target_month),r.level_first_release, s.get(r.target_month-pd.DateOffset(years=1)), r.level_prev_year_same_vintage, round(100*np.log(r.level_first_release/r.level_prev_year_same_vintage),6), r.yoy_first_release)\n\"\n","description":"Compare vintages, current and first-release"}}]}}34{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"1b108fc8-a952-4c1a-b170-43f7cab2ec93","timestamp":"2026-10-30T06:00:57.088Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"3ce505b5-15b3-49b6-84fb-888ea6a3b3e2","keep":8,"tail":["1423c8a62d371bfee428cec26ce0f4ef27f720902187cbf3008ed0cc2031078d","2e2836cf9c952cb344371e8365e1247c6a269c55f9dd2600e20834577c3c070a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"dbc3db851b41038bd7de5ac30fd92f5ad8509d6b1844036d6a901dc5049ca8a0"}35{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"da5423fd-eee4-417f-b922-384d041851e7","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}36{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}37{"parentUuid":"da5423fd-eee4-417f-b922-384d041851e7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXus8Lw6VoxRxSy9fFxx","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3045,"cache_read_input_tokens":22395,"output_tokens":2637,"output_tokens_details":{"thinking_tokens":1489},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3045},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":15445,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXus85YfWX7zWPF71f6B","requestRef":"1b108fc8-a952-4c1a-b170-43f7cab2ec93","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5abe99f0-5042-48a9-9a0d-b53b9308a114","timestamp":"2026-10-30T06:01:14.004Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}38{"parentUuid":"5abe99f0-5042-48a9-9a0d-b53b9308a114","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXus8Lw6VoxRxSy9fFxx","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017gMVJhFLiq3MR9zQ8dAu12","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; mkdir -p out/state; cat > out/state/contract.md <<'EOF'\n# Contract — T1-forecast\n\n**Question.** Real-time forecastability of US retail & food services sales (RSAFS) year-over-year log growth g_m = 100 ln(L_m/L_{m-12}) at h = 1 and h = 3 months beyond the last month published in each of 10 month-end ALFRED vintages (2025-10-31 … 2026-07-31), and whether my own model beats the naive (no-change) forecast, errors measured against first-release YoY growth (data/first_release.csv).\n\n**Estimands** (per h ∈ {1,3}, over 10 origins): (a) RMSE and MAE of naive, seasonal naive, AR(1) and my model vs first-release actuals; (b) 1 − RMSE_model/RMSE_naive; (c) DM statistic (model vs naive, squared loss, d_t = e²_naive − e²_model, Bartlett/NW LRV with truncation lag h−1, no HLN correction) and two-sided N(0,1) p-value; (d) mean |g_current − yoy_first_release| over the 10 h=1 target months.\nMeaningful under: forecasts use only information available at each origin; first release is a well-defined actual; with n = 10 the asymptotic DM distribution is only a rough guide.\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (keys per TASK.md table), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues), out/analysis.py (regenerates all from data/ deterministically), out/claims.json. Plus protocol files out/state/*, out/exclusions.csv.\n\n**Information rules.** At origin V: only RSAFS vintage V, PAYEMS vintage V, UMCSENT months ≤ month(V). last(V) = last month in RSAFS vintage V; target = last(V)+h; actual = yoy_first_release of target. RSAFS_current only for (d), never in forecasts. Model selection must not use evaluation outcomes.\n\n**Invalidating conditions.** Missing target months in first_release.csv; vintage leakage (using later vintage / current data); missing vintage files; tuning the model on the 10 evaluation errors.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > out/state/log.md","description":"Write contract, phase ledger, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3045,"cache_read_input_tokens":22395,"output_tokens":2637,"output_tokens_details":{"thinking_tokens":1489},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3045},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXus85YfWX7zWPF71f6B","requestRef":"1b108fc8-a952-4c1a-b170-43f7cab2ec93","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4ffc0c86-e5fc-472f-a125-56e7e258db67","timestamp":"2026-10-30T06:01:23.243Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}39{"parentUuid":"4ffc0c86-e5fc-472f-a125-56e7e258db67","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017gMVJhFLiq3MR9zQ8dAu12","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"2b0ffa0a-c723-4090-9953-e671e2c6424c","timestamp":"2026-10-30T06:01:23.293Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4ffc0c86-e5fc-472f-a125-56e7e258db67","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}40{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"3df19427ebf76b33c9c814c4c91df231aa14f015d28bf531676c22f4ecc3675c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_017gMVJhFLiq3MR9zQ8dAu12","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; mkdir -p out/state; cat > out/state/contract.md <<'EOF'\n# Contract — T1-forecast\n\n**Question.** Real-time forecastability of US retail & food services sales (RSAFS) year-over-year log growth g_m = 100 ln(L_m/L_{m-12}) at h = 1 and h = 3 months beyond the last month published in each of 10 month-end ALFRED vintages (2025-10-31 … 2026-07-31), and whether my own model beats the naive (no-change) forecast, errors measured against first-release YoY growth (data/first_release.csv).\n\n**Estimands** (per h ∈ {1,3}, over 10 origins): (a) RMSE and MAE of naive, seasonal naive, AR(1) and my model vs first-release actuals; (b) 1 − RMSE_model/RMSE_naive; (c) DM statistic (model vs naive, squared loss, d_t = e²_naive − e²_model, Bartlett/NW LRV with truncation lag h−1, no HLN correction) and two-sided N(0,1) p-value; (d) mean |g_current − yoy_first_release| over the 10 h=1 target months.\nMeaningful under: forecasts use only information available at each origin; first release is a well-defined actual; with n = 10 the asymptotic DM distribution is only a rough guide.\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (keys per TASK.md table), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues), out/analysis.py (regenerates all from data/ deterministically), out/claims.json. Plus protocol files out/state/*, out/exclusions.csv.\n\n**Information rules.** At origin V: only RSAFS vintage V, PAYEMS vintage V, UMCSENT months ≤ month(V). last(V) = last month in RSAFS vintage V; target = last(V)+h; actual = yoy_first_release of target. RSAFS_current only for (d), never in forecasts. Model selection must not use evaluation outcomes.\n\n**Invalidating conditions.** Missing target months in first_release.csv; vintage leakage (using later vintage / current data); missing vintage files; tuning the model on the 10 evaluation errors.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > out/state/log.md","description":"Write contract, phase ledger, log"}}]}}41{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"ebed1b77-33ab-4d5f-aab4-a1005ef6b839","timestamp":"2026-10-30T06:01:23.297Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"1b108fc8-a952-4c1a-b170-43f7cab2ec93","keep":10,"tail":["3df19427ebf76b33c9c814c4c91df231aa14f015d28bf531676c22f4ecc3675c","93cc2bda34bf4d12669f2e2ddacbec4171422df4d198834bd9ec04d8186bc7d1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"072c80b7d3880dd310ef9923a099a12d05d746a8183633aa266486df4eac25c8"}42{"parentUuid":"2b0ffa0a-c723-4090-9953-e671e2c6424c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuu4aWsMePdx4RPdDUx","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2652,"cache_read_input_tokens":25440,"output_tokens":564,"output_tokens_details":{"thinking_tokens":98},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2652},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":725,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXuu49UV5FDRupHS5jcC","requestRef":"ebed1b77-33ab-4d5f-aab4-a1005ef6b839","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"38168d2e-d76c-49d0-9cad-61c685c4ca47","timestamp":"2026-10-30T06:01:25.565Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}43{"parentUuid":"38168d2e-d76c-49d0-9cad-61c685c4ca47","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuu4aWsMePdx4RPdDUx","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CAS4WrTfTbvP5NF64WyY8u","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python - <<'EOF' > /tmp/audit_tbl.md\nimport pandas as pd,glob,hashlib\nprint(\"| file | SHA-256 | rows | cols | first | last | missing values | duplicate dates | gaps |\")\nprint(\"|---|---|---|---|---|---|---|---|---|\")\nfor f in sorted(glob.glob('data/vintages/*.csv'))+['data/RSAFS_current.csv','data/UMCSENT.csv','data/first_release.csv']:\n d=pd.read_csv(f); dt=pd.to_datetime(d.iloc[:,0])\n print(f\"| {f[5:]} | {hashlib.sha256(open(f,'rb').read()).hexdigest()} | {len(d)} | {d.shape[1]} | {dt.min().date()} | {dt.max().date()} | {int(d.isna().sum().sum())} | {int(dt.duplicated().sum())} | {int((dt.diff().dt.days>31).sum())} |\")\nEOF\ncat /tmp/audit_tbl.md | head -3","description":"Generate audit table with hashes"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2652,"cache_read_input_tokens":25440,"output_tokens":564,"output_tokens_details":{"thinking_tokens":98},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2652},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXuu49UV5FDRupHS5jcC","requestRef":"ebed1b77-33ab-4d5f-aab4-a1005ef6b839","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"65b1d3ae-f8a7-4b67-bf1a-f1875ffc79cf","timestamp":"2026-10-30T06:01:28.764Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}44{"parentUuid":"65b1d3ae-f8a7-4b67-bf1a-f1875ffc79cf","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01CAS4WrTfTbvP5NF64WyY8u","type":"tool_result","content":"| file | SHA-256 | rows | cols | first | last | missing values | duplicate dates | gaps |\n|---|---|---|---|---|---|---|---|---|\n| vintages/PAYEMS_vintage_2025-10-31.csv | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 | 1040 | 2 | 1939-01-01 | 2025-08-01 | 0 | 0 | 0 |","is_error":false}]},"uuid":"31049f4a-c6a7-493c-a9b4-16067c306b5b","timestamp":"2026-10-30T06:01:29.091Z","toolUseResult":{"stdout":"| file | SHA-256 | rows | cols | first | last | missing values | duplicate dates | gaps |\n|---|---|---|---|---|---|---|---|---|\n| vintages/PAYEMS_vintage_2025-10-31.csv | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 | 1040 | 2 | 1939-01-01 | 2025-08-01 | 0 | 0 | 0 |","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"65b1d3ae-f8a7-4b67-bf1a-f1875ffc79cf","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}45{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"71bb88cdfe7b8f37eddb1d7d112d6239725c93434438550e8b4bb44ac5faca66","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSuQcKEAgTGAI4AUIIdGhpbmtpbmcSDDjp+l4Cz8trsp+oshoMHLMjn68H3Eg6jP+JIjCUMeIv4Lr7K7WGN2aUKLE530s0n/r9zGr+Dxf6PI3AKu1F1BksxeFBP3wQSYnwUT4q1gaTT18VrjWZZbYkqAEmDl5+8PLqZVBcaIrg7Eszs23cX2fQ5qwYgj8BGfKKKaSJr1j4Vni6Q7laeEa30FaEm3gCgUGf6Duq8ol/8lG38IdsKFDT7GAGvnjqtnoVHCoGQrf+gAK3GA+fS3LvNhXnUapftnTKUvKeH4VzUBKEwryfc9WmiFerZ4B68oPjBOgZtZEN2n16JX4tW6pMlQFt67BCjtr+iBdbb5zcX3Uj6CdfSFdO7DPYPlOyLZ46vnomSdD2T6ruQIe/I2IdpRryM+rSwR70HnWybnE1eF0stJG8DdRrkrMrcRsj4Rk+YtOkFdCiVsgxa4c3LcqGMqNvplpX6hJBotaci9816wnC7eB47ffs1gQI3LtAZ07Y/ep3MMhk/cd21Oe+L178o9zF8oAKbnWpwv64PM3KHWpZS0qqyCEfM1big1Hl/mw2f1aMIKXmP6sGqaU86vCWNAd1DxUZv51WU2FrvJGi7cPNhvTeKw7VJoUFoNwZZXPW6A7JLxG9QvWnUzw6VGal330G8OXZyAAMEXFxJvE1ne7ZIjeqnzUVHCutnWkHTIqa/bu4Ws3Em/5DYFYNq//qdjJgE0TW+NGqICg3MV3EW7qiuzcBhGa8S9gfUO/wlvvuo2HjMT0usO/T/hjWLIer5h71o3FOIZAxHNtOsMTr1EwrK4nH5ofwIB9+e+HOkENgXWVptAgfTCLeJ7wQSBGax+fE4OOySVK+XfOShLBKFbTpgvX3cb/Wbo2CaIWySv34T9xvKto5dpM7jYnVTnmfTWRjlgCgG3EBg6GK54UBjlnQaU54s+QGs3mCrA+KOvJYknYU0CAGSUF1ngAqnwZ9fDHB4YMvJxzBGVc9skBc7+VKlcr2rDJ7RMBEKGRLKOSqTB+bOyDz2Q6UMjq62oZWYWHghkm95QAr6iVog3qp8lQVMp9tqXCL9j49PGYPGS2n/VtnqTPC3N8nXuvRHkdVJYoUmjc/yFY+naDWjZy77mfjnjsKTuG9zYllxMLxoid8pL+E6RQWwy4k8I/B0CEufVKlm5qyqBYoB0xHxsI7GRpQLG1x8h62QaZeLPNE0Yqq7ZLaNeQrM9toQV6V9xIL8/MGq/FTpz9DeodnCqi7szfgDOlAEEMtP9GqiBgB"},{"type":"tool_use","id":"toolu_01CAS4WrTfTbvP5NF64WyY8u","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python - <<'EOF' > /tmp/audit_tbl.md\nimport pandas as pd,glob,hashlib\nprint(\"| file | SHA-256 | rows | cols | first | last | missing values | duplicate dates | gaps |\")\nprint(\"|---|---|---|---|---|---|---|---|---|\")\nfor f in sorted(glob.glob('data/vintages/*.csv'))+['data/RSAFS_current.csv','data/UMCSENT.csv','data/first_release.csv']:\n d=pd.read_csv(f); dt=pd.to_datetime(d.iloc[:,0])\n print(f\"| {f[5:]} | {hashlib.sha256(open(f,'rb').read()).hexdigest()} | {len(d)} | {d.shape[1]} | {dt.min().date()} | {dt.max().date()} | {int(d.isna().sum().sum())} | {int(dt.duplicated().sum())} | {int((dt.diff().dt.days>31).sum())} |\")\nEOF\ncat /tmp/audit_tbl.md | head -3","description":"Generate audit table with hashes"}}]}}46{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"6e623995-e388-4c89-9329-e3230da25180","timestamp":"2026-10-30T06:01:29.094Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"ebed1b77-33ab-4d5f-aab4-a1005ef6b839","keep":12,"tail":["71bb88cdfe7b8f37eddb1d7d112d6239725c93434438550e8b4bb44ac5faca66","9ccb314419ff31e5c94aac6b55688b996a49be22484ea0902ff8aac2e03e3bbb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3c97e27523783fe671d1d363caff699978e1847d7dbd3f5e9da7a9d445502981"}47{"parentUuid":"31049f4a-c6a7-493c-a9b4-16067c306b5b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuuVJ4wVh7p4szTJZnw","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XNNHX3syZdR8kbCUTkz7WD","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; { cat <<'EOF'\n# Data audit — T1-forecast\n\nAll SHA-256 hashes below were recomputed and match `data/README.md` and `bundle.json`. Row counts = data rows after header.\n\nEOF\ncat /tmp/audit_tbl.md\ncat <<'EOF'\n\n## Schema and units\n- RSAFS vintages / current: `observation_date` (YYYY-MM-01), level in millions of USD, SA. Integers, no missing values, no duplicate dates, no internal gaps.\n- PAYEMS vintages: thousands of persons, SA, 1939-01 onward, complete.\n- UMCSENT: index 1966Q1=100; 210 empty fields, all before 1978 (quarterly survey period; last empty 1977-12). Complete from 1978-01 to 2026-09.\n- first_release.csv: 28 target months 2024-06 … 2026-09; recomputing 100·ln(level_first_release/level_prev_year_same_vintage) reproduces `yoy_first_release` to 6 decimals; for the 10 rows whose first_release_vintage is one of the shipped vintages, the levels match the shipped vintage files exactly.\n\n## Real-time design: last(V) per origin (RSAFS)\n| origin V | last(V) | gap (months before V) | h=1 target | h=3 target |\n|---|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2 (delayed) | 2025-09 | 2025-11 |\n| 2025-11-30 | 2025-09 | 2 (delayed) | 2025-10 | 2025-12 |\n| 2025-12-31 | 2025-10 | 2 (delayed) | 2025-11 | 2026-01 |\n| 2026-01-31 | 2025-11 | 2 (delayed) | 2025-12 | 2026-02 |\n| 2026-02-28 | 2025-12 | 2 (delayed) | 2026-01 | 2026-03 |\n| 2026-03-31 | 2026-01 | 2 (delayed) | 2026-02 | 2026-04 |\n| 2026-04-30 | 2026-03 | 1 (two months added at once) | 2026-04 | 2026-06 |\n| 2026-05-31 | 2026-04 | 1 | 2026-05 | 2026-07 |\n| 2026-06-30 | 2026-05 | 1 | 2026-06 | 2026-08 |\n| 2026-07-31 | 2026-06 | 1 | 2026-07 | 2026-09 |\n\nAll 20 target months are present in first_release.csv. Because of the publication delays the target months are not evenly spaced in calendar time (h=3 targets skip 2026-05; h=1 targets skip 2026-03).\n\n## Anomalies / issues\n1. **Irregular publication timing** (2025 federal shutdown period): vintages 2025-10-31 … 2026-03-31 end two months before the vintage date; 2026-04-30 adds 2026-02 and 2026-03 at once. Handled by defining targets relative to last(V), as TASK.md prescribes. The first-release dates of 2025-09 (2025-11-30 vintage) and 2026-02 (2026-04-30 vintage, same as 2026-03) reflect this.\n2. **Revisions inside the vintage grid**: the last ~3 months are revised at each vintage (e.g. 2026-05 level 763705 → 766876). Real-time forecasts use the vintage values as published; actuals are first releases.\n3. **Large level shift (benchmark/annual revision) in later data**: RSAFS_current levels are ~3.5–4% below the 2026-07-31 vintage for all months shown from 2024-06 on; first_release.csv shows the shift between the 2026-08-31 and 2026-09-30 vintages (2026-07 first-release level 763602 vs current 729915; 2026-08 base-year level 700218 vs 731700 in shipped vintages). YoY growth is computed within one vintage, so the level shift largely cancels, but it inflates estimand (d) and means the h=3 actuals for the last two origins (2026-08, 2026-09) come from post-revision vintages. Documented, not corrected (the task defines the actual).\n4. PAYEMS publication was also delayed (vintage 2025-10-31 ends 2025-08; 2025-12-31 adds 2025-10 and 2025-11). Not used by my model.\n5. UMCSENT is a current-vintage file; per README it is not revised, so restricting to months ≤ month(V) is real-time. Not used by my model.\n\n## Availability-rule violations in the inputs\n- `RSAFS_current.csv` contains post-origin information; it is read only for estimand (d).\n- `first_release.csv` contains post-origin information; used only as the evaluation actual.\n- No other violation. No rows are excluded (see out/exclusions.csv).\nEOF\n} > out/state/data_audit.md\ncat > out/exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,\"keep (origin,horizon,model) forecast-actual pairs with a first-release actual available\",80,80,0,\"all 20 target months present in first_release.csv; nothing removed\"\nEOF\necho \"- 2026-10-30 P1: data audit done; no exclusions; decision: model uses RSAFS vintage only (base-effect drift model), PAYEMS/UMCSENT not used; RSAFS_current only for (d).\" >> out/state/log.md","description":"Write data audit and exclusion ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":732,"cache_read_input_tokens":28092,"output_tokens":1952,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":732},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXuuUwUXcPWJaCtfNeRG","requestRef":"6e623995-e388-4c89-9329-e3230da25180","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cc818b42-2fd5-40a1-8db0-c454b1e6ebb8","timestamp":"2026-10-30T06:01:45.714Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"cc818b42-2fd5-40a1-8db0-c454b1e6ebb8","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01XNNHX3syZdR8kbCUTkz7WD","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"b06d2faa-3e21-4b22-bf51-e509b92928ed","timestamp":"2026-10-30T06:01:45.764Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"cc818b42-2fd5-40a1-8db0-c454b1e6ebb8","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}49{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"4d6dd9172337f9057a1da0c52eae77349522cad1eac371529cd9b21d1c4f9579","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01XNNHX3syZdR8kbCUTkz7WD","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; { cat <<'EOF'\n# Data audit — T1-forecast\n\nAll SHA-256 hashes below were recomputed and match `data/README.md` and `bundle.json`. Row counts = data rows after header.\n\nEOF\ncat /tmp/audit_tbl.md\ncat <<'EOF'\n\n## Schema and units\n- RSAFS vintages / current: `observation_date` (YYYY-MM-01), level in millions of USD, SA. Integers, no missing values, no duplicate dates, no internal gaps.\n- PAYEMS vintages: thousands of persons, SA, 1939-01 onward, complete.\n- UMCSENT: index 1966Q1=100; 210 empty fields, all before 1978 (quarterly survey period; last empty 1977-12). Complete from 1978-01 to 2026-09.\n- first_release.csv: 28 target months 2024-06 … 2026-09; recomputing 100·ln(level_first_release/level_prev_year_same_vintage) reproduces `yoy_first_release` to 6 decimals; for the 10 rows whose first_release_vintage is one of the shipped vintages, the levels match the shipped vintage files exactly.\n\n## Real-time design: last(V) per origin (RSAFS)\n| origin V | last(V) | gap (months before V) | h=1 target | h=3 target |\n|---|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2 (delayed) | 2025-09 | 2025-11 |\n| 2025-11-30 | 2025-09 | 2 (delayed) | 2025-10 | 2025-12 |\n| 2025-12-31 | 2025-10 | 2 (delayed) | 2025-11 | 2026-01 |\n| 2026-01-31 | 2025-11 | 2 (delayed) | 2025-12 | 2026-02 |\n| 2026-02-28 | 2025-12 | 2 (delayed) | 2026-01 | 2026-03 |\n| 2026-03-31 | 2026-01 | 2 (delayed) | 2026-02 | 2026-04 |\n| 2026-04-30 | 2026-03 | 1 (two months added at once) | 2026-04 | 2026-06 |\n| 2026-05-31 | 2026-04 | 1 | 2026-05 | 2026-07 |\n| 2026-06-30 | 2026-05 | 1 | 2026-06 | 2026-08 |\n| 2026-07-31 | 2026-06 | 1 | 2026-07 | 2026-09 |\n\nAll 20 target months are present in first_release.csv. Because of the publication delays the target months are not evenly spaced in calendar time (h=3 targets skip 2026-05; h=1 targets skip 2026-03).\n\n## Anomalies / issues\n1. **Irregular publication timing** (2025 federal shutdown period): vintages 2025-10-31 … 2026-03-31 end two months before the vintage date; 2026-04-30 adds 2026-02 and 2026-03 at once. Handled by defining targets relative to last(V), as TASK.md prescribes. The first-release dates of 2025-09 (2025-11-30 vintage) and 2026-02 (2026-04-30 vintage, same as 2026-03) reflect this.\n2. **Revisions inside the vintage grid**: the last ~3 months are revised at each vintage (e.g. 2026-05 level 763705 → 766876). Real-time forecasts use the vintage values as published; actuals are first releases.\n3. **Large level shift (benchmark/annual revision) in later data**: RSAFS_current levels are ~3.5–4% below the 2026-07-31 vintage for all months shown from 2024-06 on; first_release.csv shows the shift between the 2026-08-31 and 2026-09-30 vintages (2026-07 first-release level 763602 vs current 729915; 2026-08 base-year level 700218 vs 731700 in shipped vintages). YoY growth is computed within one vintage, so the level shift largely cancels, but it inflates estimand (d) and means the h=3 actuals for the last two origins (2026-08, 2026-09) come from post-revision vintages. Documented, not corrected (the task defines the actual).\n4. PAYEMS publication was also delayed (vintage 2025-10-31 ends 2025-08; 2025-12-31 adds 2025-10 and 2025-11). Not used by my model.\n5. UMCSENT is a current-vintage file; per README it is not revised, so restricting to months ≤ month(V) is real-time. Not used by my model.\n\n## Availability-rule violations in the inputs\n- `RSAFS_current.csv` contains post-origin information; it is read only for estimand (d).\n- `first_release.csv` contains post-origin information; used only as the evaluation actual.\n- No other violation. No rows are excluded (see out/exclusions.csv).\nEOF\n} > out/state/data_audit.md\ncat > out/exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,\"keep (origin,horizon,model) forecast-actual pairs with a first-release actual available\",80,80,0,\"all 20 target months present in first_release.csv; nothing removed\"\nEOF\necho \"- 2026-10-30 P1: data audit done; no exclusions; decision: model uses RSAFS vintage only (base-effect drift model), PAYEMS/UMCSENT not used; RSAFS_current only for (d).\" >> out/state/log.md","description":"Write data audit and exclusion ledger"}}]}}50{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"0bbd4007-04d4-44f2-911c-9b1fbfa79d94","timestamp":"2026-10-30T06:01:45.769Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"6e623995-e388-4c89-9329-e3230da25180","keep":14,"tail":["4d6dd9172337f9057a1da0c52eae77349522cad1eac371529cd9b21d1c4f9579","0ae30b375721557a1bd778436e2f996337c7a4b2a32c04ee3198ae8630996008"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b863cddf6a868b6dba69b34fc9b2976b8a57bac2a0b6c20bddc110a875299f2e"}51{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"b06d2faa-3e21-4b22-bf51-e509b92928ed","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}52{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}53{"parentUuid":"b06d2faa-3e21-4b22-bf51-e509b92928ed","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuviaoRrorgYAQNPbuM","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1967,"cache_read_input_tokens":28824,"output_tokens":6172,"output_tokens_details":{"thinking_tokens":401},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1967},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3504,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXuviJB3wGKr88BLtNMn","requestRef":"0bbd4007-04d4-44f2-911c-9b1fbfa79d94","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a25a262d-a4b7-4bcc-b72e-95f6457bc6ed","timestamp":"2026-10-30T06:01:50.753Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"a25a262d-a4b7-4bcc-b72e-95f6457bc6ed","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuviaoRrorgYAQNPbuM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PfFt2bhUmPjh1LZQqBiUcn","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\n\nRun from the workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png.\n\"\"\"\nimport json\nimport os\nimport glob\n\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA = \"data\"\nOUT = \"out\"\nSEED = 20261030\nB_BOOT = 9999\nBLOCK = 3\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\n\n\ndef read_series(path):\n d = pd.read_csv(path, parse_dates=[0], index_col=0)\n s = d.iloc[:, 0].astype(float)\n s.index = s.index.to_period(\"M\")\n return s\n\n\ndef n_rows(path):\n with open(path) as f:\n return sum(1 for _ in f) - 1\n\n\ndef yoy(level):\n return 100.0 * (np.log(level) - np.log(level.shift(12)))\n\n\ndef forecasts_for_origin(V):\n \"\"\"All forecasts at origin V use ONLY the RSAFS vintage dated V.\"\"\"\n L = read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"))\n assert L.index.is_monotonic_increasing and L.index.is_unique\n assert (L.index[1:] - L.index[:-1] == 1 * L.index.freq).all() if False else True\n last = L.index[-1]\n g = yoy(L)\n lnL = np.log(L)\n out = {}\n # AR(1) on g over 1993-02 <= m <= last (consecutive pairs; g starts 1993-01)\n gs = g.loc[pd.Period(\"1993-01\", \"M\"):last]\n y = gs.loc[pd.Period(\"1993-02\", \"M\"):].values\n x = gs.shift(1).loc[pd.Period(\"1993-02\", \"M\"):].values\n X = np.column_stack([np.ones_like(x), x])\n c, phi = np.linalg.lstsq(X, y, rcond=None)[0]\n # model: base-effect drift. log level path extrapolated with trailing-12m mean monthly log change\n mu = (lnL.loc[last] - lnL.loc[last - 12]) / 12.0\n for h in HORIZONS:\n T = last + h\n f_naive = g.loc[last]\n f_snaive = g.loc[T - 12]\n f = g.loc[last]\n for _ in range(h):\n f = c + phi * f\n f_ar1 = f\n f_model = 100.0 * (lnL.loc[last] + h * mu - lnL.loc[T - 12])\n out[h] = dict(target=T, naive=f_naive, snaive=f_snaive, ar1=f_ar1, model=f_model)\n return last, out, (c, phi)\n\n\ndef dm_test(e_naive, e_model, h):\n d = e_naive ** 2 - e_model ** 2\n n = len(d)\n dbar = d.mean()\n dc = d - dbar\n lrv = np.sum(dc * dc) / n\n for k in range(1, h): # truncation lag h-1, Bartlett weights 1 - k/h\n w = 1.0 - k / h\n lrv += 2.0 * w * np.sum(dc[k:] * dc[:-k]) / n\n stat = dbar / np.sqrt(lrv / n)\n p = 2.0 * (1.0 - stats.norm.cdf(abs(stat)))\n return float(stat), float(p), float(dbar), float(lrv)\n\n\ndef block_boot_rmse_diff(e_naive, e_model, rng):\n n = len(e_naive)\n nb = int(np.ceil(n / BLOCK))\n diffs = np.empty(B_BOOT)\n for b in range(B_BOOT):\n starts = rng.integers(0, n, nb)\n idx = np.concatenate([(s + np.arange(BLOCK)) % n for s in starts])[:n]\n diffs[b] = np.sqrt(np.mean(e_model[idx] ** 2)) - np.sqrt(np.mean(e_naive[idx] ** 2))\n return float(np.percentile(diffs, 2.5)), float(np.percentile(diffs, 97.5)), float(np.mean(diffs < 0))\n\n\ndef main():\n os.makedirs(OUT, exist_ok=True)\n fr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\n fr[\"T\"] = fr[\"target_month\"].dt.to_period(\"M\")\n actual = dict(zip(fr[\"T\"], fr[\"yoy_first_release\"]))\n\n rows = []\n lasts = {}\n arcoef = {}\n for V in ORIGINS:\n last, fc, cp = forecasts_for_origin(V)\n lasts[V] = last\n arcoef[V] = cp\n for h in HORIZONS:\n T = fc[h][\"target\"]\n if T not in actual:\n raise RuntimeError(f\"missing first-release actual for {T}\")\n for m in MODELS:\n rows.append(dict(origin_date=V, target_date=T.to_timestamp().strftime(\"%Y-%m-%d\"),\n horizon=h, forecast=round(float(fc[h][m]), 10),\n actual_first_release=float(actual[T]), model=m, vintage_used=V))\n F = pd.DataFrame(rows)\n F[\"error\"] = F[\"actual_first_release\"] - F[\"forecast\"]\n F.drop(columns=\"error\").to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False)\n\n res = {\"task_id\": \"T1-forecast\",\n \"model_name\": \"base-effect drift (BED)\",\n \"model_description\": (\n \"Forecast of the log level of RSAFS at T = last(V)+h from the RSAFS vintage dated V only: \"\n \"ln L_hat_T = ln L_last + h*mu, where mu = (ln L_last - ln L_{last-12})/12 is the trailing-12-month \"\n \"mean monthly log change in the same vintage (i.e. the latest YoY growth spread evenly over months). \"\n \"The YoY forecast is g_hat_T = 100*(ln L_hat_T - ln L_{T-12}), where L_{T-12} (always <= last(V) since h<=3) \"\n \"is the base-period level as published in vintage V. Equivalently: naive forecast plus the known \"\n \"base effect (drop-out of the monthly log changes of months last-11..last-12+h) plus h months of drift. \"\n \"No parameters are estimated on the evaluation sample; the specification was fixed before computing any \"\n \"out-of-sample error and no variant was compared. PAYEMS and UMCSENT are not used; RSAFS_current and \"\n \"first_release.csv never enter any forecast.\"),\n \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\n t1 = []\n for m in MODELS:\n for h in HORIZONS:\n e = F[(F.model == m) & (F.horizon == h)][\"error\"].values\n rmse = float(np.sqrt(np.mean(e ** 2)))\n mae = float(np.mean(np.abs(e)))\n res[f\"rmse_{m}_h{h}\"] = rmse\n res[f\"mae_{m}_h{h}\"] = mae\n t1.append(dict(model=m, horizon=h, rmse=rmse, mae=mae, n=len(e)))\n pd.DataFrame(t1).to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n rng = np.random.default_rng(SEED)\n extra = {}\n for h in HORIZONS:\n en = F[(F.model == \"naive\") & (F.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n em = F[(F.model == \"model\") & (F.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n res[f\"rel_improvement_rmse_h{h}\"] = 1.0 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n stat, p, dbar, lrv = dm_test(en, em, h)\n res[f\"dm_stat_h{h}\"] = stat\n res[f\"dm_pvalue_h{h}\"] = p\n better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n sig = \"significant\" if p < 0.05 else \"not_significant\"\n res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n lo, hi, share = block_boot_rmse_diff(en, em, rng)\n extra[f\"dm_mean_loss_diff_h{h}\"] = dbar\n extra[f\"dm_lrv_h{h}\"] = lrv\n extra[f\"boot_rmse_diff_lo_h{h}\"] = lo\n extra[f\"boot_rmse_diff_hi_h{h}\"] = hi\n extra[f\"boot_share_model_better_h{h}\"] = share\n extra[f\"n_model_wins_h{h}\"] = int(np.sum(em ** 2 < en ** 2))\n\n # estimand (d): revision of h=1 targets, current vintage vs first release\n cur = read_series(os.path.join(DATA, \"RSAFS_current.csv\"))\n gcur = yoy(cur)\n t_h1 = [pd.Period(t, \"M\") for t in F[(F.model == \"naive\") & (F.horizon == 1)][\"target_date\"].str[:7]]\n revs = np.array([abs(gcur.loc[T] - actual[T]) for T in t_h1])\n res[\"mean_abs_revision_h1_targets\"] = float(revs.mean())\n extra[\"mean_signed_revision_h1_targets\"] = float(np.mean([gcur.loc[T] - actual[T] for T in t_h1]))\n extra[\"max_abs_revision_h1_targets\"] = float(revs.max())\n\n res[\"feasibility\"] = \"complete\"\n res[\"feasibility_reason\"] = None\n res[\"data_issues\"] = [\n {\"issue\": \"Irregular RSAFS publication timing: vintages 2025-10-31 to 2026-03-31 end two months before the vintage date; the 2026-04-30 vintage adds 2026-02 and 2026-03 at once.\",\n \"handling\": \"Targets defined as last(V)+h from the last month actually present in each vintage, as TASK.md prescribes; target months are therefore unevenly spaced (h=1 skips 2026-03, h=3 skips 2026-05).\"},\n {\"issue\": \"Recent months are revised from vintage to vintage (e.g. 2026-05 level 763705 in the 2026-06-30 vintage, 766876 in 2026-07-31).\",\n \"handling\": \"Each forecast uses the values as published in its own vintage; actuals are first releases from first_release.csv.\"},\n {\"issue\": \"Large downward level revision (about 3.5-4%) between the 2026-08-31 and 2026-09-30 vintages, visible in first_release.csv (2026-08 base-year level 700218 vs 731700 in shipped vintages) and in RSAFS_current.\",\n \"handling\": \"YoY growth is always computed within a single vintage so the level shift mostly cancels; not corrected. It affects the h=3 actuals of the last two origins (2026-08, 2026-09) and estimand (d).\"},\n {\"issue\": \"PAYEMS publication also delayed (2025-10-31 vintage ends 2025-08; 2025-12-31 adds two months).\",\n \"handling\": \"PAYEMS not used by the model; recorded only.\"},\n {\"issue\": \"UMCSENT has 210 empty fields, all before 1978 (quarterly survey era); file is current vintage.\",\n \"handling\": \"UMCSENT not used by the model; recorded only.\"},\n {\"issue\": \"RSAFS_current.csv and first_release.csv contain post-origin information.\",\n \"handling\": \"RSAFS_current used only for estimand (d); first_release only as evaluation actual.\"},\n ]\n files = sorted(glob.glob(os.path.join(DATA, \"vintages\", \"*.csv\"))) + [\n os.path.join(DATA, f) for f in (\"RSAFS_current.csv\", \"UMCSENT.csv\", \"first_release.csv\")]\n # PAYEMS and UMCSENT files are read only for the audit row counts (they do not enter forecasts)\n res[\"n_input_rows\"] = {os.path.relpath(f, DATA): n_rows(f) for f in files}\n res[\"n_analysed\"] = int(len(F[F.model == \"model\"]))\n res[\"random_seed\"] = SEED\n res.update(extra)\n res[\"block_bootstrap\"] = {\"B\": B_BOOT, \"block_length\": BLOCK, \"type\": \"circular moving-block, paired errors\"}\n res[\"last_month_by_origin\"] = {V: str(lasts[V]) for V in ORIGINS}\n res[\"ar1_coef_by_origin\"] = {V: {\"const\": float(arcoef[V][0]), \"phi\": float(arcoef[V][1])} for V in ORIGINS}\n res[\"abs_revision_by_h1_target\"] = {str(T): float(r) for T, r in zip(t_h1, revs)}\n\n with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\n # figure\n fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\n for ax, h in zip(axes, HORIZONS):\n sub = F[F.horizon == h]\n a = sub[sub.model == \"naive\"].sort_values(\"target_date\")\n x = pd.to_datetime(a[\"target_date\"])\n ax.plot(x, a[\"actual_first_release\"], \"k-o\", label=\"first-release actual\")\n for m, st in ((\"naive\", \"b--s\"), (\"model\", \"r-.^\")):\n s = sub[sub.model == m].sort_values(\"target_date\")\n ax.plot(pd.to_datetime(s[\"target_date\"]), s[\"forecast\"], st,\n label=f\"{m} (RMSE {res[f'rmse_{m}_h{h}']:.2f})\" if m == \"naive\" else\n f\"BED model (RMSE {res[f'rmse_{m}_h{h}']:.2f})\")\n ax.set_title(f\"h = {h}\")\n ax.set_ylabel(\"YoY growth, % (100 ln)\")\n ax.grid(alpha=0.3)\n ax.legend(fontsize=8)\n ax.tick_params(axis=\"x\", rotation=45)\n fig.suptitle(\"RSAFS YoY growth: real-time forecasts vs first release (10 origins, 2025-10-31 to 2026-07-31)\")\n fig.tight_layout()\n fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n plt.close(fig)\n\n for h in HORIZONS:\n print(f\"h={h}: \" + \", \".join(f\"{m} RMSE={res[f'rmse_{m}_h{h}']:.4f}\" for m in MODELS)\n + f\"; DM={res[f'dm_stat_h{h}']:.3f} p={res[f'dm_pvalue_h{h}']:.3f} -> {res[f'conclusion_code_h{h}']}\")\n print(f\"mean abs revision (h=1 targets) = {res['mean_abs_revision_h1_targets']:.4f}\")\n\n\nif __name__ == \"__main__\":\n main()\nEOF\nsed -i '' '/is_monotonic_increasing/{n;d;}' out/analysis.py; grep -n \"if False\" out/analysis.py; ~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv && column -s, -t out/forecasts.csv | head -90","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1967,"cache_read_input_tokens":28824,"output_tokens":6172,"output_tokens_details":{"thinking_tokens":401},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1967},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXuviJB3wGKr88BLtNMn","requestRef":"0bbd4007-04d4-44f2-911c-9b1fbfa79d94","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"55605a43-f1db-482b-bb31-61abbd23b5ad","timestamp":"2026-10-30T06:02:32.599Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}55{"parentUuid":"55605a43-f1db-482b-bb31-61abbd23b5ad","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PfFt2bhUmPjh1LZQqBiUcn","type":"tool_result","content":"h=1: naive RMSE=0.9969, snaive RMSE=1.6745, ar1 RMSE=0.9405, model RMSE=0.5503; DM=2.429 p=0.015 -> model_better_significant\nh=3: naive RMSE=1.4200, snaive RMSE=1.3161, ar1 RMSE=1.1871, model RMSE=1.1422; DM=1.547 p=0.122 -> model_better_not_significant\nmean abs revision (h=1 targets) = 0.5482\nmodel,horizon,rmse,mae,n\nnaive,1,0.9968743518549719,0.8487221879899998,10\nnaive,3,1.420040373740657,1.2004486337699998,10\nsnaive,1,1.6745428991300964,1.30666987625,10\nsnaive,3,1.3160788989366212,1.06586869147,10\nar1,1,0.9405244111134986,0.7976510573200001,10\nar1,3,1.1871178147503472,0.9526895961500002,10\nmodel,1,0.5502977033465031,0.4863319392900001,10\nmodel,3,1.1422197516160006,0.9339774440799996,10\norigin_date target_date horizon forecast actual_first_release model vintage_used\n2025-10-31 2025-09-01 1 4.8783538599 4.17354 naive 2025-10-31\n2025-10-31 2025-09-01 1 1.9643255347 4.17354 snaive 2025-10-31\n2025-10-31 2025-09-01 1 4.821775512 4.17354 ar1 2025-10-31\n2025-10-31 2025-09-01 1 4.4390208923 4.17354 model 2025-10-31\n2025-10-31 2025-11-01 3 4.8783538599 3.277601 naive 2025-10-31\n2025-10-31 2025-11-01 3 3.8383986588 3.277601 snaive 2025-10-31\n2025-10-31 2025-11-01 3 4.7343454616 3.277601 ar1 2025-10-31\n2025-10-31 2025-11-01 3 3.9708517357 3.277601 model 2025-10-31\n2025-11-30 2025-10-01 1 4.1735403067 3.410194 naive 2025-11-30\n2025-11-30 2025-10-01 1 3.0803986182 3.410194 snaive 2025-11-30\n2025-11-30 2025-10-01 1 4.2282014336 3.410194 ar1 2025-11-30\n2025-11-30 2025-10-01 1 3.9078234306 3.410194 model 2025-11-30\n2025-11-30 2025-12-01 3 4.1735403067 2.398715 naive 2025-11-30\n2025-11-30 2025-12-01 3 4.4717369808 2.398715 snaive 2025-11-30\n2025-11-30 2025-12-01 3 4.3126650647 2.398715 ar1 2025-11-30\n2025-11-30 2025-12-01 3 3.1932762775 2.398715 model 2025-11-30\n2025-12-31 2025-11-01 1 3.4101935512 3.277601 naive 2025-12-31\n2025-12-31 2025-11-01 1 3.8383986588 3.277601 snaive 2025-12-31\n2025-12-31 2025-11-01 1 3.5849322197 3.277601 ar1 2025-12-31\n2025-12-31 2025-11-01 1 3.1205179971 3.277601 model 2025-12-31\n2025-12-31 2026-01-01 3 3.4101935512 3.1072 naive 2025-12-31\n2025-12-31 2026-01-01 3 4.4557440592 3.1072 snaive 2025-12-31\n2025-12-31 2026-01-01 3 3.8549609369 3.1072 ar1 2025-12-31\n2025-12-31 2026-01-01 3 3.7849775999 3.1072 model 2025-12-31\n2026-01-31 2025-12-01 1 3.2776007711 2.398715 naive 2026-01-31\n2026-01-31 2025-12-01 1 4.4717369808 2.398715 snaive 2026-01-31\n2026-01-31 2025-12-01 1 3.4726686566 2.398715 ar1 2026-01-31\n2026-01-31 2025-12-01 1 2.7832303294 2.398715 model 2026-01-31\n2026-01-31 2026-02-01 3 3.2776007711 3.886121 naive 2026-01-31\n2026-01-31 2026-02-01 3 3.7909047157 3.886121 snaive 2026-01-31\n2026-01-31 2026-02-01 3 3.7741287847 3.886121 ar1 2026-01-31\n2026-01-31 2026-02-01 3 4.1557116343 3.886121 model 2026-01-31\n2026-02-28 2026-01-01 1 2.3987149531 3.1072 naive 2026-02-28\n2026-02-28 2026-01-01 1 4.4557440592 3.1072 snaive 2026-02-28\n2026-02-28 2026-01-01 1 2.731302727 3.1072 ar1 2026-02-28\n2026-02-28 2026-01-01 1 3.4503927119 3.1072 model 2026-02-28\n2026-02-28 2026-03-01 3 2.3987149531 3.89269 naive 2026-02-28\n2026-02-28 2026-03-01 3 4.9550169579 3.89269 snaive 2026-02-28\n2026-02-28 2026-03-01 3 3.2454429903 3.89269 ar1 2026-02-28\n2026-02-28 2026-03-01 3 2.3005318628 3.89269 model 2026-02-28\n2026-03-31 2026-02-01 1 3.1072003887 3.886121 naive 2026-03-31\n2026-03-31 2026-02-01 1 3.7909047157 3.886121 snaive 2026-03-31\n2026-03-31 2026-02-01 1 3.3275144689 3.886121 ar1 2026-03-31\n2026-03-31 2026-02-01 1 3.2730812025 3.886121 model 2026-03-31\n2026-03-31 2026-04-01 3 3.1072003887 4.758475 naive 2026-03-31\n2026-03-31 2026-04-01 3 4.8522670242 4.758475 snaive 2026-03-31\n2026-03-31 2026-04-01 3 3.6680446108 4.758475 ar1 2026-03-31\n2026-03-31 2026-04-01 3 2.391318795 4.758475 model 2026-03-31\n2026-04-30 2026-04-01 1 3.8926897961 4.758475 naive 2026-04-30\n2026-04-30 2026-04-01 1 4.8522670242 4.758475 snaive 2026-04-30\n2026-04-30 2026-04-01 1 3.9886847294 4.758475 ar1 2026-04-30\n2026-04-30 2026-04-01 1 4.4331152786 4.758475 model 2026-04-30\n2026-04-30 2026-06-01 3 3.8926897961 6.503056 naive 2026-04-30\n2026-04-30 2026-06-01 3 4.3220275131 6.503056 snaive 2026-04-30\n2026-04-30 2026-06-01 3 4.137029724 6.503056 ar1 2026-04-30\n2026-04-30 2026-06-01 3 4.9096957256 6.503056 model 2026-04-30\n2026-05-31 2026-05-01 1 4.7584751634 6.650342 naive 2026-05-31\n2026-05-31 2026-05-01 1 3.3117390789 6.650342 snaive 2026-05-31\n2026-05-31 2026-05-01 1 4.7179315355 6.650342 ar1 2026-05-31\n2026-05-31 2026-05-01 1 5.9619709975 6.650342 model 2026-05-31\n2026-05-31 2026-07-01 3 4.7584751634 4.887817 naive 2026-05-31\n2026-05-31 2026-07-01 3 4.0511314999 4.887817 snaive 2026-05-31\n2026-05-31 2026-07-01 3 4.6552855554 4.887817 ar1 2026-05-31\n2026-05-31 2026-07-01 3 5.1445742513 4.887817 model 2026-05-31\n2026-06-30 2026-06-01 1 6.6503424656 6.503056 naive 2026-06-30\n2026-06-30 2026-06-01 1 4.3220275131 6.503056 snaive 2026-06-30\n2026-06-30 2026-06-01 1 6.3114946125 6.503056 ar1 2026-06-30\n2026-06-30 2026-06-01 1 6.026867673 6.503056 model 2026-06-30\n2026-06-30 2026-08-01 3 6.6503424656 5.223092 naive 2026-06-30\n2026-06-30 2026-08-01 3 4.8529230606 5.223092 snaive 2026-06-30\n2026-06-30 2026-08-01 3 5.7879514961 5.223092 ar1 2026-06-30\n2026-06-30 2026-08-01 3 5.943685122 5.223092 model 2026-06-30\n2026-07-31 2026-07-01 1 6.5030562267 4.887817 naive 2026-07-31\n2026-07-31 2026-07-01 1 4.0511314999 4.887817 snaive 2026-07-31\n2026-07-31 2026-07-01 1 6.1885338246 4.887817 ar1 2026-07-31\n2026-07-31 2026-07-01 1 6.0002761774 4.887817 model 2026-07-31\n2026-07-31 2026-09-01 3 6.5030562267 6.09787 naive 2026-07-31\n2026-07-31 2026-09-01 3 4.0607649769 6.09787 snaive 2026-07-31\n2026-07-31 2026-09-01 3 5.7025163326 6.09787 ar1 2026-07-31\n2026-07-31 2026-09-01 3 6.4724392035 6.09787 model 2026-07-31","is_error":false}]},"uuid":"683f16c9-1b31-4540-b430-715b17c69658","timestamp":"2026-10-30T06:02:33.903Z","toolUseResult":{"stdout":"h=1: naive RMSE=0.9969, snaive RMSE=1.6745, ar1 RMSE=0.9405, model RMSE=0.5503; DM=2.429 p=0.015 -> model_better_significant\nh=3: naive RMSE=1.4200, snaive RMSE=1.3161, ar1 RMSE=1.1871, model RMSE=1.1422; DM=1.547 p=0.122 -> model_better_not_significant\nmean abs revision (h=1 targets) = 0.5482\nmodel,horizon,rmse,mae,n\nnaive,1,0.9968743518549719,0.8487221879899998,10\nnaive,3,1.420040373740657,1.2004486337699998,10\nsnaive,1,1.6745428991300964,1.30666987625,10\nsnaive,3,1.3160788989366212,1.06586869147,10\nar1,1,0.9405244111134986,0.7976510573200001,10\nar1,3,1.1871178147503472,0.9526895961500002,10\nmodel,1,0.5502977033465031,0.4863319392900001,10\nmodel,3,1.1422197516160006,0.9339774440799996,10\norigin_date target_date horizon forecast actual_first_release model vintage_used\n2025-10-31 2025-09-01 1 4.8783538599 4.17354 naive 2025-10-31\n2025-10-31 2025-09-01 1 1.9643255347 4.17354 snaive 2025-10-31\n2025-10-31 2025-09-01 1 4.821775512 4.17354 ar1 2025-10-31\n2025-10-31 2025-09-01 1 4.4390208923 4.17354 model 2025-10-31\n2025-10-31 2025-11-01 3 4.8783538599 3.277601 naive 2025-10-31\n2025-10-31 2025-11-01 3 3.8383986588 3.277601 snaive 2025-10-31\n2025-10-31 2025-11-01 3 4.7343454616 3.277601 ar1 2025-10-31\n2025-10-31 2025-11-01 3 3.9708517357 3.277601 model 2025-10-31\n2025-11-30 2025-10-01 1 4.1735403067 3.410194 naive 2025-11-30\n2025-11-30 2025-10-01 1 3.0803986182 3.410194 snaive 2025-11-30\n2025-11-30 2025-10-01 1 4.2282014336 3.410194 ar1 2025-11-30\n2025-11-30 2025-10-01 1 3.9078234306 3.410194 model 2025-11-30\n2025-11-30 2025-12-01 3 4.1735403067 2.398715 naive 2025-11-30\n2025-11-30 2025-12-01 3 4.4717369808 2.398715 snaive 2025-11-30\n2025-11-30 2025-12-01 3 4.3126650647 2.398715 ar1 2025-11-30\n2025-11-30 2025-12-01 3 3.1932762775 2.398715 model 2025-11-30\n2025-12-31 2025-11-01 1 3.4101935512 3.277601 naive 2025-12-31\n2025-12-31 2025-11-01 1 3.8383986588 3.277601 snaive 2025-12-31\n2025-12-31 2025-11-01 1 3.5849322197 3.277601 ar1 2025-12-31\n2025-12-31 2025-11-01 1 3.1205179971 3.277601 model 2025-12-31\n2025-12-31 2026-01-01 3 3.4101935512 3.1072 naive 2025-12-31\n2025-12-31 2026-01-01 3 4.4557440592 3.1072 snaive 2025-12-31\n2025-12-31 2026-01-01 3 3.8549609369 3.1072 ar1 2025-12-31\n2025-12-31 2026-01-01 3 3.7849775999 3.1072 model 2025-12-31\n2026-01-31 2025-12-01 1 3.2776007711 2.398715 naive 2026-01-31\n2026-01-31 2025-12-01 1 4.4717369808 2.398715 snaive 2026-01-31\n2026-01-31 2025-12-01 1 3.4726686566 2.398715 ar1 2026-01-31\n2026-01-31 2025-12-01 1 2.7832303294 2.398715 model 2026-01-31\n2026-01-31 2026-02-01 3 3.2776007711 3.886121 naive 2026-01-31\n2026-01-31 2026-02-01 3 3.7909047157 3.886121 snaive 2026-01-31\n2026-01-31 2026-02-01 3 3.7741287847 3.886121 ar1 2026-01-31\n2026-01-31 2026-02-01 3 4.1557116343 3.886121 model 2026-01-31\n2026-02-28 2026-01-01 1 2.3987149531 3.1072 naive 2026-02-28\n2026-02-28 2026-01-01 1 4.4557440592 3.1072 snaive 2026-02-28\n2026-02-28 2026-01-01 1 2.731302727 3.1072 ar1 2026-02-28\n2026-02-28 2026-01-01 1 3.4503927119 3.1072 model 2026-02-28\n2026-02-28 2026-03-01 3 2.3987149531 3.89269 naive 2026-02-28\n2026-02-28 2026-03-01 3 4.9550169579 3.89269 snaive 2026-02-28\n2026-02-28 2026-03-01 3 3.2454429903 3.89269 ar1 2026-02-28\n2026-02-28 2026-03-01 3 2.3005318628 3.89269 model 2026-02-28\n2026-03-31 2026-02-01 1 3.1072003887 3.886121 naive 2026-03-31\n2026-03-31 2026-02-01 1 3.7909047157 3.886121 snaive 2026-03-31\n2026-03-31 2026-02-01 1 3.3275144689 3.886121 ar1 2026-03-31\n2026-03-31 2026-02-01 1 3.2730812025 3.886121 model 2026-03-31\n2026-03-31 2026-04-01 3 3.1072003887 4.758475 naive 2026-03-31\n2026-03-31 2026-04-01 3 4.8522670242 4.758475 snaive 2026-03-31\n2026-03-31 2026-04-01 3 3.6680446108 4.758475 ar1 2026-03-31\n2026-03-31 2026-04-01 3 2.391318795 4.758475 model 2026-03-31\n2026-04-30 2026-04-01 1 3.8926897961 4.758475 naive 2026-04-30\n2026-04-30 2026-04-01 1 4.8522670242 4.758475 snaive 2026-04-30\n2026-04-30 2026-04-01 1 3.9886847294 4.758475 ar1 2026-04-30\n2026-04-30 2026-04-01 1 4.4331152786 4.758475 model 2026-04-30\n2026-04-30 2026-06-01 3 3.8926897961 6.503056 naive 2026-04-30\n2026-04-30 2026-06-01 3 4.3220275131 6.503056 snaive 2026-04-30\n2026-04-30 2026-06-01 3 4.137029724 6.503056 ar1 2026-04-30\n2026-04-30 2026-06-01 3 4.9096957256 6.503056 model 2026-04-30\n2026-05-31 2026-05-01 1 4.7584751634 6.650342 naive 2026-05-31\n2026-05-31 2026-05-01 1 3.3117390789 6.650342 snaive 2026-05-31\n2026-05-31 2026-05-01 1 4.7179315355 6.650342 ar1 2026-05-31\n2026-05-31 2026-05-01 1 5.9619709975 6.650342 model 2026-05-31\n2026-05-31 2026-07-01 3 4.7584751634 4.887817 naive 2026-05-31\n2026-05-31 2026-07-01 3 4.0511314999 4.887817 snaive 2026-05-31\n2026-05-31 2026-07-01 3 4.6552855554 4.887817 ar1 2026-05-31\n2026-05-31 2026-07-01 3 5.1445742513 4.887817 model 2026-05-31\n2026-06-30 2026-06-01 1 6.6503424656 6.503056 naive 2026-06-30\n2026-06-30 2026-06-01 1 4.3220275131 6.503056 snaive 2026-06-30\n2026-06-30 2026-06-01 1 6.3114946125 6.503056 ar1 2026-06-30\n2026-06-30 2026-06-01 1 6.026867673 6.503056 model 2026-06-30\n2026-06-30 2026-08-01 3 6.6503424656 5.223092 naive 2026-06-30\n2026-06-30 2026-08-01 3 4.8529230606 5.223092 snaive 2026-06-30\n2026-06-30 2026-08-01 3 5.7879514961 5.223092 ar1 2026-06-30\n2026-06-30 2026-08-01 3 5.943685122 5.223092 model 2026-06-30\n2026-07-31 2026-07-01 1 6.5030562267 4.887817 naive 2026-07-31\n2026-07-31 2026-07-01 1 4.0511314999 4.887817 snaive 2026-07-31\n2026-07-31 2026-07-01 1 6.1885338246 4.887817 ar1 2026-07-31\n2026-07-31 2026-07-01 1 6.0002761774 4.887817 model 2026-07-31\n2026-07-31 2026-09-01 3 6.5030562267 6.09787 naive 2026-07-31\n2026-07-31 2026-09-01 3 4.0607649769 6.09787 snaive 2026-07-31\n2026-07-31 2026-09-01 3 5.7025163326 6.09787 ar1 2026-07-31\n2026-07-31 2026-09-01 3 6.4724392035 6.09787 model 2026-07-31","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":true},"sandboxed":false,"sourceToolAssistantUUID":"55605a43-f1db-482b-bb31-61abbd23b5ad","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}56{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"44b052e9b2cc60d46fb40872608f2a7b0a367499d7b5f404357486a93a82e6bc","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS8QwKEAgTGAI4AUIIdGhpbmtpbmcSDLQ1IHJj+GswzsrzoBoMDvcM+6PBYkE2E78DIjBgBBk2OD1JOwfrPAY/Y/psiWECDET/F2EWNQw7o7vVQNNvSQXJy+rAhwW3l0Eh9nwqjgyCKmxatGqlrr8+WQ1IvuSDhphsO9SFvgodMiJbKRwQC4tTIbS4VZxo8A3HCYbbfO+8tZjEwEJI1DSQgP7MuubqbBNlA9VKj5bb8a1K6P0veCWpGb4kfB5SSOYqE1HD9DSp/Vwm1FfDOC8nsl1EYx+ZyTSgM7xsx2jWVy+N85M7EUchNDujJQJtxz+58fHvWFcoSY3RHGGqgCf/OFJLdWo/gvkLb/2IuUmPs2xWcvXblOkpvpG4N0seFswzqtPAfrtgGO7BFdqhkuvpIPO4lhrZex+dK4dagZmYgrTjECilkhS0yJnicnE+XYaEmAGNlKYma+3QtRriuFebkIoLV60BhDSlWyAtJm8u1TcDyjbsH9djlW79tcuMdmkMxRSDfAHUMLz/Ub8wbohellURlBx0+cWD91vv0YjUTjvX6kQ7fIjVkSGQ/yUiFUka8Sq7AGtEosZIvgDV9lZ/TRVmsxSCtmHIX8Et/ZjVcend1saJhI5ZNsfjog/0rxTIb5sedQQ0zh9m1+XF758T5E1ATGPXZrAnVx1YsvxyvbjXgMf8JistsYqWLA8uPMBVtikSjtaNg0G+pIA5k++huDsXlPIpXqZWjiDr6+kkh4d19Xa5xXvmsc2ivrdZMbeixM4gXn70eFEwGSqWAr3DKttWED0UzRzbHD32g9mRe/YMbBlGjYaQj6btVN47/7grMOEiLQ3W3bjkTDPXEK6cQC1yekl1FsUfGZTJpkE6wxaa7TzvefsdoHdSqIBnHn2UiFKcRWm2y8ncB8nw3yItzc92gk5vdbGga5pDv6jxJg71fgP2G7JB+19vEaQpKnHmYzP5+2Y3KbUJU9JI+GZfpn+6Sc/B1TcEl4l1MdY0dcYqAiaunk1vllhebciiwgkfdlPsuGy86J/6kRNdNqrZzGI5c+TInzKEGhokLGmpnRFyXcho2cqpT/DnRGMoOwj5Ze2TR/bsTo0Gau1mxa4uJzL7SFQxJptDx0H/Ewj8uY72qjfNk4wlY4USxRYg2tad4M2QoKzHB9fK+ZXRNFSE0nsIWopSHEjzHgni3QDpBYlSpzIwqKs8bLdwwB8Q+bu4RuN682csrFG3mNVtSrNTjg7b1+Rkacsb2Noqlf0khtqBTPQqaGkgK42NVWCGd5sRlIMqoQrc363RY/DsAWCe3OfnHtCSrDjs/j/50NuCR1aUDbg64tPWG+s7lWyxUBHVqQJ+7KPdr5LNq31ErND8BJ2IC0/miCgrz6zvLq6fqi40BF//v0z9LU5S64C+ZxFwsto7TeTDmlifF3Uc87Of9oXFPVqOBDXqmPYaQik70ECKwJtjuLg6L30Oh2VoQP5y/nRLmOp2aW1BBLGeHCgkeLsRjW2xKzB4Vwz6cW093Ac4ahR1RJBsU4s4pVR9+2xfbZ9NTNpTp4uklTQcCozpxC4l9CPxOrgZi0otYs/yzYCbbiszAmsJHnjs4f0Nx3lB+Lp9qPxSyLYjr6Qu04ZpZ4pvN7nORbMPykA/C3c0D3uU5V2MR4b866TiHrOf6rvCjecBfrhaA4iBzvqSmSoUXs1lwaakox9CxIPXvNtLKp9E/vG9H3D0M7cHrnDuH5dZms9eB2PiWNmWmFUHPtGXvo622/fQnUtTxr1TcpQoWHbcs/JWEGYturD9pxAsjnh6tsBVq/oipta/yoNxmHT3/jreuon7Wb2MpQnRLc4aFxHX13zEhbB/yujfNdJYgDxUnsVZRH9olirIBJm19qo4hkhiUgouYEFVV8p2tOx14zleGdP37r3YZmgvsKxVSkaGE4j/WqddxG1NslnhCg++gFma+/qXEtgOnXV56f5psYCTJopIyQG69QvirMWObnw5v4ldjaArua2Sg0IklaWPIds1QyeRfnnIyHIBpry9wbb+2dONFygV8GVFEAITJ/TAympX05xMQ13n7ykL7ZAk9T4pI2AH9bVMXiMlDDv5QHa1qcNM3ZYFsl0hVWYBtiK+Ex1ZbQF6SNYb91EkobEZC2QfW7m3dH0jJCFmuP99uA0bFmtEnj6voFFkXDrpKU662i6NSmXZ4QxeNi3IEzQCxR/i1BgB"},{"type":"tool_use","id":"toolu_01PfFt2bhUmPjh1LZQqBiUcn","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\n\nRun from the workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png.\n\"\"\"\nimport json\nimport os\nimport glob\n\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA = \"data\"\nOUT = \"out\"\nSEED = 20261030\nB_BOOT = 9999\nBLOCK = 3\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\n\n\ndef read_series(path):\n d = pd.read_csv(path, parse_dates=[0], index_col=0)\n s = d.iloc[:, 0].astype(float)\n s.index = s.index.to_period(\"M\")\n return s\n\n\ndef n_rows(path):\n with open(path) as f:\n return sum(1 for _ in f) - 1\n\n\ndef yoy(level):\n return 100.0 * (np.log(level) - np.log(level.shift(12)))\n\n\ndef forecasts_for_origin(V):\n \"\"\"All forecasts at origin V use ONLY the RSAFS vintage dated V.\"\"\"\n L = read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"))\n assert L.index.is_monotonic_increasing and L.index.is_unique\n assert (L.index[1:] - L.index[:-1] == 1 * L.index.freq).all() if False else True\n last = L.index[-1]\n g = yoy(L)\n lnL = np.log(L)\n out = {}\n # AR(1) on g over 1993-02 <= m <= last (consecutive pairs; g starts 1993-01)\n gs = g.loc[pd.Period(\"1993-01\", \"M\"):last]\n y = gs.loc[pd.Period(\"1993-02\", \"M\"):].values\n x = gs.shift(1).loc[pd.Period(\"1993-02\", \"M\"):].values\n X = np.column_stack([np.ones_like(x), x])\n c, phi = np.linalg.lstsq(X, y, rcond=None)[0]\n # model: base-effect drift. log level path extrapolated with trailing-12m mean monthly log change\n mu = (lnL.loc[last] - lnL.loc[last - 12]) / 12.0\n for h in HORIZONS:\n T = last + h\n f_naive = g.loc[last]\n f_snaive = g.loc[T - 12]\n f = g.loc[last]\n for _ in range(h):\n f = c + phi * f\n f_ar1 = f\n f_model = 100.0 * (lnL.loc[last] + h * mu - lnL.loc[T - 12])\n out[h] = dict(target=T, naive=f_naive, snaive=f_snaive, ar1=f_ar1, model=f_model)\n return last, out, (c, phi)\n\n\ndef dm_test(e_naive, e_model, h):\n d = e_naive ** 2 - e_model ** 2\n n = len(d)\n dbar = d.mean()\n dc = d - dbar\n lrv = np.sum(dc * dc) / n\n for k in range(1, h): # truncation lag h-1, Bartlett weights 1 - k/h\n w = 1.0 - k / h\n lrv += 2.0 * w * np.sum(dc[k:] * dc[:-k]) / n\n stat = dbar / np.sqrt(lrv / n)\n p = 2.0 * (1.0 - stats.norm.cdf(abs(stat)))\n return float(stat), float(p), float(dbar), float(lrv)\n\n\ndef block_boot_rmse_diff(e_naive, e_model, rng):\n n = len(e_naive)\n nb = int(np.ceil(n / BLOCK))\n diffs = np.empty(B_BOOT)\n for b in range(B_BOOT):\n starts = rng.integers(0, n, nb)\n idx = np.concatenate([(s + np.arange(BLOCK)) % n for s in starts])[:n]\n diffs[b] = np.sqrt(np.mean(e_model[idx] ** 2)) - np.sqrt(np.mean(e_naive[idx] ** 2))\n return float(np.percentile(diffs, 2.5)), float(np.percentile(diffs, 97.5)), float(np.mean(diffs < 0))\n\n\ndef main():\n os.makedirs(OUT, exist_ok=True)\n fr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\n fr[\"T\"] = fr[\"target_month\"].dt.to_period(\"M\")\n actual = dict(zip(fr[\"T\"], fr[\"yoy_first_release\"]))\n\n rows = []\n lasts = {}\n arcoef = {}\n for V in ORIGINS:\n last, fc, cp = forecasts_for_origin(V)\n lasts[V] = last\n arcoef[V] = cp\n for h in HORIZONS:\n T = fc[h][\"target\"]\n if T not in actual:\n raise RuntimeError(f\"missing first-release actual for {T}\")\n for m in MODELS:\n rows.append(dict(origin_date=V, target_date=T.to_timestamp().strftime(\"%Y-%m-%d\"),\n horizon=h, forecast=round(float(fc[h][m]), 10),\n actual_first_release=float(actual[T]), model=m, vintage_used=V))\n F = pd.DataFrame(rows)\n F[\"error\"] = F[\"actual_first_release\"] - F[\"forecast\"]\n F.drop(columns=\"error\").to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False)\n\n res = {\"task_id\": \"T1-forecast\",\n \"model_name\": \"base-effect drift (BED)\",\n \"model_description\": (\n \"Forecast of the log level of RSAFS at T = last(V)+h from the RSAFS vintage dated V only: \"\n \"ln L_hat_T = ln L_last + h*mu, where mu = (ln L_last - ln L_{last-12})/12 is the trailing-12-month \"\n \"mean monthly log change in the same vintage (i.e. the latest YoY growth spread evenly over months). \"\n \"The YoY forecast is g_hat_T = 100*(ln L_hat_T - ln L_{T-12}), where L_{T-12} (always <= last(V) since h<=3) \"\n \"is the base-period level as published in vintage V. Equivalently: naive forecast plus the known \"\n \"base effect (drop-out of the monthly log changes of months last-11..last-12+h) plus h months of drift. \"\n \"No parameters are estimated on the evaluation sample; the specification was fixed before computing any \"\n \"out-of-sample error and no variant was compared. PAYEMS and UMCSENT are not used; RSAFS_current and \"\n \"first_release.csv never enter any forecast.\"),\n \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\n t1 = []\n for m in MODELS:\n for h in HORIZONS:\n e = F[(F.model == m) & (F.horizon == h)][\"error\"].values\n rmse = float(np.sqrt(np.mean(e ** 2)))\n mae = float(np.mean(np.abs(e)))\n res[f\"rmse_{m}_h{h}\"] = rmse\n res[f\"mae_{m}_h{h}\"] = mae\n t1.append(dict(model=m, horizon=h, rmse=rmse, mae=mae, n=len(e)))\n pd.DataFrame(t1).to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n rng = np.random.default_rng(SEED)\n extra = {}\n for h in HORIZONS:\n en = F[(F.model == \"naive\") & (F.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n em = F[(F.model == \"model\") & (F.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n res[f\"rel_improvement_rmse_h{h}\"] = 1.0 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n stat, p, dbar, lrv = dm_test(en, em, h)\n res[f\"dm_stat_h{h}\"] = stat\n res[f\"dm_pvalue_h{h}\"] = p\n better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n sig = \"significant\" if p < 0.05 else \"not_significant\"\n res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n lo, hi, share = block_boot_rmse_diff(en, em, rng)\n extra[f\"dm_mean_loss_diff_h{h}\"] = dbar\n extra[f\"dm_lrv_h{h}\"] = lrv\n extra[f\"boot_rmse_diff_lo_h{h}\"] = lo\n extra[f\"boot_rmse_diff_hi_h{h}\"] = hi\n extra[f\"boot_share_model_better_h{h}\"] = share\n extra[f\"n_model_wins_h{h}\"] = int(np.sum(em ** 2 < en ** 2))\n\n # estimand (d): revision of h=1 targets, current vintage vs first release\n cur = read_series(os.path.join(DATA, \"RSAFS_current.csv\"))\n gcur = yoy(cur)\n t_h1 = [pd.Period(t, \"M\") for t in F[(F.model == \"naive\") & (F.horizon == 1)][\"target_date\"].str[:7]]\n revs = np.array([abs(gcur.loc[T] - actual[T]) for T in t_h1])\n res[\"mean_abs_revision_h1_targets\"] = float(revs.mean())\n extra[\"mean_signed_revision_h1_targets\"] = float(np.mean([gcur.loc[T] - actual[T] for T in t_h1]))\n extra[\"max_abs_revision_h1_targets\"] = float(revs.max())\n\n res[\"feasibility\"] = \"complete\"\n res[\"feasibility_reason\"] = None\n res[\"data_issues\"] = [\n {\"issue\": \"Irregular RSAFS publication timing: vintages 2025-10-31 to 2026-03-31 end two months before the vintage date; the 2026-04-30 vintage adds 2026-02 and 2026-03 at once.\",\n \"handling\": \"Targets defined as last(V)+h from the last month actually present in each vintage, as TASK.md prescribes; target months are therefore unevenly spaced (h=1 skips 2026-03, h=3 skips 2026-05).\"},\n {\"issue\": \"Recent months are revised from vintage to vintage (e.g. 2026-05 level 763705 in the 2026-06-30 vintage, 766876 in 2026-07-31).\",\n \"handling\": \"Each forecast uses the values as published in its own vintage; actuals are first releases from first_release.csv.\"},\n {\"issue\": \"Large downward level revision (about 3.5-4%) between the 2026-08-31 and 2026-09-30 vintages, visible in first_release.csv (2026-08 base-year level 700218 vs 731700 in shipped vintages) and in RSAFS_current.\",\n \"handling\": \"YoY growth is always computed within a single vintage so the level shift mostly cancels; not corrected. It affects the h=3 actuals of the last two origins (2026-08, 2026-09) and estimand (d).\"},\n {\"issue\": \"PAYEMS publication also delayed (2025-10-31 vintage ends 2025-08; 2025-12-31 adds two months).\",\n \"handling\": \"PAYEMS not used by the model; recorded only.\"},\n {\"issue\": \"UMCSENT has 210 empty fields, all before 1978 (quarterly survey era); file is current vintage.\",\n \"handling\": \"UMCSENT not used by the model; recorded only.\"},\n {\"issue\": \"RSAFS_current.csv and first_release.csv contain post-origin information.\",\n \"handling\": \"RSAFS_current used only for estimand (d); first_release only as evaluation actual.\"},\n ]\n files = sorted(glob.glob(os.path.join(DATA, \"vintages\", \"*.csv\"))) + [\n os.path.join(DATA, f) for f in (\"RSAFS_current.csv\", \"UMCSENT.csv\", \"first_release.csv\")]\n # PAYEMS and UMCSENT files are read only for the audit row counts (they do not enter forecasts)\n res[\"n_input_rows\"] = {os.path.relpath(f, DATA): n_rows(f) for f in files}\n res[\"n_analysed\"] = int(len(F[F.model == \"model\"]))\n res[\"random_seed\"] = SEED\n res.update(extra)\n res[\"block_bootstrap\"] = {\"B\": B_BOOT, \"block_length\": BLOCK, \"type\": \"circular moving-block, paired errors\"}\n res[\"last_month_by_origin\"] = {V: str(lasts[V]) for V in ORIGINS}\n res[\"ar1_coef_by_origin\"] = {V: {\"const\": float(arcoef[V][0]), \"phi\": float(arcoef[V][1])} for V in ORIGINS}\n res[\"abs_revision_by_h1_target\"] = {str(T): float(r) for T, r in zip(t_h1, revs)}\n\n with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\n # figure\n fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\n for ax, h in zip(axes, HORIZONS):\n sub = F[F.horizon == h]\n a = sub[sub.model == \"naive\"].sort_values(\"target_date\")\n x = pd.to_datetime(a[\"target_date\"])\n ax.plot(x, a[\"actual_first_release\"], \"k-o\", label=\"first-release actual\")\n for m, st in ((\"naive\", \"b--s\"), (\"model\", \"r-.^\")):\n s = sub[sub.model == m].sort_values(\"target_date\")\n ax.plot(pd.to_datetime(s[\"target_date\"]), s[\"forecast\"], st,\n label=f\"{m} (RMSE {res[f'rmse_{m}_h{h}']:.2f})\" if m == \"naive\" else\n f\"BED model (RMSE {res[f'rmse_{m}_h{h}']:.2f})\")\n ax.set_title(f\"h = {h}\")\n ax.set_ylabel(\"YoY growth, % (100 ln)\")\n ax.grid(alpha=0.3)\n ax.legend(fontsize=8)\n ax.tick_params(axis=\"x\", rotation=45)\n fig.suptitle(\"RSAFS YoY growth: real-time forecasts vs first release (10 origins, 2025-10-31 to 2026-07-31)\")\n fig.tight_layout()\n fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n plt.close(fig)\n\n for h in HORIZONS:\n print(f\"h={h}: \" + \", \".join(f\"{m} RMSE={res[f'rmse_{m}_h{h}']:.4f}\" for m in MODELS)\n + f\"; DM={res[f'dm_stat_h{h}']:.3f} p={res[f'dm_pvalue_h{h}']:.3f} -> {res[f'conclusion_code_h{h}']}\")\n print(f\"mean abs revision (h=1 targets) = {res['mean_abs_revision_h1_targets']:.4f}\")\n\n\nif __name__ == \"__main__\":\n main()\nEOF\nsed -i '' '/is_monotonic_increasing/{n;d;}' out/analysis.py; grep -n \"if False\" out/analysis.py; ~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv && column -s, -t out/forecasts.csv | head -90","description":"Write and run analysis script"}}]}}57{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"8bafefd6-3ae5-468a-8a36-e2ca9a1a9746","timestamp":"2026-10-30T06:02:33.907Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"0bbd4007-04d4-44f2-911c-9b1fbfa79d94","keep":16,"tail":["44b052e9b2cc60d46fb40872608f2a7b0a367499d7b5f404357486a93a82e6bc","516ef0b234d49a3042fb1f7c38a012ab169686f661fd20a6f9b9701626e6f8eb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"efca64e9a8ba220764951f40bbb1832917fc41b43b22a03e86b93c6c1a0e4384"}58{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"683f16c9-1b31-4540-b430-715b17c69658","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}59{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}60{"parentUuid":"683f16c9-1b31-4540-b430-715b17c69658","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuzGKbZ5KgJUCKf6uiq","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":9649,"cache_read_input_tokens":30791,"output_tokens":446,"output_tokens_details":{"thinking_tokens":249},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":9649},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2276,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXuzG3E3EGXw3fsj2jeS","requestRef":"8bafefd6-3ae5-468a-8a36-e2ca9a1a9746","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d059633e-d2a6-4b08-ab1d-403a8ab97985","timestamp":"2026-10-30T06:02:37.634Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"d059633e-d2a6-4b08-ab1d-403a8ab97985","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuzGKbZ5KgJUCKf6uiq","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QzR3NT1w8aAfY1PinYR5EF","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n if k not in ('data_issues','model_description','ar1_coef_by_origin'): print(k,v)\nprint(r['ar1_coef_by_origin']['2026-07-31'])\"","description":"Show results json"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":9649,"cache_read_input_tokens":30791,"output_tokens":446,"output_tokens_details":{"thinking_tokens":249},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":9649},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXuzG3E3EGXw3fsj2jeS","requestRef":"8bafefd6-3ae5-468a-8a36-e2ca9a1a9746","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d7eda620-1883-4f08-8063-8c438c4d39c7","timestamp":"2026-10-30T06:02:38.828Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"d7eda620-1883-4f08-8063-8c438c4d39c7","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QzR3NT1w8aAfY1PinYR5EF","type":"tool_result","content":"task_id T1-forecast\nmodel_name base-effect drift (BED)\nn_origins 10\nfirst_origin 2025-10-31\nlast_origin 2026-07-31\nrmse_naive_h1 0.9968743518549719\nmae_naive_h1 0.8487221879899998\nrmse_naive_h3 1.420040373740657\nmae_naive_h3 1.2004486337699998\nrmse_snaive_h1 1.6745428991300964\nmae_snaive_h1 1.30666987625\nrmse_snaive_h3 1.3160788989366212\nmae_snaive_h3 1.06586869147\nrmse_ar1_h1 0.9405244111134986\nmae_ar1_h1 0.7976510573200001\nrmse_ar1_h3 1.1871178147503472\nmae_ar1_h3 0.9526895961500002\nrmse_model_h1 0.5502977033465031\nmae_model_h1 0.4863319392900001\nrmse_model_h3 1.1422197516160006\nmae_model_h3 0.9339774440799996\nrel_improvement_rmse_h1 0.4479768665704803\ndm_stat_h1 2.4289778515163323\ndm_pvalue_h1 0.015141457285868354\nconclusion_code_h1 model_better_significant\nrel_improvement_rmse_h3 0.19564276288344107\ndm_stat_h3 1.5465768014563988\ndm_pvalue_h3 0.12196532729131726\nconclusion_code_h3 model_better_not_significant\nmean_abs_revision_h1_targets 0.5482198028389015\nfeasibility complete\nfeasibility_reason None\nn_input_rows {'vintages/PAYEMS_vintage_2025-10-31.csv': 1040, 'vintages/PAYEMS_vintage_2025-11-30.csv': 1041, 'vintages/PAYEMS_vintage_2025-12-31.csv': 1043, 'vintages/PAYEMS_vintage_2026-01-31.csv': 1044, 'vintages/PAYEMS_vintage_2026-02-28.csv': 1045, 'vintages/PAYEMS_vintage_2026-03-31.csv': 1046, 'vintages/PAYEMS_vintage_2026-04-30.csv': 1047, 'vintages/PAYEMS_vintage_2026-05-31.csv': 1048, 'vintages/PAYEMS_vintage_2026-06-30.csv': 1049, 'vintages/PAYEMS_vintage_2026-07-31.csv': 1050, 'vintages/RSAFS_vintage_2025-10-31.csv': 404, 'vintages/RSAFS_vintage_2025-11-30.csv': 405, 'vintages/RSAFS_vintage_2025-12-31.csv': 406, 'vintages/RSAFS_vintage_2026-01-31.csv': 407, 'vintages/RSAFS_vintage_2026-02-28.csv': 408, 'vintages/RSAFS_vintage_2026-03-31.csv': 409, 'vintages/RSAFS_vintage_2026-04-30.csv': 411, 'vintages/RSAFS_vintage_2026-05-31.csv': 412, 'vintages/RSAFS_vintage_2026-06-30.csv': 413, 'vintages/RSAFS_vintage_2026-07-31.csv': 414, 'RSAFS_current.csv': 417, 'UMCSENT.csv': 887, 'first_release.csv': 28}\nn_analysed 20\nrandom_seed 20261030\ndm_mean_loss_diff_h1 0.6909309110778346\ndm_lrv_h1 0.8091371397979005\nboot_rmse_diff_lo_h1 -0.6487094313166794\nboot_rmse_diff_hi_h1 -0.2787995997807278\nboot_share_model_better_h1 1.0\nn_model_wins_h1 8\ndm_mean_loss_diff_h3 0.7118487020717866\ndm_lrv_h3 2.1185192375008524\nboot_rmse_diff_lo_h3 -0.6877226202234573\nboot_rmse_diff_hi_h3 0.08193647367241552\nboot_share_model_better_h3 0.9314931493149315\nn_model_wins_h3 6\nmean_signed_revision_h1_targets -0.5482198028389015\nmax_abs_revision_h1_targets 0.9756759757612712\nblock_bootstrap {'B': 9999, 'block_length': 3, 'type': 'circular moving-block, paired errors'}\nlast_month_by_origin {'2025-10-31': '2025-08', '2025-11-30': '2025-09', '2025-12-31': '2025-10', '2026-01-31': '2025-11', '2026-02-28': '2025-12', '2026-03-31': '2026-01', '2026-04-30': '2026-03', '2026-05-31': '2026-04', '2026-06-30': '2026-05', '2026-07-31': '2026-06'}\nabs_revision_by_h1_target {'2025-09': 0.5502167925401169, '2025-10': 0.6641763167215546, '2025-11': 0.43891998227811113, '2025-12': 0.32862681655441595, '2026-01': 0.9756759757612712, '2026-02': 0.4099556308938235, '2026-04': 0.7481728291013168, '2026-05': 0.16533992600872516, '2026-06': 0.7440888135517616, '2026-07': 0.4570249449779187}\n{'const': 0.7268024118912031, 'phi': 0.839871473088339}","is_error":false}]},"uuid":"a99b5f36-99fc-4ef3-a92b-3aaab3376457","timestamp":"2026-10-30T06:02:38.889Z","toolUseResult":{"stdout":"task_id T1-forecast\nmodel_name base-effect drift (BED)\nn_origins 10\nfirst_origin 2025-10-31\nlast_origin 2026-07-31\nrmse_naive_h1 0.9968743518549719\nmae_naive_h1 0.8487221879899998\nrmse_naive_h3 1.420040373740657\nmae_naive_h3 1.2004486337699998\nrmse_snaive_h1 1.6745428991300964\nmae_snaive_h1 1.30666987625\nrmse_snaive_h3 1.3160788989366212\nmae_snaive_h3 1.06586869147\nrmse_ar1_h1 0.9405244111134986\nmae_ar1_h1 0.7976510573200001\nrmse_ar1_h3 1.1871178147503472\nmae_ar1_h3 0.9526895961500002\nrmse_model_h1 0.5502977033465031\nmae_model_h1 0.4863319392900001\nrmse_model_h3 1.1422197516160006\nmae_model_h3 0.9339774440799996\nrel_improvement_rmse_h1 0.4479768665704803\ndm_stat_h1 2.4289778515163323\ndm_pvalue_h1 0.015141457285868354\nconclusion_code_h1 model_better_significant\nrel_improvement_rmse_h3 0.19564276288344107\ndm_stat_h3 1.5465768014563988\ndm_pvalue_h3 0.12196532729131726\nconclusion_code_h3 model_better_not_significant\nmean_abs_revision_h1_targets 0.5482198028389015\nfeasibility complete\nfeasibility_reason None\nn_input_rows {'vintages/PAYEMS_vintage_2025-10-31.csv': 1040, 'vintages/PAYEMS_vintage_2025-11-30.csv': 1041, 'vintages/PAYEMS_vintage_2025-12-31.csv': 1043, 'vintages/PAYEMS_vintage_2026-01-31.csv': 1044, 'vintages/PAYEMS_vintage_2026-02-28.csv': 1045, 'vintages/PAYEMS_vintage_2026-03-31.csv': 1046, 'vintages/PAYEMS_vintage_2026-04-30.csv': 1047, 'vintages/PAYEMS_vintage_2026-05-31.csv': 1048, 'vintages/PAYEMS_vintage_2026-06-30.csv': 1049, 'vintages/PAYEMS_vintage_2026-07-31.csv': 1050, 'vintages/RSAFS_vintage_2025-10-31.csv': 404, 'vintages/RSAFS_vintage_2025-11-30.csv': 405, 'vintages/RSAFS_vintage_2025-12-31.csv': 406, 'vintages/RSAFS_vintage_2026-01-31.csv': 407, 'vintages/RSAFS_vintage_2026-02-28.csv': 408, 'vintages/RSAFS_vintage_2026-03-31.csv': 409, 'vintages/RSAFS_vintage_2026-04-30.csv': 411, 'vintages/RSAFS_vintage_2026-05-31.csv': 412, 'vintages/RSAFS_vintage_2026-06-30.csv': 413, 'vintages/RSAFS_vintage_2026-07-31.csv': 414, 'RSAFS_current.csv': 417, 'UMCSENT.csv': 887, 'first_release.csv': 28}\nn_analysed 20\nrandom_seed 20261030\ndm_mean_loss_diff_h1 0.6909309110778346\ndm_lrv_h1 0.8091371397979005\nboot_rmse_diff_lo_h1 -0.6487094313166794\nboot_rmse_diff_hi_h1 -0.2787995997807278\nboot_share_model_better_h1 1.0\nn_model_wins_h1 8\ndm_mean_loss_diff_h3 0.7118487020717866\ndm_lrv_h3 2.1185192375008524\nboot_rmse_diff_lo_h3 -0.6877226202234573\nboot_rmse_diff_hi_h3 0.08193647367241552\nboot_share_model_better_h3 0.9314931493149315\nn_model_wins_h3 6\nmean_signed_revision_h1_targets -0.5482198028389015\nmax_abs_revision_h1_targets 0.9756759757612712\nblock_bootstrap {'B': 9999, 'block_length': 3, 'type': 'circular moving-block, paired errors'}\nlast_month_by_origin {'2025-10-31': '2025-08', '2025-11-30': '2025-09', '2025-12-31': '2025-10', '2026-01-31': '2025-11', '2026-02-28': '2025-12', '2026-03-31': '2026-01', '2026-04-30': '2026-03', '2026-05-31': '2026-04', '2026-06-30': '2026-05', '2026-07-31': '2026-06'}\nabs_revision_by_h1_target {'2025-09': 0.5502167925401169, '2025-10': 0.6641763167215546, '2025-11': 0.43891998227811113, '2025-12': 0.32862681655441595, '2026-01': 0.9756759757612712, '2026-02': 0.4099556308938235, '2026-04': 0.7481728291013168, '2026-05': 0.16533992600872516, '2026-06': 0.7440888135517616, '2026-07': 0.4570249449779187}\n{'const': 0.7268024118912031, 'phi': 0.839871473088339}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d7eda620-1883-4f08-8063-8c438c4d39c7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}63{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"4944dc4f759c4691f901f33370344f54746729a0f6f53ae48ee29031225a0ddc","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01QzR3NT1w8aAfY1PinYR5EF","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n if k not in ('data_issues','model_description','ar1_coef_by_origin'): print(k,v)\nprint(r['ar1_coef_by_origin']['2026-07-31'])\"","description":"Show results json"}}]}}64{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"fb526e72-d8d4-4c69-bea5-b1218e135594","timestamp":"2026-10-30T06:02:38.893Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"8bafefd6-3ae5-468a-8a36-e2ca9a1a9746","keep":18,"tail":["4944dc4f759c4691f901f33370344f54746729a0f6f53ae48ee29031225a0ddc","297f11eb984fcec0d6784434cf4b8d98db610bb8a76b77645cae733a798532ec"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b86d87a9717ba3d626ba2fca468edf865542096aac97defcc1c34fc7b9aa9d8f"}65{"parentUuid":"a99b5f36-99fc-4ef3-a92b-3aaab3376457","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuzdZ32FiWmJw9NKArr","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2360,"cache_read_input_tokens":40440,"output_tokens":2723,"output_tokens_details":{"thinking_tokens":98},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2360},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":590,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXuzdNcv8wkPQPecUPz8","requestRef":"fb526e72-d8d4-4c69-bea5-b1218e135594","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"01d3c601-0710-4154-a50b-dbcc6ae72dea","timestamp":"2026-10-30T06:02:40.851Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}66{"parentUuid":"01d3c601-0710-4154-a50b-dbcc6ae72dea","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXuzdZ32FiWmJw9NKArr","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DQ8P1Z8H6pYDhERgCcSZy8","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cp out/results.json /tmp/r1.json; md5 -q out/forecasts.csv out/table1.csv > /tmp/m1; rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp /tmp/r1.json out/results.json && echo RESULTS_IDENTICAL; md5 -q out/forecasts.csv out/table1.csv | diff - /tmp/m1 && echo CSV_IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json, numpy as np, pandas as pd, statsmodels.api as sm\nfrom scipy import stats\nr=json.load(open('out/results.json')); F=pd.read_csv('out/forecasts.csv')\nchk=[]\nchk.append((\"80 rows, unique keys\", len(F)==80 and not F.duplicated(['origin_date','horizon','model']).any()))\nchk.append((\"vintage_used<=origin_date<target_date\", ((F.vintage_used<=F.origin_date)&(F.origin_date<F.target_date)).all()))\n# independent AR(1) via statsmodels for 2026-07-31\nL=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',index_col=0).iloc[:,0]\ng=100*np.log(L/L.shift(12)); g=g.dropna()\ny=g.iloc[1:].values; x=sm.add_constant(g.iloc[:-1].values)\nc,p=sm.OLS(y,x).fit().params\nchk.append((\"AR1 coefs match statsmodels (2026-07-31)\", np.allclose([c,p],[r['ar1_coef_by_origin']['2026-07-31'][k] for k in ('const','phi')])))\nf3=g.iloc[-1]\nfor _ in range(3): f3=c+p*f3\nchk.append((\"AR1 h3 forecast 2026-07-31 matches\", np.isclose(f3,F.query(\"origin_date=='2026-07-31' and horizon==3 and model=='ar1'\").forecast.iloc[0])))\n# model identity: model = naive - base effect + drift\nlnL=np.log(L); last=len(L)-1\nmu=(lnL.iloc[last]-lnL.iloc[last-12])/12\nfm=100*(lnL.iloc[last]+3*mu-lnL.iloc[last-9])\nchk.append((\"model h3 forecast 2026-07-31 recomputed\", np.isclose(fm,F.query(\"origin_date=='2026-07-31' and horizon==3 and model=='model'\").forecast.iloc[0])))\n# RMSE recompute & DM recompute\nfor h in (1,3):\n e={m:(F.query(f\"horizon=={h} and model=='{m}'\").sort_values('origin_date').eval('actual_first_release-forecast')).values for m in ('naive','snaive','ar1','model')}\n for m in e: chk.append((f\"rmse/mae {m} h{h}\", np.isclose(np.sqrt((e[m]**2).mean()),r[f'rmse_{m}_h{h}']) and np.isclose(np.abs(e[m]).mean(),r[f'mae_{m}_h{h}'])))\n d=e['naive']**2-e['model']**2; n=10\n # NW via statsmodels-like formula: gamma_k with demeaned, bartlett weights\n dc=d-d.mean(); g0=dc@dc/n; lrv=g0+sum(2*(1-k/h)*(dc[k:]@dc[:-k])/n for k in range(1,h))\n s=d.mean()/np.sqrt(lrv/n)\n chk.append((f\"DM h{h} recomputed\", np.isclose(s,r[f'dm_stat_h{h}']) and np.isclose(2*stats.norm.sf(abs(s)),r[f'dm_pvalue_h{h}'])))\n chk.append((f\"rel_improvement h{h}\", np.isclose(1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}'],r[f'rel_improvement_rmse_h{h}'])))\n chk.append((f\"bootstrap CI ordered h{h}\", r[f'boot_rmse_diff_lo_h{h}']<=r[f'boot_rmse_diff_hi_h{h}']))\n chk.append((f\"LRV positive h{h}\", r[f'dm_lrv_h{h}']>0))\n# actuals match first_release\nfr=pd.read_csv('data/first_release.csv'); a=dict(zip(fr.target_month,fr.yoy_first_release))\nchk.append((\"actuals match first_release.csv\", all(np.isclose(a[t],v) for t,v in zip(F.target_date,F.actual_first_release))))\n# naive at origin k equals the vintage g_last; target = last+h\nchk.append((\"target = last(V)+h\", all(pd.Period(t[:7],'M')==pd.Period(r['last_month_by_origin'][o],'M')+h for o,t,h in zip(F.origin_date,F.target_date,F.horizon))))\n# revision recompute\ncur=pd.read_csv('data/RSAFS_current.csv',index_col=0).iloc[:,0]; gc=100*np.log(cur/cur.shift(12))\ntg=F.query(\"horizon==1 and model=='naive'\").target_date\nchk.append((\"revision (d) recomputed\", np.isclose(np.mean([abs(gc[t]-a[t]) for t in tg]),r['mean_abs_revision_h1_targets'])))\nchk.append((\"all RMSE>0, MAE<=RMSE\", all(r[f'rmse_{m}_h{h}']>0 and r[f'mae_{m}_h{h}']<=r[f'rmse_{m}_h{h}']+1e-12 for m in ('naive','snaive','ar1','model') for h in (1,3))))\nchk.append((\"conclusion codes consistent\", all(r[f'conclusion_code_h{h}']==(\"model\" if r[f'rmse_model_h{h}']<r[f'rmse_naive_h{h}'] else \"naive\")+\"_better_\"+(\"significant\" if r[f'dm_pvalue_h{h}']<0.05 else \"not_significant\") for h in (1,3))))\nchk.append((\"n_analysed = 20 = 80 - 0 exclusions / 4 models\", r['n_analysed']==20))\nwith open('out/state/checks.md','w') as f:\n f.write(\"# Verification checks (P4)\\n\\nRun by an independent script (statsmodels OLS for AR(1), hand-recomputed DM/RMSE/revision).\\n\\n| check | outcome |\\n|---|---|\\n\")\n f.write(\"| clean re-run of analysis.py regenerates byte-identical results.json, forecasts.csv, table1.csv | PASS |\\n\")\n for k,v in chk: f.write(f\"| {k} | {'PASS' if v else 'FAIL'} |\\n\"); print(k,v)\n f.write(\"\\nMagnitudes: all RMSEs 0.55–1.67 pp of YoY growth, comparable to the spread of first-release YoY (2.4–6.7%); model RMSE below naive at both horizons, consistent with baseline ordering in table1.csv.\\n\")\nEOF","description":"Clean rerun and independent verification checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2360,"cache_read_input_tokens":40440,"output_tokens":2723,"output_tokens_details":{"thinking_tokens":98},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2360},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXuzdNcv8wkPQPecUPz8","requestRef":"fb526e72-d8d4-4c69-bea5-b1218e135594","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5468fb61-cda7-47b9-94a3-689167a869d4","timestamp":"2026-10-30T06:03:00.999Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}67{"parentUuid":"5468fb61-cda7-47b9-94a3-689167a869d4","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01DQ8P1Z8H6pYDhERgCcSZy8","type":"tool_result","content":"RESULTS_IDENTICAL\nCSV_IDENTICAL\n80 rows, unique keys True\nvintage_used<=origin_date<target_date False\nAR1 coefs match statsmodels (2026-07-31) True\nAR1 h3 forecast 2026-07-31 matches True\nmodel h3 forecast 2026-07-31 recomputed True\nrmse/mae naive h1 True\nrmse/mae snaive h1 True\nrmse/mae ar1 h1 True\nrmse/mae model h1 True\nDM h1 recomputed True\nrel_improvement h1 True\nbootstrap CI ordered h1 True\nLRV positive h1 True\nrmse/mae naive h3 True\nrmse/mae snaive h3 True\nrmse/mae ar1 h3 True\nrmse/mae model h3 True\nDM h3 recomputed True\nrel_improvement h3 True\nbootstrap CI ordered h3 True\nLRV positive h3 True\nactuals match first_release.csv True\ntarget = last(V)+h True\nrevision (d) recomputed True\nall RMSE>0, MAE<=RMSE True\nconclusion codes consistent True\nn_analysed = 20 = 80 - 0 exclusions / 4 models True","is_error":false}]},"uuid":"5f050d1f-081c-4d7e-83fa-04faf4c26254","timestamp":"2026-10-30T06:03:03.482Z","toolUseResult":{"stdout":"RESULTS_IDENTICAL\nCSV_IDENTICAL\n80 rows, unique keys True\nvintage_used<=origin_date<target_date False\nAR1 coefs match statsmodels (2026-07-31) True\nAR1 h3 forecast 2026-07-31 matches True\nmodel h3 forecast 2026-07-31 recomputed True\nrmse/mae naive h1 True\nrmse/mae snaive h1 True\nrmse/mae ar1 h1 True\nrmse/mae model h1 True\nDM h1 recomputed True\nrel_improvement h1 True\nbootstrap CI ordered h1 True\nLRV positive h1 True\nrmse/mae naive h3 True\nrmse/mae snaive h3 True\nrmse/mae ar1 h3 True\nrmse/mae model h3 True\nDM h3 recomputed True\nrel_improvement h3 True\nbootstrap CI ordered h3 True\nLRV positive h3 True\nactuals match first_release.csv True\ntarget = last(V)+h True\nrevision (d) recomputed True\nall RMSE>0, MAE<=RMSE True\nconclusion codes consistent True\nn_analysed = 20 = 80 - 0 exclusions / 4 models True","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5468fb61-cda7-47b9-94a3-689167a869d4","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}68{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"2b891af3cf4c84d1fb7e4eb1abad1bddfd8111b40c581291aebce43be04988ba","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01DQ8P1Z8H6pYDhERgCcSZy8","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cp out/results.json /tmp/r1.json; md5 -q out/forecasts.csv out/table1.csv > /tmp/m1; rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp /tmp/r1.json out/results.json && echo RESULTS_IDENTICAL; md5 -q out/forecasts.csv out/table1.csv | diff - /tmp/m1 && echo CSV_IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json, numpy as np, pandas as pd, statsmodels.api as sm\nfrom scipy import stats\nr=json.load(open('out/results.json')); F=pd.read_csv('out/forecasts.csv')\nchk=[]\nchk.append((\"80 rows, unique keys\", len(F)==80 and not F.duplicated(['origin_date','horizon','model']).any()))\nchk.append((\"vintage_used<=origin_date<target_date\", ((F.vintage_used<=F.origin_date)&(F.origin_date<F.target_date)).all()))\n# independent AR(1) via statsmodels for 2026-07-31\nL=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',index_col=0).iloc[:,0]\ng=100*np.log(L/L.shift(12)); g=g.dropna()\ny=g.iloc[1:].values; x=sm.add_constant(g.iloc[:-1].values)\nc,p=sm.OLS(y,x).fit().params\nchk.append((\"AR1 coefs match statsmodels (2026-07-31)\", np.allclose([c,p],[r['ar1_coef_by_origin']['2026-07-31'][k] for k in ('const','phi')])))\nf3=g.iloc[-1]\nfor _ in range(3): f3=c+p*f3\nchk.append((\"AR1 h3 forecast 2026-07-31 matches\", np.isclose(f3,F.query(\"origin_date=='2026-07-31' and horizon==3 and model=='ar1'\").forecast.iloc[0])))\n# model identity: model = naive - base effect + drift\nlnL=np.log(L); last=len(L)-1\nmu=(lnL.iloc[last]-lnL.iloc[last-12])/12\nfm=100*(lnL.iloc[last]+3*mu-lnL.iloc[last-9])\nchk.append((\"model h3 forecast 2026-07-31 recomputed\", np.isclose(fm,F.query(\"origin_date=='2026-07-31' and horizon==3 and model=='model'\").forecast.iloc[0])))\n# RMSE recompute & DM recompute\nfor h in (1,3):\n e={m:(F.query(f\"horizon=={h} and model=='{m}'\").sort_values('origin_date').eval('actual_first_release-forecast')).values for m in ('naive','snaive','ar1','model')}\n for m in e: chk.append((f\"rmse/mae {m} h{h}\", np.isclose(np.sqrt((e[m]**2).mean()),r[f'rmse_{m}_h{h}']) and np.isclose(np.abs(e[m]).mean(),r[f'mae_{m}_h{h}'])))\n d=e['naive']**2-e['model']**2; n=10\n # NW via statsmodels-like formula: gamma_k with demeaned, bartlett weights\n dc=d-d.mean(); g0=dc@dc/n; lrv=g0+sum(2*(1-k/h)*(dc[k:]@dc[:-k])/n for k in range(1,h))\n s=d.mean()/np.sqrt(lrv/n)\n chk.append((f\"DM h{h} recomputed\", np.isclose(s,r[f'dm_stat_h{h}']) and np.isclose(2*stats.norm.sf(abs(s)),r[f'dm_pvalue_h{h}'])))\n chk.append((f\"rel_improvement h{h}\", np.isclose(1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}'],r[f'rel_improvement_rmse_h{h}'])))\n chk.append((f\"bootstrap CI ordered h{h}\", r[f'boot_rmse_diff_lo_h{h}']<=r[f'boot_rmse_diff_hi_h{h}']))\n chk.append((f\"LRV positive h{h}\", r[f'dm_lrv_h{h}']>0))\n# actuals match first_release\nfr=pd.read_csv('data/first_release.csv'); a=dict(zip(fr.target_month,fr.yoy_first_release))\nchk.append((\"actuals match first_release.csv\", all(np.isclose(a[t],v) for t,v in zip(F.target_date,F.actual_first_release))))\n# naive at origin k equals the vintage g_last; target = last+h\nchk.append((\"target = last(V)+h\", all(pd.Period(t[:7],'M')==pd.Period(r['last_month_by_origin'][o],'M')+h for o,t,h in zip(F.origin_date,F.target_date,F.horizon))))\n# revision recompute\ncur=pd.read_csv('data/RSAFS_current.csv',index_col=0).iloc[:,0]; gc=100*np.log(cur/cur.shift(12))\ntg=F.query(\"horizon==1 and model=='naive'\").target_date\nchk.append((\"revision (d) recomputed\", np.isclose(np.mean([abs(gc[t]-a[t]) for t in tg]),r['mean_abs_revision_h1_targets'])))\nchk.append((\"all RMSE>0, MAE<=RMSE\", all(r[f'rmse_{m}_h{h}']>0 and r[f'mae_{m}_h{h}']<=r[f'rmse_{m}_h{h}']+1e-12 for m in ('naive','snaive','ar1','model') for h in (1,3))))\nchk.append((\"conclusion codes consistent\", all(r[f'conclusion_code_h{h}']==(\"model\" if r[f'rmse_model_h{h}']<r[f'rmse_naive_h{h}'] else \"naive\")+\"_better_\"+(\"significant\" if r[f'dm_pvalue_h{h}']<0.05 else \"not_significant\") for h in (1,3))))\nchk.append((\"n_analysed = 20 = 80 - 0 exclusions / 4 models\", r['n_analysed']==20))\nwith open('out/state/checks.md','w') as f:\n f.write(\"# Verification checks (P4)\\n\\nRun by an independent script (statsmodels OLS for AR(1), hand-recomputed DM/RMSE/revision).\\n\\n| check | outcome |\\n|---|---|\\n\")\n f.write(\"| clean re-run of analysis.py regenerates byte-identical results.json, forecasts.csv, table1.csv | PASS |\\n\")\n for k,v in chk: f.write(f\"| {k} | {'PASS' if v else 'FAIL'} |\\n\"); print(k,v)\n f.write(\"\\nMagnitudes: all RMSEs 0.55–1.67 pp of YoY growth, comparable to the spread of first-release YoY (2.4–6.7%); model RMSE below naive at both horizons, consistent with baseline ordering in table1.csv.\\n\")\nEOF","description":"Clean rerun and independent verification checks"}}]}}69{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"ed33e65b-5a00-4bb4-a86b-8c92d441fa25","timestamp":"2026-10-30T06:03:03.486Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"fb526e72-d8d4-4c69-bea5-b1218e135594","keep":20,"tail":["2b891af3cf4c84d1fb7e4eb1abad1bddfd8111b40c581291aebce43be04988ba","f89d9a8898f6668d4235e26158006db4a9c3b581d759e71bf573d013f5c47806"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9cd5bea52f6f8844c9fa880893c8d3ea30a90d56f4bec9a423cee3784c5f401f"}70{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"5f050d1f-081c-4d7e-83fa-04faf4c26254","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}71{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}72{"parentUuid":"5f050d1f-081c-4d7e-83fa-04faf4c26254","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv2Sogw3SrbFtCSVfeR","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS/A4KEAgTGAI4AUIIdGhpbmtpbmcSDHo83vRq479HmlZmxBoMlgyHtGQgSW5k45M6IjB30ipFgwA2Mo44GNU/Q6Lemm8ueWJgRn71AIKgHzPmucP4QIt2P4prlEww284izOsqmQ6wMSUg6DTw58ePhJFb6TMerAj1o7I1GUa2BYYFkc8taJ2HdH0+Hl43zNHFUIZidrGv4MOHBoRLJubjbN1C42lGJWA0ub0g0E25S3Up8QrKgUyAg/IJPDpFdmsQxI4QEJbpRfOTnP9BbNPrYU9f3WZHmG8KpfVBhznn32RmfeXSj/j41EJApY05XSqgD5gBYw819jJqqlYo2ZRi3GRaFNqv3jHM5ttxdADTW/RBPmV8Xgrg2nvB/4icVcjXXSPm23duElPbwBfqFVSs5YEQ6cYsbIR5Keql9baFnO9rRQkeE3fDiNJUPSCOPwPlCi9WNkMqDHJW3Xdx9juXp6Ik8jN+BVFfWjR35Ae5g4tsSceMqLac+JCq6trPgnxAkZOdke10uf8bIExaCkg1rGs8AQGa/Z/B4MUEkwID78Xp1j6LAVVwLXUUjJ8y1TWAGfgL/vCPRJN0q8aR/heVgJGHjCbMsOnWbQXtwGfaPjZqr0e06O+pfrKUoWdCDxm/+4V9KMQjl++6F6m67tfB3v3NaVlq3g8jnVWzD2w+wU8J79k/FRw8e1aQFzlg/lEe4yFZt1fW9VlHEVqzbAVPbaPlMh6cHTCf4U9MBsmnelHbcr923RwT+ljhqO262/iOAmyY1YgMBix3IajNYSl9cLRimOKqLSoyvoOUfqRVJyjeaerOZLh892wB+ec11r0L8SZV7KgHxJUl00Rrpp3mbnYX/b5yj7r0U+hkEmkQc83MO02qRKZVJrDw60TZj5EnhUbjUioin0g/lpTOP9UIP/CXe8/7oQsIpQoNQdGY9QC8+0EGtJ1GakEIUMSvatQYIl3l7O76nP7XnD6NGHPFzvWT/CKfS1whj/3PT7nfougQLMai8+oIh+MS/JTcEbXNIqO90z1W1C4nG3jVu8RN0SuOXDtcsU9umlbmIc4C30Rb/vx2SdALPs9zTyLBVd+EjS6fPCQqloCLYim/nhGLUXBVMO63YUBruu61NslIQxbmxgjirKIgjVmu56dAonSL88rjOmY7PWo4Rnr2i5XE+4lrE31DMs7Y9FyOdxFgermQwWNDqqJtMmwrOGOVCigNP/BAOV1e/31aMGiYwLdQGuOD3HU7BE42gMgahgrxreCjBvJDmC15+8RGrwnyIwmERUyIf8JAWgi1bfNpw0St1s/Xu0OxBwduXdUIml2TwnKen4FmXkeL4SdomW0mV95CtM1tScaz0j2XO8n5zwZ6VVmJ3aeyHZ10qv4KbpHrXEtA5kYXbAceidyqc+piyoJ7GqbSXozYVydDZRB1kCZjQrGh+ornU6xO0s4l6RfxglxjeD6WHYzbipRyBf2ZfdTP6BlQipw1jG2aen79CBd4d2IxP5QAPbRXKPobrL4x+7o8M5iSdYe9/EWi9CAavxZu8alyKzSUtLgWLSbBP5rhTgRKhqFAU10geaNC8Z02Ohfi7cBgz6UMjlsSpSTTHRjudIGnUeuGhyZ93C8heafSBpixzLbWPdgUxP1HTOaxxKr0AB8LUGbJR+EMQMvsf4s1FWN9/KrL8fhXs0MANzn9zLwaJK5rS2q8eLyqzhRPDbsv+t+Z18pEo0JwhzidL12Y+B4xGGoDYu/7PONBusF6IC0qV6nibOlKHu/wfbUxWFXXRNjprJrzRaiOfp3dFQ1lvfZWpM2DlrFI1/WRN9c6aor6nwDzz8Mza2KV1ud1PGeH25DQkvW4Dam/E+RD4AEiWOhnACemUMx9DA95i/zJHNiSNhMFy2Ktm+BSdFMSyFNgdzY/Qf2zOnDZ3aqs5u0t6l7B5CLUBQCkyXqlYSmcdSFY2AcTx4hST+eJRyYj1KmcXziXBfaz8a8Wtxo6xTG50AwrRHClt/2K8NP+CMBeXLYMeYsdD9QGIwPjNbZZzmmA0LIvSxdUWGE219qhLYhz1jyZ7zPV5dzZ3wHWBN+BUg7K51yiCr1Yjvcnqr1A6mfJCyC8V+YLhML6PZeHXH7vJJJiLla3V0L7RiBYc6wNjccY1lAZoPT42YJA3A0vtJT7CdjiWzB3aN1kl6M2n9cuF8Bp4Al5Zg7K//BA1cttb1jkl11R/EbFD6l01H4jeI8kmpyZIc9TK2WmNAj1yELf+lJ2r8aIy4FyFC6oRTFrOSHt6z67Nz2qTcwiILNvRCTmxnjvykhqh7BqCw8skfXrbtVTSOipqW1/RGaT/9MfMudHSx8z4uRNkK9rjUOH6rDxJ/l6ic+A/ZRbDdK9ID5529kDMeGZTLfwfXPtNs0UFcYWWyuRikClnYN3KRBUy7MZXGQ1+hgifswJgPq3915D8Qe/YQweNR4ChrkGpZif475O7yDqEsSAUaOV29WNTAD1hEoZnDXKcbpOPbNUSMOZVl//Mta6thiy95zzWFyIcnliPT3VJdNmv8Cx4WAsDQ1+DDvfTnGHm/lAFJN+nRgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3140,"cache_read_input_tokens":42800,"output_tokens":571,"output_tokens_details":{"thinking_tokens":439},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3140},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4234,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXv2SXKjweozC44hDbt6","requestRef":"ed33e65b-5a00-4bb4-a86b-8c92d441fa25","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3ddea7fc-6602-4729-a453-fd2af8b99b2e","timestamp":"2026-10-30T06:03:09.111Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}73{"parentUuid":"3ddea7fc-6602-4729-a453-fd2af8b99b2e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv2Sogw3SrbFtCSVfeR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HTB2T4827LK5hbBmRjY64v","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -40","description":"Run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3140,"cache_read_input_tokens":42800,"output_tokens":571,"output_tokens_details":{"thinking_tokens":439},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3140},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv2SXKjweozC44hDbt6","requestRef":"ed33e65b-5a00-4bb4-a86b-8c92d441fa25","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"793fa64f-63b8-4f3a-afad-e1dc25e4a825","timestamp":"2026-10-30T06:03:09.948Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}74{"parentUuid":"793fa64f-63b8-4f3a-afad-e1dc25e4a825","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HTB2T4827LK5hbBmRjY64v","type":"tool_result","content":" [ok] key:rmse_model_h1: ok\n [ok] key:mae_model_h1: ok\n [ok] key:rmse_model_h3: ok\n [ok] key:mae_model_h3: ok\n [ok] key:rel_improvement_rmse_h1: ok\n [ok] key:rel_improvement_rmse_h3: ok\n [ok] key:dm_stat_h1: ok\n [ok] key:dm_pvalue_h1: ok\n [ok] key:dm_stat_h3: ok\n [ok] key:dm_pvalue_h3: ok\n [ok] key:conclusion_code_h1: ok\n [ok] key:conclusion_code_h3: ok\n [ok] key:mean_abs_revision_h1_targets: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P1', 'P2', 'P3', 'P4', 'P5']\n [ok] exclusion_ledger: 1 steps consistent\n [ok] positive:rmse_naive_h1: 0.9968743518549719\n [ok] positive:rmse_naive_h3: 1.420040373740657\n [ok] positive:rmse_snaive_h1: 1.6745428991300964\n [ok] positive:rmse_snaive_h3: 1.3160788989366212\n [ok] positive:rmse_ar1_h1: 0.9405244111134986\n [ok] positive:rmse_ar1_h3: 1.1871178147503472\n [ok] positive:rmse_model_h1: 0.5502977033465031\n [ok] positive:rmse_model_h3: 1.1422197516160006\n [ok] chronology:first_origin<=last_origin: 2025-10-31 vs 2026-07-31\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\n [ok] reproducibility: regenerated in 1.4s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060311.428944Z.json","is_error":false}]},"uuid":"f5e0865d-697a-4895-8b91-3edfdd6a7672","timestamp":"2026-10-30T06:03:11.438Z","toolUseResult":{"stdout":" [ok] key:rmse_model_h1: ok\n [ok] key:mae_model_h1: ok\n [ok] key:rmse_model_h3: ok\n [ok] key:mae_model_h3: ok\n [ok] key:rel_improvement_rmse_h1: ok\n [ok] key:rel_improvement_rmse_h3: ok\n [ok] key:dm_stat_h1: ok\n [ok] key:dm_pvalue_h1: ok\n [ok] key:dm_stat_h3: ok\n [ok] key:dm_pvalue_h3: ok\n [ok] key:conclusion_code_h1: ok\n [ok] key:conclusion_code_h3: ok\n [ok] key:mean_abs_revision_h1_targets: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P1', 'P2', 'P3', 'P4', 'P5']\n [ok] exclusion_ledger: 1 steps consistent\n [ok] positive:rmse_naive_h1: 0.9968743518549719\n [ok] positive:rmse_naive_h3: 1.420040373740657\n [ok] positive:rmse_snaive_h1: 1.6745428991300964\n [ok] positive:rmse_snaive_h3: 1.3160788989366212\n [ok] positive:rmse_ar1_h1: 0.9405244111134986\n [ok] positive:rmse_ar1_h3: 1.1871178147503472\n [ok] positive:rmse_model_h1: 0.5502977033465031\n [ok] positive:rmse_model_h3: 1.1422197516160006\n [ok] chronology:first_origin<=last_origin: 2025-10-31 vs 2026-07-31\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\n [ok] reproducibility: regenerated in 1.4s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060311.428944Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"793fa64f-63b8-4f3a-afad-e1dc25e4a825","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}75{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"392b72740628466b53e2fe921b8ad7894ac19cac4600cff111860b3384e57985","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01HTB2T4827LK5hbBmRjY64v","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -40","description":"Run gate"}}]}}76{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"9dc72129-0003-412f-8cfb-9bf949131efb","timestamp":"2026-10-30T06:03:11.442Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"ed33e65b-5a00-4bb4-a86b-8c92d441fa25","keep":22,"tail":["392b72740628466b53e2fe921b8ad7894ac19cac4600cff111860b3384e57985","8ebef63b43544edb2bdd1e5d5ccf1c86b913f7c429e531c46f63904dd1b6fc7a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"6dbd7767b934eb1fff6833d9a939c0e8b77b3f17c0089a0986ab43201223970f"}77{"parentUuid":"f5e0865d-697a-4895-8b91-3edfdd6a7672","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv32oaJPW1Ut1RwuMr6","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1530,"cache_read_input_tokens":45940,"output_tokens":643,"output_tokens_details":{"thinking_tokens":510},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1530},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4560,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXv32WyVK4tPzGS9Xjqd","requestRef":"9dc72129-0003-412f-8cfb-9bf949131efb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e22f916a-fc3d-4d1a-a7d2-683306823de6","timestamp":"2026-10-30T06:03:17.472Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"e22f916a-fc3d-4d1a-a7d2-683306823de6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv32oaJPW1Ut1RwuMr6","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DXeU3r2qbTbNbXyE1Ucdfm","name":"Bash","input":{"command":"grep -n -A40 \"def .*chronolog\" ~/wp29/gates/pgar_gate.py | grep -n -B2 -A40 forecasts | head -80","description":"Inspect gate chronology check"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1530,"cache_read_input_tokens":45940,"output_tokens":643,"output_tokens_details":{"thinking_tokens":510},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1530},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv32WyVK4tPzGS9Xjqd","requestRef":"9dc72129-0003-412f-8cfb-9bf949131efb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0e4ef087-b7f7-4b94-935a-7d2f3fa9a77b","timestamp":"2026-10-30T06:03:18.557Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}79{"parentUuid":"0e4ef087-b7f7-4b94-935a-7d2f3fa9a77b","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01DXeU3r2qbTbNbXyE1Ucdfm","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"3ec1495d-4415-4416-b787-ce573e703643","timestamp":"2026-10-30T06:03:18.601Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"0e4ef087-b7f7-4b94-935a-7d2f3fa9a77b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}80{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"4a6788b247c76be6da268c44511eeeac1017f73682ffa376ee8fff1cfcafee61","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01DXeU3r2qbTbNbXyE1Ucdfm","name":"Bash","input":{"command":"grep -n -A40 \"def .*chronolog\" ~/wp29/gates/pgar_gate.py | grep -n -B2 -A40 forecasts | head -80","description":"Inspect gate chronology check"}}]}}81{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"1ec9a46a-5581-4271-a853-6fa2f5ef7e0d","timestamp":"2026-10-30T06:03:18.605Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"9dc72129-0003-412f-8cfb-9bf949131efb","keep":24,"tail":["4a6788b247c76be6da268c44511eeeac1017f73682ffa376ee8fff1cfcafee61","4812cba4ced36a4da2096afd35b330980e2e65b960c5ab27a55bf79fa045acf4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9976cd7a73ff1605b22396b7c87f7e62320c2f83d0ec10ade217016a9d5a2483"}82{"parentUuid":"3ec1495d-4415-4416-b787-ce573e703643","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv3ZTpJuCEs2DcQb8xp","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BnoAvJPcdMKzJCM9iHdbpy","name":"Bash","input":{"command":"grep -n \"forecasts_chronology\\|target_col\\|origin_col\\|vintage_col\\|def \" ~/wp29/gates/pgar_gate.py | head -60","description":"Locate chronology code in gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":658,"cache_read_input_tokens":47470,"output_tokens":133,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":658},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXv3ZBh7kh3EdN5RbtHm","requestRef":"1ec9a46a-5581-4271-a853-6fa2f5ef7e0d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c41f7c65-a897-4d2e-b87c-e50d9472b150","timestamp":"2026-10-30T06:03:20.471Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}83{"parentUuid":"c41f7c65-a897-4d2e-b87c-e50d9472b150","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BnoAvJPcdMKzJCM9iHdbpy","type":"tool_result","content":"14:def _utc():\n17:def _load_json(path):\n26:def _is_num(v):\n29:def _type_ok(v, t, nullable):\n36:def _parse_date(s):\n42:def _compare_results(a, b, rel):\n67:def run_gate(ws, python=None, do_repro=True):\n70: def add(cid, ok, detail=\"\"):\n179: add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n181: add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n213:def _finish(ws, checks):\n228:def main(argv):","is_error":false}]},"uuid":"5a234131-4722-4272-ae52-797aca842357","timestamp":"2026-10-30T06:03:20.508Z","toolUseResult":{"stdout":"14:def _utc():\n17:def _load_json(path):\n26:def _is_num(v):\n29:def _type_ok(v, t, nullable):\n36:def _parse_date(s):\n42:def _compare_results(a, b, rel):\n67:def run_gate(ws, python=None, do_repro=True):\n70: def add(cid, ok, detail=\"\"):\n179: add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n181: add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n213:def _finish(ws, checks):\n228:def main(argv):","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c41f7c65-a897-4d2e-b87c-e50d9472b150","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}84{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"ef419b93b16e834a21cbc32cee0caf1f23c0fa15ab2ff480ba490a15f5ed9dfc","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01BnoAvJPcdMKzJCM9iHdbpy","name":"Bash","input":{"command":"grep -n \"forecasts_chronology\\|target_col\\|origin_col\\|vintage_col\\|def \" ~/wp29/gates/pgar_gate.py | head -60","description":"Locate chronology code in gate"}}]}}85{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"595a0a39-1a54-4f02-aeae-f1e9e734da45","timestamp":"2026-10-30T06:03:20.511Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"1ec9a46a-5581-4271-a853-6fa2f5ef7e0d","keep":26,"tail":["ef419b93b16e834a21cbc32cee0caf1f23c0fa15ab2ff480ba490a15f5ed9dfc","e50d5d69b3462527a7af96c8abd4e86046b9a2ddd9509c285bf80c7af6aa9f9c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e42dce467852e83c5d03dc2ad6dd2b35caa4b8cfa5bfa68765528c107a34cc44"}86{"parentUuid":"5a234131-4722-4272-ae52-797aca842357","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv3hbTSdWd8uYgrV1Hb","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XBpGtZJ6E69W2To9H169pY","name":"Bash","input":{"command":"sed -n 30,45p ~/wp29/gates/pgar_gate.py; sed -n 155,182p ~/wp29/gates/pgar_gate.py","description":"Read gate chronology logic"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":365,"cache_read_input_tokens":48128,"output_tokens":130,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":365},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXv3hJ6cUCyTEUC7SkEz","requestRef":"595a0a39-1a54-4f02-aeae-f1e9e734da45","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f4ca3b00-e40b-4303-a2fb-10008c58a6ad","timestamp":"2026-10-30T06:03:22.265Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}87{"parentUuid":"f4ca3b00-e40b-4303-a2fb-10008c58a6ad","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01XBpGtZJ6E69W2To9H169pY","type":"tool_result","content":" if v is None:\n return bool(nullable)\n return {\"number\": _is_num(v), \"integer\": isinstance(v, int) and not isinstance(v, bool),\n \"string\": isinstance(v, str), \"boolean\": isinstance(v, bool), \"array\": isinstance(v, list),\n \"object\": isinstance(v, dict)}.get(t, True)\n\ndef _parse_date(s):\n try:\n return datetime.date.fromisoformat(str(s)[:10])\n except Exception: # noqa: BLE001\n return None\n\ndef _compare_results(a, b, rel):\n \"\"\"Return list of keys whose values differ beyond rel tolerance (numbers) or are unequal (others).\"\"\"\n diffs = []\n keys = set(a) | set(b)\n add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n # 7. numeric sanity checks\n if \"ci_contains_estimate\" in fam:\n for est, lo, hi in spec.get(\"ci_pairs\", []):\n e, l, h = res.get(est), res.get(lo), res.get(hi)\n if all(_is_num(v) for v in (e, l, h)):\n add(f\"ci:{est}\", l <= e <= h, f\"{l} <= {e} <= {h}\")\n elif e is None and l is None and h is None:\n add(f\"ci:{est}\", True, \"all null (allowed if reported infeasible)\")\n else:\n add(f\"ci:{est}\", False, \"non-numeric CI triple\")\n if \"positive_se\" in fam:\n for k in spec.get(\"positive_keys\", []):\n v = res.get(k)\n add(f\"positive:{k}\", (v is None) or (_is_num(v) and v > 0), f\"{v}\")\n if \"chronology\" in fam:\n for a, b in spec.get(\"chronology_pairs\", []):\n da, db = _parse_date(res.get(a)), _parse_date(res.get(b))\n add(f\"chronology:{a}<={b}\", da is not None and db is not None and da <= db, f\"{res.get(a)} vs {res.get(b)}\")\n if \"forecasts_csv_chronology\" in fam:\n fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n try:\n rows = list(csv.DictReader(open(fp, newline=\"\")))\n bad = sum(1 for r in rows if not (_parse_date(r.get(\"origin_date\")) and _parse_date(r.get(\"target_date\")) and _parse_date(r[\"origin_date\"]) < _parse_date(r[\"target_date\"])))\n add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n except Exception as e: # noqa: BLE001\n add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n # 8. reproducibility","is_error":false}]},"uuid":"fe7a41d1-5e27-4357-b230-04ffbf968480","timestamp":"2026-10-30T06:03:22.308Z","toolUseResult":{"stdout":" if v is None:\n return bool(nullable)\n return {\"number\": _is_num(v), \"integer\": isinstance(v, int) and not isinstance(v, bool),\n \"string\": isinstance(v, str), \"boolean\": isinstance(v, bool), \"array\": isinstance(v, list),\n \"object\": isinstance(v, dict)}.get(t, True)\n\ndef _parse_date(s):\n try:\n return datetime.date.fromisoformat(str(s)[:10])\n except Exception: # noqa: BLE001\n return None\n\ndef _compare_results(a, b, rel):\n \"\"\"Return list of keys whose values differ beyond rel tolerance (numbers) or are unequal (others).\"\"\"\n diffs = []\n keys = set(a) | set(b)\n add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n # 7. numeric sanity checks\n if \"ci_contains_estimate\" in fam:\n for est, lo, hi in spec.get(\"ci_pairs\", []):\n e, l, h = res.get(est), res.get(lo), res.get(hi)\n if all(_is_num(v) for v in (e, l, h)):\n add(f\"ci:{est}\", l <= e <= h, f\"{l} <= {e} <= {h}\")\n elif e is None and l is None and h is None:\n add(f\"ci:{est}\", True, \"all null (allowed if reported infeasible)\")\n else:\n add(f\"ci:{est}\", False, \"non-numeric CI triple\")\n if \"positive_se\" in fam:\n for k in spec.get(\"positive_keys\", []):\n v = res.get(k)\n add(f\"positive:{k}\", (v is None) or (_is_num(v) and v > 0), f\"{v}\")\n if \"chronology\" in fam:\n for a, b in spec.get(\"chronology_pairs\", []):\n da, db = _parse_date(res.get(a)), _parse_date(res.get(b))\n add(f\"chronology:{a}<={b}\", da is not None and db is not None and da <= db, f\"{res.get(a)} vs {res.get(b)}\")\n if \"forecasts_csv_chronology\" in fam:\n fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n try:\n rows = list(csv.DictReader(open(fp, newline=\"\")))\n bad = sum(1 for r in rows if not (_parse_date(r.get(\"origin_date\")) and _parse_date(r.get(\"target_date\")) and _parse_date(r[\"origin_date\"]) < _parse_date(r[\"target_date\"])))\n add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n except Exception as e: # noqa: BLE001\n add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n # 8. reproducibility","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f4ca3b00-e40b-4303-a2fb-10008c58a6ad","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}88{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"e1a111fb6a43005bedf7d5b31eebbba0374259e205ee32b12e71bf08599f56a4","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01XBpGtZJ6E69W2To9H169pY","name":"Bash","input":{"command":"sed -n 30,45p ~/wp29/gates/pgar_gate.py; sed -n 155,182p ~/wp29/gates/pgar_gate.py","description":"Read gate chronology logic"}}]}}89{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"b56fa996-d914-4d80-93b1-4f7ec787deed","timestamp":"2026-10-30T06:03:22.311Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"595a0a39-1a54-4f02-aeae-f1e9e734da45","keep":28,"tail":["e1a111fb6a43005bedf7d5b31eebbba0374259e205ee32b12e71bf08599f56a4","bd330bc245a0d56571e0bf8bd245e93aba415104a648fce61b569a8caf602728"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"68e887f2bdc4c7e81eecc9b4f49c76d9ccbad7b5cbcdb25aa293d4a719ad66ea"}90{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"fe7a41d1-5e27-4357-b230-04ffbf968480","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}91{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}92{"parentUuid":"fe7a41d1-5e27-4357-b230-04ffbf968480","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv3qHZPgLhfh1EsP274","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1103,"cache_read_input_tokens":48493,"output_tokens":800,"output_tokens_details":{"thinking_tokens":679},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1103},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6580,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXv3pzhZHKCyFe7N7Q7W","requestRef":"b56fa996-d914-4d80-93b1-4f7ec787deed","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b2d2d208-b60e-4f76-9fa7-6546dfd90a1b","timestamp":"2026-10-30T06:03:30.389Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}93{"parentUuid":"b2d2d208-b60e-4f76-9fa7-6546dfd90a1b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv3qHZPgLhfh1EsP274","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UnpJN3gLYKEesBTxvdEDkD","name":"Bash","input":{"command":"grep -n -i \"terminal\\|passed\\|blocked\" ~/wp29/gates/pgar_gate.py | head -30","description":"Check gate phase terminal statuses"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1103,"cache_read_input_tokens":48493,"output_tokens":800,"output_tokens_details":{"thinking_tokens":679},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1103},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv3pzhZHKCyFe7N7Q7W","requestRef":"b56fa996-d914-4d80-93b1-4f7ec787deed","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3db42385-9f2d-4334-89a5-a4a5ececb855","timestamp":"2026-10-30T06:03:31.175Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}94{"parentUuid":"3db42385-9f2d-4334-89a5-a4a5ececb855","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UnpJN3gLYKEesBTxvdEDkD","type":"tool_result","content":"7:Writes a receipt to <workspace_dir>/out/state/gate_receipts/<utc>.json and exits 0 if passed, 1 otherwise.\n71: checks.append({\"id\": cid, \"passed\": bool(ok), \"detail\": detail})\n131: if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n133: if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n134: bad.append(f\"{pid}: passed without recorded checks\")\n135: not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n137: bad.append(f\"phases not terminal: {not_done}\")\n214: passed = all(c[\"passed\"] for c in checks) and bool(checks)\n216: \"passed\": passed, \"n_checks\": len(checks), \"n_failed\": sum(1 for c in checks if not c[\"passed\"]), \"checks\": checks}\n242: print(f\"PGAR GATE {r['gate_version']} — {'PASSED' if r['passed'] else 'FAILED'} ({r['n_failed']} of {r['n_checks']} checks failed)\")\n244: print(f\" [{'ok' if c['passed'] else 'FAIL'}] {c['id']}: {c['detail']}\")\n246: return 0 if r[\"passed\"] else 1","is_error":false}]},"uuid":"e7d49a34-3ea1-4f42-8e7c-c621b3378fe6","timestamp":"2026-10-30T06:03:31.215Z","toolUseResult":{"stdout":"7:Writes a receipt to <workspace_dir>/out/state/gate_receipts/<utc>.json and exits 0 if passed, 1 otherwise.\n71: checks.append({\"id\": cid, \"passed\": bool(ok), \"detail\": detail})\n131: if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n133: if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n134: bad.append(f\"{pid}: passed without recorded checks\")\n135: not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n137: bad.append(f\"phases not terminal: {not_done}\")\n214: passed = all(c[\"passed\"] for c in checks) and bool(checks)\n216: \"passed\": passed, \"n_checks\": len(checks), \"n_failed\": sum(1 for c in checks if not c[\"passed\"]), \"checks\": checks}\n242: print(f\"PGAR GATE {r['gate_version']} — {'PASSED' if r['passed'] else 'FAILED'} ({r['n_failed']} of {r['n_checks']} checks failed)\")\n244: print(f\" [{'ok' if c['passed'] else 'FAIL'}] {c['id']}: {c['detail']}\")\n246: return 0 if r[\"passed\"] else 1","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"3db42385-9f2d-4334-89a5-a4a5ececb855","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}95{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"a9503ee5c1ab02db89fe42e928f59178243fbbfda0f3b109e10bdb26475fc091","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01UnpJN3gLYKEesBTxvdEDkD","name":"Bash","input":{"command":"grep -n -i \"terminal\\|passed\\|blocked\" ~/wp29/gates/pgar_gate.py | head -30","description":"Check gate phase terminal statuses"}}]}}96{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"29e1ddbd-27fd-4b83-98d4-e7790fa35649","timestamp":"2026-10-30T06:03:31.218Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"b56fa996-d914-4d80-93b1-4f7ec787deed","keep":30,"tail":["a9503ee5c1ab02db89fe42e928f59178243fbbfda0f3b109e10bdb26475fc091","6f89a704dff69ab0762ebcfbd9697385e22c326e1de728ac525486e8c57ba019"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9228c17d71d0d0b7887c3da74441ff841d56f0374fad0a3838a47537ba321471"}97{"parentUuid":"e7d49a34-3ea1-4f42-8e7c-c621b3378fe6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv4VM3EKRB4AWk2EwU5","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1308,"cache_read_input_tokens":49596,"output_tokens":1248,"output_tokens_details":{"thinking_tokens":523},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1308},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":5412,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXv4V4fzywbtv9pvRxVw","requestRef":"29e1ddbd-27fd-4b83-98d4-e7790fa35649","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0994a4fb-9c71-48a2-b2af-74ca202a503d","timestamp":"2026-10-30T06:03:38.045Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}98{"parentUuid":"0994a4fb-9c71-48a2-b2af-74ca202a503d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv4VM3EKRB4AWk2EwU5","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_014zvj6h6jQaJ7dwDsAkohec","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat >> out/state/checks.md <<'EOF'\n\n## Note on the FAIL above (and gate check `forecasts_chronology`)\n`vintage_used <= origin_date` holds for all 80 rows (vintage_used = origin_date). `origin_date < target_date` fails for all 40 h = 1 rows (and only those): TASK.md defines the target as last(V)+h with `target_date` written as YYYY-MM-01, and because last(V) is at least one month before the month of V, the h = 1 target month always *begins* on or before the month-end origin (e.g. origin 2026-04-30, last = 2026-03, target 2026-04-01; origin 2025-10-31, last = 2025-08, target 2025-09-01). This is not information leakage: the target value is not published in vintage V and the actual comes from a later vintage (first_release_vintage > origin for all 20 targets; verified below). The gate rule `origin_date < target_date` is therefore inconsistent with the task's own target definition for h = 1. I did not relabel target dates to pass the gate, since that would misstate the target month. Reported as an open issue.\nEOF\n~/wp29/venv/bin/python -c \"\nimport pandas as pd\nF=pd.read_csv('out/forecasts.csv'); fr=pd.read_csv('data/first_release.csv')\nm=F.merge(fr,left_on='target_date',right_on='target_month')\nprint('first_release_vintage > origin for all rows:', (m.first_release_vintage>m.origin_date).all(), len(m))\nprint('rows with target<=origin by horizon:', F[F.target_date<=F.origin_date].groupby('horizon').size().to_dict())\n\" | tee -a /tmp/fr.txt; echo \"| first_release_vintage > origin_date for all 80 rows (no leakage of the actual) | PASS |\" >> out/state/checks.md","description":"Document chronology conflict and verify no leakage"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1308,"cache_read_input_tokens":49596,"output_tokens":1248,"output_tokens_details":{"thinking_tokens":523},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1308},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv4V4fzywbtv9pvRxVw","requestRef":"29e1ddbd-27fd-4b83-98d4-e7790fa35649","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2890f25e-bc6a-4b3c-9b6f-cf2836cd67ad","timestamp":"2026-10-30T06:03:44.134Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}99{"parentUuid":"2890f25e-bc6a-4b3c-9b6f-cf2836cd67ad","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_014zvj6h6jQaJ7dwDsAkohec","type":"tool_result","content":"first_release_vintage > origin for all rows: True 80\nrows with target<=origin by horizon: {1: 40}","is_error":false}]},"uuid":"30a26d16-981c-4179-bf13-3c0639f5d5c3","timestamp":"2026-10-30T06:03:44.417Z","toolUseResult":{"stdout":"first_release_vintage > origin for all rows: True 80\nrows with target<=origin by horizon: {1: 40}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2890f25e-bc6a-4b3c-9b6f-cf2836cd67ad","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}100{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"8b755eeef7c38e3bb474d8c6ffcb2fabb478b4aac58fa8a09002bcf4e6004770","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_014zvj6h6jQaJ7dwDsAkohec","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat >> out/state/checks.md <<'EOF'\n\n## Note on the FAIL above (and gate check `forecasts_chronology`)\n`vintage_used <= origin_date` holds for all 80 rows (vintage_used = origin_date). `origin_date < target_date` fails for all 40 h = 1 rows (and only those): TASK.md defines the target as last(V)+h with `target_date` written as YYYY-MM-01, and because last(V) is at least one month before the month of V, the h = 1 target month always *begins* on or before the month-end origin (e.g. origin 2026-04-30, last = 2026-03, target 2026-04-01; origin 2025-10-31, last = 2025-08, target 2025-09-01). This is not information leakage: the target value is not published in vintage V and the actual comes from a later vintage (first_release_vintage > origin for all 20 targets; verified below). The gate rule `origin_date < target_date` is therefore inconsistent with the task's own target definition for h = 1. I did not relabel target dates to pass the gate, since that would misstate the target month. Reported as an open issue.\nEOF\n~/wp29/venv/bin/python -c \"\nimport pandas as pd\nF=pd.read_csv('out/forecasts.csv'); fr=pd.read_csv('data/first_release.csv')\nm=F.merge(fr,left_on='target_date',right_on='target_month')\nprint('first_release_vintage > origin for all rows:', (m.first_release_vintage>m.origin_date).all(), len(m))\nprint('rows with target<=origin by horizon:', F[F.target_date<=F.origin_date].groupby('horizon').size().to_dict())\n\" | tee -a /tmp/fr.txt; echo \"| first_release_vintage > origin_date for all 80 rows (no leakage of the actual) | PASS |\" >> out/state/checks.md","description":"Document chronology conflict and verify no leakage"}}]}}101{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"24b8ab08-f85a-4e03-832b-db9b31240560","timestamp":"2026-10-30T06:03:44.420Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"29e1ddbd-27fd-4b83-98d4-e7790fa35649","keep":32,"tail":["8b755eeef7c38e3bb474d8c6ffcb2fabb478b4aac58fa8a09002bcf4e6004770","4e0168cdf82b82e081533ef82e2c5ffd461c2700753b36b53e8a36ffdeb4d9b4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9e3991b80da06ac2ce113c471c228bfea2de7110cd7f89dfc6f093fce7ede24a"}102{"type":"tools-used","tools":["Bash","Read"],"sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}103{"parentUuid":"30a26d16-981c-4179-bf13-3c0639f5d5c3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv5To48ozi5HQTRKhP8","type":"message","role":"assistant","content":[{"type":"text","text":"Now the report, claims, and figure check."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1291,"cache_read_input_tokens":50904,"output_tokens":94,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1291},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXv5TWh2NbDoz23XHFkF","requestRef":"24b8ab08-f85a-4e03-832b-db9b31240560","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"75110202-bb60-42f4-ad94-4f7a66560011","timestamp":"2026-10-30T06:03:45.594Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}104{"parentUuid":"75110202-bb60-42f4-ad94-4f7a66560011","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv5To48ozi5HQTRKhP8","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ThJc6xNCNipAjN1cVoKAMN","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0026/out/figure1.png"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1291,"cache_read_input_tokens":50904,"output_tokens":94,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1291},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv5TWh2NbDoz23XHFkF","requestRef":"24b8ab08-f85a-4e03-832b-db9b31240560","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"78b06e9d-39ea-4f22-b201-61fb71ef8c18","timestamp":"2026-10-30T06:03:46.066Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}105{"parentUuid":"78b06e9d-39ea-4f22-b201-61fb71ef8c18","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ThJc6xNCNipAjN1cVoKAMN","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"ee2ca140-99b0-4b93-bf02-1ac3ce9ca430","timestamp":"2026-10-30T06:03:46.073Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":96709,"dimensions":{"originalWidth":1440,"originalHeight":540,"displayWidth":1440,"displayHeight":540}}},"sourceToolAssistantUUID":"78b06e9d-39ea-4f22-b201-61fb71ef8c18","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}106{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"20dcb37141804282223deb7612d5d95a858baa698024c0025afb3f6304616f97","message":{"role":"assistant","content":[{"type":"text","text":"Now the report, claims, and figure check."},{"type":"tool_use","id":"toolu_01ThJc6xNCNipAjN1cVoKAMN","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0026/out/figure1.png"}}]}}107{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"7a646460-80c9-4f23-95b9-a593d8e2a7f5","timestamp":"2026-10-30T06:03:46.077Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"24b8ab08-f85a-4e03-832b-db9b31240560","keep":34,"tail":["20dcb37141804282223deb7612d5d95a858baa698024c0025afb3f6304616f97","efdf0a2002ad6bc07550b29ebaba15c43f55b325837ee2204b16153e2a675834"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7280f84fa35cce25ef724880fda7dbc3e30409294063d8e97c3d1ce678e9ae6c"}108{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"ee2ca140-99b0-4b93-bf02-1ac3ce9ca430","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}109{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}110{"parentUuid":"ee2ca140-99b0-4b93-bf02-1ac3ce9ca430","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv5asCyE6FbNjC5rRAS","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1153,"cache_read_input_tokens":52195,"output_tokens":5085,"output_tokens_details":{"thinking_tokens":25},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1153},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":330,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXv5afYTpdF2FBctrctN","requestRef":"7a646460-80c9-4f23-95b9-a593d8e2a7f5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5fe24f5b-93e4-4964-a001-2b7b87ba97f2","timestamp":"2026-10-30T06:03:47.798Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}111{"parentUuid":"5fe24f5b-93e4-4964-a001-2b7b87ba97f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv5asCyE6FbNjC5rRAS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Df3S4jLPbmpKenAF2D5ZAR","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from ALFRED vintages (T1-forecast)\n\n## Question\nCould the year-over-year log growth of US retail and food services sales (RSAFS), g_m = 100·ln(L_m/L_{m−12}), have been forecast in real time, using only the data published at each of 10 month-end origins (2025-10-31 … 2026-07-31; `first_origin`, `last_origin`, `n_origins`), one and three months beyond the last published month? And does a model of my own design beat the no-change (naive) forecast, when errors are measured against the first-release value of each target month?\n\n## Data and exclusions\nInputs (hashes verified against `data/README.md`; row counts in `n_input_rows`; full audit in `out/state/data_audit.md`): 10 ALFRED vintages of RSAFS and of PAYEMS, current UMCSENT, current RSAFS, and `first_release.csv`.\n\n**Real-time design.** The forecast at origin V uses only the RSAFS vintage dated V (`vintage_used` = `origin_date` in every row of `out/forecasts.csv`). The target is last(V)+h, where last(V) is the last month present in that vintage (`last_month_by_origin`):\n\n| origin V | last(V) | h=1 target | h=3 target |\n|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2025-09 | 2025-11 |\n| 2025-11-30 | 2025-09 | 2025-10 | 2025-12 |\n| 2025-12-31 | 2025-10 | 2025-11 | 2026-01 |\n| 2026-01-31 | 2025-11 | 2025-12 | 2026-02 |\n| 2026-02-28 | 2025-12 | 2026-01 | 2026-03 |\n| 2026-03-31 | 2026-01 | 2026-02 | 2026-04 |\n| 2026-04-30 | 2026-03 | 2026-04 | 2026-06 |\n| 2026-05-31 | 2026-04 | 2026-05 | 2026-07 |\n| 2026-06-30 | 2026-05 | 2026-06 | 2026-08 |\n| 2026-07-31 | 2026-06 | 2026-07 | 2026-09 |\n\n**Publication delays observed.** The first six vintages (2025-10-31 to 2026-03-31) end two months before the vintage date rather than one; the 2026-04-30 vintage adds two months at once (2026-02 and 2026-03). So the target months are unevenly spaced (h=1 never targets 2026-03, h=3 never targets 2026-05). The actual for every target is `yoy_first_release` from `first_release.csv`. Its first-release vintage is always later than the origin. Other data issues are listed in `data_issues`: revisions within the vintage grid, a large (~3.5–4 %) downward level revision between the 2026-08-31 and 2026-09-30 vintages that also appears in the current file, PAYEMS delays, and pre-1978 gaps in UMCSENT. `RSAFS_current.csv` is used only for estimand (d).\n\n**Exclusions.** None: 80 forecast–actual pairs out of 80, of which 20 belong to my model (`n_analysed`). See `out/exclusions.csv`.\n\n## Method\nAll four forecasts are computed from the RSAFS vintage dated V only:\n- **naive**: g_{last(V)} for both horizons;\n- **seasonal naive (snaive)**: g_{T−12} from the vintage;\n- **AR(1)**: OLS of g_m on a constant and g_{m−1}, 1993-02 ≤ m ≤ last(V), with iterated forecasts (coefficients in `ar1_coef_by_origin`);\n- **my model, \"base-effect drift\" (BED)** (`model_name`, `model_description`): the log level is extrapolated as ln L̂_T = ln L_last + h·μ, with μ = (ln L_last − ln L_{last−12})/12 (the latest YoY growth spread evenly across months). The forecast is ĝ_T = 100·(ln L̂_T − ln L_{T−12}), where the base-period level L_{T−12} is already published in vintage V. In words, the naive forecast is corrected for the known *base effect*, i.e. the monthly changes from a year ago that drop out of the YoY window, and h months of drift are added. The model estimates no parameters. Its specification was fixed before any out-of-sample error was computed, and no alternative variant was tried on the evaluation sample. PAYEMS and UMCSENT are not used.\n\nEvaluation: RMSE and MAE over the 10 origins per horizon against first-release YoY. Relative improvement = 1 − RMSE_model/RMSE_naive. Diebold–Mariano test of model vs naive: d_t = e²_naive − e²_model, Bartlett (Newey–West) long-run variance with truncation lag h−1, no HLN correction, two-sided normal p-value. Supplementary measure: a circular moving-block bootstrap (block length 3, B = 9999, seed `random_seed` = 20261030) of the paired errors, giving a 95 % percentile interval for RMSE_model − RMSE_naive. Estimand (d) is the mean over the 10 h=1 targets of |g_current − yoy_first_release|. Everything is produced by `out/analysis.py`.\n\n## Results\nRMSE / MAE in percentage points of YoY growth (`out/table1.csv`, n = 10 each):\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 (`rmse_naive_h1`) | 0.849 (`mae_naive_h1`) | 1.420 (`rmse_naive_h3`) | 1.200 (`mae_naive_h3`) |\n| seasonal naive | 1.675 (`rmse_snaive_h1`) | 1.307 (`mae_snaive_h1`) | 1.316 (`rmse_snaive_h3`) | 1.066 (`mae_snaive_h3`) |\n| AR(1) | 0.941 (`rmse_ar1_h1`) | 0.798 (`mae_ar1_h1`) | 1.187 (`rmse_ar1_h3`) | 0.953 (`mae_ar1_h3`) |\n| BED model | 0.550 (`rmse_model_h1`) | 0.486 (`mae_model_h1`) | 1.142 (`rmse_model_h3`) | 0.934 (`mae_model_h3`) |\n\n- **h = 1:** the BED model has the lowest RMSE and MAE of the four methods. Its RMSE is 44.8 % below naive (`rel_improvement_rmse_h1` = 0.448), and it has the smaller squared error at 8 of 10 origins (`n_model_wins_h1`). DM = 2.43, p = 0.015 (`dm_stat_h1`, `dm_pvalue_h1`), so `conclusion_code_h1` = `model_better_significant`.\n- **h = 3:** the BED model again has the lowest RMSE and MAE, but its margin over AR(1) is small (1.142 vs 1.187). Its RMSE is 19.6 % below naive (`rel_improvement_rmse_h3` = 0.196), with 6 wins out of 10 (`n_model_wins_h3`). DM = 1.55, p = 0.122 (`dm_stat_h3`, `dm_pvalue_h3`), so `conclusion_code_h3` = `model_better_not_significant`.\n- Seasonal naive is the worst method at h = 1 but beats naive at h = 3. AR(1) beats naive at both horizons.\n- **Revisions (d):** the first-release YoY growth of the 10 h=1 target months differs from the currently published growth by 0.548 pp on average (`mean_abs_revision_h1_targets`). The revisions are all downward (`mean_signed_revision_h1_targets` = −0.548; maximum 0.976 pp, `max_abs_revision_h1_targets`). That average revision is the same size as the BED model's h=1 RMSE.\n- Figure: `out/figure1.png` shows the first-release actuals with the naive and BED forecasts, one panel per horizon.\n\n## Uncertainty\nThere are only 10 origins, the evaluation window is a single year, and the h = 3 errors overlap. The DM statistic is compared with the standard normal, which is an asymptotic approximation. With n = 10 the Newey–West variance estimate is itself very noisy, and the test is known to over-reject in small samples (this is why the Harvey–Leybourne–Newbold correction exists; as the task specifies, it is not applied here). So the h = 1 p-value of 0.015 (`dm_pvalue_h1`) should be read as suggestive evidence, not decisive. With the HLN factor and t(9) critical values it would be less extreme; that variant was not computed for the reported keys. Two things support the h = 1 result: the model wins at 8 of 10 origins, and every block-bootstrap resample gives the model the lower RMSE. The 95 % interval for RMSE_model − RMSE_naive is [−0.649, −0.279] pp (`boot_rmse_diff_lo_h1`, `boot_rmse_diff_hi_h1`, `boot_share_model_better_h1`). This bootstrap is crude at n = 10 and should not be over-interpreted. At h = 3 the DM test does not reject (p = 0.122, `dm_pvalue_h3`), and the bootstrap interval [−0.688, 0.082] pp includes zero (`boot_rmse_diff_lo_h3`, `boot_rmse_diff_hi_h3`). An improvement over naive at h = 3 is plausible but not established.\n\n## Limitations and open issues\n- **Gate chronology check conflicts with the task definition.** The gate requires `origin_date < target_date` in `out/forecasts.csv`, which fails for all 40 h = 1 rows. TASK.md defines the target as last(V)+h, written as YYYY-MM-01. Since last(V) is always at least one month before the month of V, the h = 1 target month always begins on or before the month-end origin (e.g. origin 2026-04-30, target 2026-04-01). The forecast is still made before the target's value exists in any data: the target value is absent from vintage V, and its first-release vintage is later than the origin in all 80 rows (`out/state/checks.md`). I kept the target dates as TASK.md defines them rather than relabelling them to pass the gate. So the gate reports this one check as failed, and phases P4/P5 are marked \"blocked\" for this reason only. All other gate checks, including reproducibility, pass.\n- Small sample (10 origins, one year, a period with shutdown-related publication disruption). The ranking of methods could change in other periods.\n- The model was designed by one analyst, and its design reflects general knowledge of how YoY base effects work. I did not search over variants on these data. Still, I cannot fully exclude awareness of the general behaviour of 2025–26 data as a source of bias.\n- The h = 3 actuals for the last two origins (targets 2026-08 and 2026-09) come from vintages released after a large level revision. Within-vintage YoY growth is less affected than levels, but not entirely unaffected.\n- The large downward revision behind estimand (d) is mostly a single annual/benchmark revision. It is a statement about this particular window, not about typical revision sizes.\n- PAYEMS and UMCSENT were not used. Whether they would add information was not evaluated.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect drift model has the lowest RMSE and MAE of all four methods and reduces RMSE by about 45% relative to the naive forecast.\",\"results_keys\":[\"rmse_model_h1\",\"mae_model_h1\",\"rmse_naive_h1\",\"rmse_snaive_h1\",\"rmse_ar1_h1\",\"rel_improvement_rmse_h1\"],\"status\":\"supported\",\"caveat\":\"10 origins over one year only.\"},\n {\"id\":\"C2\",\"text\":\"At h=1 the Diebold-Mariano test (Newey-West lag 0, normal p-value) rejects equal accuracy of model and naive at 5%.\",\"results_keys\":[\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\",\"n_model_wins_h1\",\"boot_rmse_diff_lo_h1\",\"boot_rmse_diff_hi_h1\"],\"status\":\"supported\",\"caveat\":\"Asymptotic test with n=10 and no HLN correction; suggestive rather than decisive.\"},\n {\"id\":\"C3\",\"text\":\"At h=3 the model has a lower RMSE than naive (about 20% improvement) but the difference is not statistically significant.\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\",\"boot_rmse_diff_lo_h3\",\"boot_rmse_diff_hi_h3\"],\"status\":\"supported\",\"caveat\":\"Margin over AR(1) at h=3 is small; bootstrap interval includes zero.\"},\n {\"id\":\"C4\",\"text\":\"Seasonal naive is the worst method at h=1 but beats naive at h=3; AR(1) beats naive at both horizons.\",\"results_keys\":[\"rmse_snaive_h1\",\"rmse_snaive_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\",\"rmse_ar1_h1\",\"rmse_ar1_h3\"],\"status\":\"supported\",\"caveat\":\"No significance tests for baseline comparisons.\"},\n {\"id\":\"C5\",\"text\":\"The first-release YoY growth of the h=1 target months differs from currently published growth by about 0.55 pp on average, all revisions being downward.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"mean_signed_revision_h1_targets\",\"max_abs_revision_h1_targets\"],\"status\":\"supported\",\"caveat\":\"Dominated by one large annual/benchmark revision in 2026.\"},\n {\"id\":\"C6\",\"text\":\"All forecasts respect the information-availability rule: each uses only the RSAFS vintage dated at its origin, and every actual is first released after the origin.\",\"results_keys\":[\"last_month_by_origin\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"The gate's origin_date < target_date rule fails for h=1 rows by construction of the task's target definition; see Limitations.\"}\n]\nEOF\necho ok","description":"Write report and claims ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1153,"cache_read_input_tokens":52195,"output_tokens":5085,"output_tokens_details":{"thinking_tokens":25},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1153},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv5afYTpdF2FBctrctN","requestRef":"7a646460-80c9-4f23-95b9-a593d8e2a7f5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b2957811-959d-49ff-8e88-6a07ff7db508","timestamp":"2026-10-30T06:04:27.675Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}112{"parentUuid":"b2957811-959d-49ff-8e88-6a07ff7db508","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Df3S4jLPbmpKenAF2D5ZAR","type":"tool_result","content":"ok","is_error":false}]},"uuid":"84f7e6e5-cdc5-42f2-ae3e-045b2bd06dc7","timestamp":"2026-10-30T06:04:27.716Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":true},"sandboxed":false,"sourceToolAssistantUUID":"b2957811-959d-49ff-8e88-6a07ff7db508","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}113{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"6fb1ed93f88c5cbab5a0f7b099c7a1b21889e40dfb1b2c37f63b0ee8b7687d9d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Df3S4jLPbmpKenAF2D5ZAR","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from ALFRED vintages (T1-forecast)\n\n## Question\nCould the year-over-year log growth of US retail and food services sales (RSAFS), g_m = 100·ln(L_m/L_{m−12}), have been forecast in real time, using only the data published at each of 10 month-end origins (2025-10-31 … 2026-07-31; `first_origin`, `last_origin`, `n_origins`), one and three months beyond the last published month? And does a model of my own design beat the no-change (naive) forecast, when errors are measured against the first-release value of each target month?\n\n## Data and exclusions\nInputs (hashes verified against `data/README.md`; row counts in `n_input_rows`; full audit in `out/state/data_audit.md`): 10 ALFRED vintages of RSAFS and of PAYEMS, current UMCSENT, current RSAFS, and `first_release.csv`.\n\n**Real-time design.** The forecast at origin V uses only the RSAFS vintage dated V (`vintage_used` = `origin_date` in every row of `out/forecasts.csv`). The target is last(V)+h, where last(V) is the last month present in that vintage (`last_month_by_origin`):\n\n| origin V | last(V) | h=1 target | h=3 target |\n|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2025-09 | 2025-11 |\n| 2025-11-30 | 2025-09 | 2025-10 | 2025-12 |\n| 2025-12-31 | 2025-10 | 2025-11 | 2026-01 |\n| 2026-01-31 | 2025-11 | 2025-12 | 2026-02 |\n| 2026-02-28 | 2025-12 | 2026-01 | 2026-03 |\n| 2026-03-31 | 2026-01 | 2026-02 | 2026-04 |\n| 2026-04-30 | 2026-03 | 2026-04 | 2026-06 |\n| 2026-05-31 | 2026-04 | 2026-05 | 2026-07 |\n| 2026-06-30 | 2026-05 | 2026-06 | 2026-08 |\n| 2026-07-31 | 2026-06 | 2026-07 | 2026-09 |\n\n**Publication delays observed.** The first six vintages (2025-10-31 to 2026-03-31) end two months before the vintage date rather than one; the 2026-04-30 vintage adds two months at once (2026-02 and 2026-03). So the target months are unevenly spaced (h=1 never targets 2026-03, h=3 never targets 2026-05). The actual for every target is `yoy_first_release` from `first_release.csv`. Its first-release vintage is always later than the origin. Other data issues are listed in `data_issues`: revisions within the vintage grid, a large (~3.5–4 %) downward level revision between the 2026-08-31 and 2026-09-30 vintages that also appears in the current file, PAYEMS delays, and pre-1978 gaps in UMCSENT. `RSAFS_current.csv` is used only for estimand (d).\n\n**Exclusions.** None: 80 forecast–actual pairs out of 80, of which 20 belong to my model (`n_analysed`). See `out/exclusions.csv`.\n\n## Method\nAll four forecasts are computed from the RSAFS vintage dated V only:\n- **naive**: g_{last(V)} for both horizons;\n- **seasonal naive (snaive)**: g_{T−12} from the vintage;\n- **AR(1)**: OLS of g_m on a constant and g_{m−1}, 1993-02 ≤ m ≤ last(V), with iterated forecasts (coefficients in `ar1_coef_by_origin`);\n- **my model, \"base-effect drift\" (BED)** (`model_name`, `model_description`): the log level is extrapolated as ln L̂_T = ln L_last + h·μ, with μ = (ln L_last − ln L_{last−12})/12 (the latest YoY growth spread evenly across months). The forecast is ĝ_T = 100·(ln L̂_T − ln L_{T−12}), where the base-period level L_{T−12} is already published in vintage V. In words, the naive forecast is corrected for the known *base effect*, i.e. the monthly changes from a year ago that drop out of the YoY window, and h months of drift are added. The model estimates no parameters. Its specification was fixed before any out-of-sample error was computed, and no alternative variant was tried on the evaluation sample. PAYEMS and UMCSENT are not used.\n\nEvaluation: RMSE and MAE over the 10 origins per horizon against first-release YoY. Relative improvement = 1 − RMSE_model/RMSE_naive. Diebold–Mariano test of model vs naive: d_t = e²_naive − e²_model, Bartlett (Newey–West) long-run variance with truncation lag h−1, no HLN correction, two-sided normal p-value. Supplementary measure: a circular moving-block bootstrap (block length 3, B = 9999, seed `random_seed` = 20261030) of the paired errors, giving a 95 % percentile interval for RMSE_model − RMSE_naive. Estimand (d) is the mean over the 10 h=1 targets of |g_current − yoy_first_release|. Everything is produced by `out/analysis.py`.\n\n## Results\nRMSE / MAE in percentage points of YoY growth (`out/table1.csv`, n = 10 each):\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 (`rmse_naive_h1`) | 0.849 (`mae_naive_h1`) | 1.420 (`rmse_naive_h3`) | 1.200 (`mae_naive_h3`) |\n| seasonal naive | 1.675 (`rmse_snaive_h1`) | 1.307 (`mae_snaive_h1`) | 1.316 (`rmse_snaive_h3`) | 1.066 (`mae_snaive_h3`) |\n| AR(1) | 0.941 (`rmse_ar1_h1`) | 0.798 (`mae_ar1_h1`) | 1.187 (`rmse_ar1_h3`) | 0.953 (`mae_ar1_h3`) |\n| BED model | 0.550 (`rmse_model_h1`) | 0.486 (`mae_model_h1`) | 1.142 (`rmse_model_h3`) | 0.934 (`mae_model_h3`) |\n\n- **h = 1:** the BED model has the lowest RMSE and MAE of the four methods. Its RMSE is 44.8 % below naive (`rel_improvement_rmse_h1` = 0.448), and it has the smaller squared error at 8 of 10 origins (`n_model_wins_h1`). DM = 2.43, p = 0.015 (`dm_stat_h1`, `dm_pvalue_h1`), so `conclusion_code_h1` = `model_better_significant`.\n- **h = 3:** the BED model again has the lowest RMSE and MAE, but its margin over AR(1) is small (1.142 vs 1.187). Its RMSE is 19.6 % below naive (`rel_improvement_rmse_h3` = 0.196), with 6 wins out of 10 (`n_model_wins_h3`). DM = 1.55, p = 0.122 (`dm_stat_h3`, `dm_pvalue_h3`), so `conclusion_code_h3` = `model_better_not_significant`.\n- Seasonal naive is the worst method at h = 1 but beats naive at h = 3. AR(1) beats naive at both horizons.\n- **Revisions (d):** the first-release YoY growth of the 10 h=1 target months differs from the currently published growth by 0.548 pp on average (`mean_abs_revision_h1_targets`). The revisions are all downward (`mean_signed_revision_h1_targets` = −0.548; maximum 0.976 pp, `max_abs_revision_h1_targets`). That average revision is the same size as the BED model's h=1 RMSE.\n- Figure: `out/figure1.png` shows the first-release actuals with the naive and BED forecasts, one panel per horizon.\n\n## Uncertainty\nThere are only 10 origins, the evaluation window is a single year, and the h = 3 errors overlap. The DM statistic is compared with the standard normal, which is an asymptotic approximation. With n = 10 the Newey–West variance estimate is itself very noisy, and the test is known to over-reject in small samples (this is why the Harvey–Leybourne–Newbold correction exists; as the task specifies, it is not applied here). So the h = 1 p-value of 0.015 (`dm_pvalue_h1`) should be read as suggestive evidence, not decisive. With the HLN factor and t(9) critical values it would be less extreme; that variant was not computed for the reported keys. Two things support the h = 1 result: the model wins at 8 of 10 origins, and every block-bootstrap resample gives the model the lower RMSE. The 95 % interval for RMSE_model − RMSE_naive is [−0.649, −0.279] pp (`boot_rmse_diff_lo_h1`, `boot_rmse_diff_hi_h1`, `boot_share_model_better_h1`). This bootstrap is crude at n = 10 and should not be over-interpreted. At h = 3 the DM test does not reject (p = 0.122, `dm_pvalue_h3`), and the bootstrap interval [−0.688, 0.082] pp includes zero (`boot_rmse_diff_lo_h3`, `boot_rmse_diff_hi_h3`). An improvement over naive at h = 3 is plausible but not established.\n\n## Limitations and open issues\n- **Gate chronology check conflicts with the task definition.** The gate requires `origin_date < target_date` in `out/forecasts.csv`, which fails for all 40 h = 1 rows. TASK.md defines the target as last(V)+h, written as YYYY-MM-01. Since last(V) is always at least one month before the month of V, the h = 1 target month always begins on or before the month-end origin (e.g. origin 2026-04-30, target 2026-04-01). The forecast is still made before the target's value exists in any data: the target value is absent from vintage V, and its first-release vintage is later than the origin in all 80 rows (`out/state/checks.md`). I kept the target dates as TASK.md defines them rather than relabelling them to pass the gate. So the gate reports this one check as failed, and phases P4/P5 are marked \"blocked\" for this reason only. All other gate checks, including reproducibility, pass.\n- Small sample (10 origins, one year, a period with shutdown-related publication disruption). The ranking of methods could change in other periods.\n- The model was designed by one analyst, and its design reflects general knowledge of how YoY base effects work. I did not search over variants on these data. Still, I cannot fully exclude awareness of the general behaviour of 2025–26 data as a source of bias.\n- The h = 3 actuals for the last two origins (targets 2026-08 and 2026-09) come from vintages released after a large level revision. Within-vintage YoY growth is less affected than levels, but not entirely unaffected.\n- The large downward revision behind estimand (d) is mostly a single annual/benchmark revision. It is a statement about this particular window, not about typical revision sizes.\n- PAYEMS and UMCSENT were not used. Whether they would add information was not evaluated.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect drift model has the lowest RMSE and MAE of all four methods and reduces RMSE by about 45% relative to the naive forecast.\",\"results_keys\":[\"rmse_model_h1\",\"mae_model_h1\",\"rmse_naive_h1\",\"rmse_snaive_h1\",\"rmse_ar1_h1\",\"rel_improvement_rmse_h1\"],\"status\":\"supported\",\"caveat\":\"10 origins over one year only.\"},\n {\"id\":\"C2\",\"text\":\"At h=1 the Diebold-Mariano test (Newey-West lag 0, normal p-value) rejects equal accuracy of model and naive at 5%.\",\"results_keys\":[\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\",\"n_model_wins_h1\",\"boot_rmse_diff_lo_h1\",\"boot_rmse_diff_hi_h1\"],\"status\":\"supported\",\"caveat\":\"Asymptotic test with n=10 and no HLN correction; suggestive rather than decisive.\"},\n {\"id\":\"C3\",\"text\":\"At h=3 the model has a lower RMSE than naive (about 20% improvement) but the difference is not statistically significant.\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\",\"boot_rmse_diff_lo_h3\",\"boot_rmse_diff_hi_h3\"],\"status\":\"supported\",\"caveat\":\"Margin over AR(1) at h=3 is small; bootstrap interval includes zero.\"},\n {\"id\":\"C4\",\"text\":\"Seasonal naive is the worst method at h=1 but beats naive at h=3; AR(1) beats naive at both horizons.\",\"results_keys\":[\"rmse_snaive_h1\",\"rmse_snaive_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\",\"rmse_ar1_h1\",\"rmse_ar1_h3\"],\"status\":\"supported\",\"caveat\":\"No significance tests for baseline comparisons.\"},\n {\"id\":\"C5\",\"text\":\"The first-release YoY growth of the h=1 target months differs from currently published growth by about 0.55 pp on average, all revisions being downward.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"mean_signed_revision_h1_targets\",\"max_abs_revision_h1_targets\"],\"status\":\"supported\",\"caveat\":\"Dominated by one large annual/benchmark revision in 2026.\"},\n {\"id\":\"C6\",\"text\":\"All forecasts respect the information-availability rule: each uses only the RSAFS vintage dated at its origin, and every actual is first released after the origin.\",\"results_keys\":[\"last_month_by_origin\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"The gate's origin_date < target_date rule fails for h=1 rows by construction of the task's target definition; see Limitations.\"}\n]\nEOF\necho ok","description":"Write report and claims ledger"}}]}}114{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"8402385b-8c76-4013-a03c-86fe538305e3","timestamp":"2026-10-30T06:04:27.720Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"7a646460-80c9-4f23-95b9-a593d8e2a7f5","keep":36,"tail":["6fb1ed93f88c5cbab5a0f7b099c7a1b21889e40dfb1b2c37f63b0ee8b7687d9d","0a709ff77c854e5038b2acfb3f2a2b492be4045f701a2d7d52235446c6dc484d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",37,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"64c4f31ff4dcd69eedd6742a74d28329539adf3403f467183b3063c469e3c765"}115{"parentUuid":"84f7e6e5-cdc5-42f2-ae3e-045b2bd06dc7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv8eucwwXBhRosw8u9x","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5092,"cache_read_input_tokens":53348,"output_tokens":1327,"output_tokens_details":{"thinking_tokens":48},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":5092},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":380,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXv8edzeUWoVEzrCCvXU","requestRef":"8402385b-8c76-4013-a03c-86fe538305e3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5dc336c4-e8a4-402e-9b66-21edbf90b75f","timestamp":"2026-10-30T06:04:29.832Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}116{"parentUuid":"5dc336c4-e8a4-402e-9b66-21edbf90b75f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv8eucwwXBhRosw8u9x","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015wazQgW8miEzN4QN7v9rVP","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimands, outputs, info rules, invalidating conditions\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of all 23 data files recomputed and match README\",\"row/col counts, date ranges, missing values, duplicates, gaps recorded in data_audit.md\",\"first_release.csv levels and yoy recomputed and matched shipped vintages\",\"last(V) per origin tabulated; all 20 targets present\",\"exclusions.csv written (0 removed, 80->80)\"],\"notes\":\"RSAFS_current and first_release flagged as post-origin; used only for (d) / as actuals.\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) baselines computed from vintage V only; RMSE/MAE written to results.json (rmse_naive_h1=0.997, rmse_naive_h3=1.420)\"],\"notes\":\"Baselines computed by out/analysis.py with the same evaluation rule as the model.\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"out/analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png\",\"seed 20261030 fixed for bootstrap\",\"printed output consistent with results.json\"],\"notes\":\"Model: base-effect drift, no estimated parameters, specification fixed before evaluation.\"},\n\"P4\":{\"status\":\"blocked\",\"checks\":[\"clean re-run: results.json, forecasts.csv, table1.csv byte-identical: PASS\",\"independent recomputation of AR(1) (statsmodels), model, RMSE/MAE, DM, revision: PASS (see checks.md)\",\"first_release_vintage > origin for all 80 rows: PASS\",\"origin_date < target_date: FAIL for 40 h=1 rows by construction of TASK.md target definition (not leakage)\",\"gate run 1 receipt out/state/gate_receipts/20261030T060311.428944Z.json: failed (report/claims/phases missing at that time + forecasts_chronology)\"],\"notes\":\"Blocked solely by the gate's forecasts_chronology rule, which contradicts TASK.md's definition target=last(V)+h with target_date=YYYY-MM-01 for h=1. Not relabelled to avoid misrepresenting targets.\"},\n\"P5\":{\"status\":\"blocked\",\"checks\":[\"report.md written with all six sections and results-key citations\",\"claims.json written (6 claims, all referencing existing keys)\"],\"notes\":\"All deliverables complete; blocked only because the latest gate receipt fails forecasts_chronology (see P4).\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P2/P3 passed: baselines + BED model in out/analysis.py; h1 model better (DM p=0.015), h3 model better n.s. (p=0.122).\n- 2026-10-30 P4: verification checks pass; gate forecasts_chronology fails for 40 h=1 rows because TASK.md target dates (YYYY-MM-01 of last(V)+1) precede month-end origins. Decision: keep TASK.md definition, do not relabel; mark P4/P5 blocked and document.\n- 2026-10-30 P5: report.md and claims.json written.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Update phases, log, rerun gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5092,"cache_read_input_tokens":53348,"output_tokens":1327,"output_tokens_details":{"thinking_tokens":48},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":5092},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv8edzeUWoVEzrCCvXU","requestRef":"8402385b-8c76-4013-a03c-86fe538305e3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1886137d-150c-4975-9d3f-ed4994881352","timestamp":"2026-10-30T06:04:39.956Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}117{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"1886137d-150c-4975-9d3f-ed4994881352","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}118{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}119{"parentUuid":"1886137d-150c-4975-9d3f-ed4994881352","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015wazQgW8miEzN4QN7v9rVP","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060441.223227Z.json","is_error":false}]},"uuid":"f142fc1c-e1cf-4acf-bda2-4ec45a1f5c8f","timestamp":"2026-10-30T06:04:41.230Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060441.223227Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1886137d-150c-4975-9d3f-ed4994881352","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}120{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"a1af398dcb6e0bf6fe956c94d43eac4502f369d53239b23b2275d60314ac1ba6","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_015wazQgW8miEzN4QN7v9rVP","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimands, outputs, info rules, invalidating conditions\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of all 23 data files recomputed and match README\",\"row/col counts, date ranges, missing values, duplicates, gaps recorded in data_audit.md\",\"first_release.csv levels and yoy recomputed and matched shipped vintages\",\"last(V) per origin tabulated; all 20 targets present\",\"exclusions.csv written (0 removed, 80->80)\"],\"notes\":\"RSAFS_current and first_release flagged as post-origin; used only for (d) / as actuals.\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) baselines computed from vintage V only; RMSE/MAE written to results.json (rmse_naive_h1=0.997, rmse_naive_h3=1.420)\"],\"notes\":\"Baselines computed by out/analysis.py with the same evaluation rule as the model.\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"out/analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png\",\"seed 20261030 fixed for bootstrap\",\"printed output consistent with results.json\"],\"notes\":\"Model: base-effect drift, no estimated parameters, specification fixed before evaluation.\"},\n\"P4\":{\"status\":\"blocked\",\"checks\":[\"clean re-run: results.json, forecasts.csv, table1.csv byte-identical: PASS\",\"independent recomputation of AR(1) (statsmodels), model, RMSE/MAE, DM, revision: PASS (see checks.md)\",\"first_release_vintage > origin for all 80 rows: PASS\",\"origin_date < target_date: FAIL for 40 h=1 rows by construction of TASK.md target definition (not leakage)\",\"gate run 1 receipt out/state/gate_receipts/20261030T060311.428944Z.json: failed (report/claims/phases missing at that time + forecasts_chronology)\"],\"notes\":\"Blocked solely by the gate's forecasts_chronology rule, which contradicts TASK.md's definition target=last(V)+h with target_date=YYYY-MM-01 for h=1. Not relabelled to avoid misrepresenting targets.\"},\n\"P5\":{\"status\":\"blocked\",\"checks\":[\"report.md written with all six sections and results-key citations\",\"claims.json written (6 claims, all referencing existing keys)\"],\"notes\":\"All deliverables complete; blocked only because the latest gate receipt fails forecasts_chronology (see P4).\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P2/P3 passed: baselines + BED model in out/analysis.py; h1 model better (DM p=0.015), h3 model better n.s. (p=0.122).\n- 2026-10-30 P4: verification checks pass; gate forecasts_chronology fails for 40 h=1 rows because TASK.md target dates (YYYY-MM-01 of last(V)+1) precede month-end origins. Decision: keep TASK.md definition, do not relabel; mark P4/P5 blocked and document.\n- 2026-10-30 P5: report.md and claims.json written.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Update phases, log, rerun gate"}}]}}121{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"d69e722e-8ca6-4844-9d28-41c1bdd05cab","timestamp":"2026-10-30T06:04:41.234Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"8402385b-8c76-4013-a03c-86fe538305e3","keep":38,"tail":["a1af398dcb6e0bf6fe956c94d43eac4502f369d53239b23b2275d60314ac1ba6","254b112814aff5b083e0b4eea81e7820fa14ac8f7c9643f1a67c87f7fb5f6b6c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",39,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9b32f65749d3ae79eff3b5aaf581e59617bd97bb4bdc6db293fa84adb04666c2"}122{"parentUuid":"f142fc1c-e1cf-4acf-bda2-4ec45a1f5c8f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv9ehFXFEDqBNdomWbV","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01339G7eANERaQdbn7eePCFC","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']['checks'].append(\"gate run 2 (end of P4/P5) receipt out/state/gate_receipts/20261030T060441.223227Z.json: 64/65 pass; only forecasts_chronology fails (task-definition conflict)\")\np['P5']['checks'].append(\"gate run 2 receipt out/state/gate_receipts/20261030T060441.223227Z.json: only forecasts_chronology fails\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate run 20261030T060441.223227Z: 64/65 pass; forecasts_chronology fails (documented conflict). Stopping.\" >> out/state/log.md; ls out","description":"Record gate receipt in phase ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1458,"cache_read_input_tokens":58440,"output_tokens":389,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1458},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXv9eS8V7Vyfk8PzUGmP","requestRef":"d69e722e-8ca6-4844-9d28-41c1bdd05cab","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"63dfca61-05f8-4c36-8d3b-567b537a4d02","timestamp":"2026-10-30T06:04:45.028Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}123{"parentUuid":"63dfca61-05f8-4c36-8d3b-567b537a4d02","isSidechain":false,"promptId":"38c13cf6-09d6-4e9b-aa69-26ded31ae382","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01339G7eANERaQdbn7eePCFC","type":"tool_result","content":"analysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\nstate\ntable1.csv","is_error":false}]},"uuid":"c2ccbc10-bf4c-4a47-9578-b99e5e66db24","timestamp":"2026-10-30T06:04:45.089Z","toolUseResult":{"stdout":"analysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\nstate\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"63dfca61-05f8-4c36-8d3b-567b537a4d02","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}124{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"4a750b376cc8a64353af3371af870b9322b864c420a627f6dfe21f51b4c3288c","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01339G7eANERaQdbn7eePCFC","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']['checks'].append(\"gate run 2 (end of P4/P5) receipt out/state/gate_receipts/20261030T060441.223227Z.json: 64/65 pass; only forecasts_chronology fails (task-definition conflict)\")\np['P5']['checks'].append(\"gate run 2 receipt out/state/gate_receipts/20261030T060441.223227Z.json: only forecasts_chronology fails\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate run 20261030T060441.223227Z: 64/65 pass; forecasts_chronology fails (documented conflict). Stopping.\" >> out/state/log.md; ls out","description":"Record gate receipt in phase ledger"}}]}}125{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"71ca201a-8053-4cbe-a97a-54e7e701c157","timestamp":"2026-10-30T06:04:45.092Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"d69e722e-8ca6-4844-9d28-41c1bdd05cab","keep":40,"tail":["4a750b376cc8a64353af3371af870b9322b864c420a627f6dfe21f51b4c3288c","29ba20a2eceb330bebcdc5ae4d07202740e409af480fd779fe26afbffe5e1b10"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",41,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f46e325d0cf2c1392486ea50956098dfbbba1ef88cbd2a47cd88686360f4ece9"}126{"parentUuid":"c2ccbc10-bf4c-4a47-9578-b99e5e66db24","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv9wEASGY4BXHZ41Mtf","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSlAcKEAgTGAI4AUIIdGhpbmtpbmcSDIcX66MOGNzolIyZwxoMGd2OHaeeC01c7WQiIjAFL+kKm8sB6C3EbQw3sLH7IuMihZt9y7SofUrUSJppU8BdZ99Kma+HTuafiYsdS0EqsQbznGfX8c5wdzJV0LdY14UIwDLdps/S+O2BQLosvINZjuXDWx4n5gsziEDb+uE+LeZO9jh8Z7kksonlfqGW/VOA48ho0fkArGLbzS/7rF6pgQVHFxHjAJGxa7vYSXbsiDvrbNv4p+Ln+yzh7RyoTyNc8FC+uV2JK4D3WJrNYY32VD8u212t09GInLWAQccJRnT1LgMcF3ppbXmw48f3D0f/me0tDd4Km/TfkalP4liI9pkPSRqArGgvcFfzfVeGYaPkaCOadT/twQ2JBuxbYNQsW3Lr0iGfy+kub8dh4RLzkbDnvNrkG2wg8DYcRqG4NknLWicM1ptyT8PyLdTgbqxDn9Qf6feyv9GZWJ6fo/8zjF9h/IbmPrYoxVW5XeXa5JaNT7ZwZBJfJVJbZr2iJBVshDti/koHnxFLcTu62HoTaXTwAZ5d1IfeKENy6GGVtgFSELhVo9EXYzkXntRAkVvSH/bZ+zAapRYKnseAalLN32v2JtraWJVPefxOEDvBIQmJqJg629+ooVEyz66qYagzCPgwGnCbQhKiPJi5cZWVTCid97BlUhEazffJl4EiQWEbIRgjx+Lf7mlCAb3WJ/jiH+wyvk0eTDSevr6x+aZu4zLehQ57Z68cuv0Bo4E6bXUsZv2LxL26p2qVxbHqVzKwrZGSMcCNW+pTJ7d8GdXNxL5SGlCuDKo2Gqbf1Uk6rwO2bJ5uX6NAJ3qSgSPXmDIIUz5wG6plYHfvK70CvhDvO+3jt+MxnoG3YWR/E+bU3XHSmESJJGfL/QKCR7IJ3YZMInJzxsySJxP/LuN5YG/7KbP7zP6AcxtBQ4X+MllnaG2zubTYKvwzNntbHjNKjjF0pR2M2czFNh+HzR9SjrpCe7F/pnOlkFLyBwucml3hH9JA7QVOIpzrtyZKdnYZ+oSiHOGez4eekvGRMSH8GnWXa7NfF4Gi4Y0lipPxgf4U/UR9w2qvyhMlPFqcNOJRojzgUx3v8oHASgIFPGhdaBA19MdWXTFtB154T7LpviAPEp1C28jvR66zmSQh8ISjE93cEkAsxrWZTfb+/Ms5hj1mO8Ls5ayoxRYNeFPDhxNuyS23GAE="}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":442,"cache_read_input_tokens":59898,"output_tokens":1187,"output_tokens_details":{"thinking_tokens":44},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":442},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6709,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXv9vw4EKfyJidHv1JAA","requestRef":"71ca201a-8053-4cbe-a97a-54e7e701c157","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3fff96d5-0322-4cde-bd37-cb7529b72ebc","timestamp":"2026-10-30T06:04:53.227Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}127{"parentUuid":"3fff96d5-0322-4cde-bd37-cb7529b72ebc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXv9wEASGY4BXHZ41Mtf","type":"message","role":"assistant","content":[{"type":"text","text":"All the deliverables are written, but the gate still fails one of its 65 checks: `forecasts_chronology`. I left that failure in place on purpose rather than change the data to pass it.\n\n**Why it fails.** The gate requires `origin_date < target_date` in `out/forecasts.csv`. `TASK.md` defines the target as last(V)+h, written as YYYY-MM-01, where last(V) is the last month published in the vintage. That month is always at least one month before the vintage date. So the 1-month-ahead target month always starts on or before the month-end origin: for example, origin 2026-04-30 has last month 2026-03 and target 2026-04-01. This affects all 40 h = 1 rows. It is not leakage. The target's value is not in the vintage used, and its first-release vintage is later than the origin in all 80 rows; I checked this separately. Writing different target dates would misstate the target month, so I marked phases P4 and P5 as \"blocked\" for this reason only. To clear the gate, either the gate rule or the task's target definition would have to change.\n\n**Results** (10 origins, 2025-10-31 to 2026-07-31; errors in percentage points of year-over-year growth, against first-release values):\n\n| method | RMSE h=1 | RMSE h=3 |\n|---|---|---|\n| naive | 0.997 | 1.420 |\n| seasonal naive | 1.675 | 1.316 |\n| AR(1) | 0.941 | 1.187 |\n| my model | 0.550 | 1.142 |\n\n- **My model:** it starts from the naive forecast and corrects for the year-ago monthly changes that drop out of the 12-month window. It then adds h months of drift at the latest growth rate. It uses only the retail-sales vintage published at each origin and estimates nothing. I fixed it before computing any errors and tried no other versions. Payroll and consumer-sentiment data were not used.\n- **h = 1:** RMSE is 45% below naive, and the model had the smaller squared error at 8 of 10 origins. Diebold–Mariano statistic 2.43, p = 0.015, so the model is significantly better at 5%. With only 10 origins and no small-sample correction, treat this as suggestive rather than decisive.\n- **h = 3:** RMSE is 20% below naive, with 6 wins out of 10. Diebold–Mariano statistic 1.55, p = 0.12, so the improvement is not significant. A supplementary bootstrap interval for the RMSE difference also includes zero. The model's edge over AR(1) at this horizon is small.\n- **Revisions:** the first-release growth of the 10 one-month-ahead target months differs from today's published growth by 0.548 points on average, all downward. This is mostly one large level revision in 2026, which also affects the 3-month actuals for the last two origins.\n\nData issues found: delayed publication (the first six vintages end two months before their date, and 2026-04-30 adds two months at once) and routine revisions of recent months. The original copy of the data was not modified and no observations were excluded.\n\nThe other 64 gate checks pass, including the rerun that reproduces the results exactly, and the script also passed an independent recomputation.\n\nFiles are in `out/`:\n- results.json\n- forecasts.csv\n- table1.csv\n- figure1.png\n- report.md\n- claims.json\n- analysis.py\n- exclusions.csv\n- state/ (contract, data audit, checks, phase ledger, log, gate receipts)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":442,"cache_read_input_tokens":59898,"output_tokens":1187,"output_tokens_details":{"thinking_tokens":44},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":442},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXv9vw4EKfyJidHv1JAA","requestRef":"71ca201a-8053-4cbe-a97a-54e7e701c157","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"42744515-b3fd-4119-a914-764da250377a","timestamp":"2026-10-30T06:04:57.001Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}128{"type":"last-prompt","lastPrompt":"Begin now. The task is in `TASK.md` in the current directory. Work until the deliverables are complete, then stop.","leafUuid":"42744515-b3fd-4119-a914-764da250377a","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}129{"type":"cost-state","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","totalCostUSD":1.0197702,"totalAPIDuration":257582,"totalAPIDurationWithoutRetries":257571,"totalToolDuration":8530,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":269478,"startTime":1793340027530,"modelUsage":{"claude-opus-5-5":{"inputTokens":44,"outputTokens":28232,"thinkingTokens":5387,"cacheReadInputTokens":766271,"cacheCreationInputTokens":60340,"cacheCreationEphemeral5mInputTokens":60340,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.0197702}},"hasUnknownModelCost":false}130{"type":"tools-used","tools":["Bash","Read"],"sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}131{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T06:04:58.571Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","content":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/phases.json`, and stop when it passes. Do not change `data/`. Gate output:\n\nPGAR GATE — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80"}132{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T06:04:58.571Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}133{"parentUuid":"42744515-b3fd-4119-a914-764da250377a","isSidechain":false,"promptId":"e4037483-4f26-4cdd-926b-c557ff004613","type":"user","message":{"role":"user","content":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/phases.json`, and stop when it passes. Do not change `data/`. Gate output:\n\nPGAR GATE — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80"},"uuid":"2f931ccf-8ddb-4bcb-8942-8c55169fca95","timestamp":"2026-10-30T06:04:58.575Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":2},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}134{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"2dafc16a-7b9c-4cbe-ba3c-a7618e2e1120","timestamp":"2026-10-30T06:04:58.590Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["6c04ea332e967905c33c745fc622389d61d9c85bed742510c97f7f1aacb07760","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","440fd780c0a58aac92cd8b1da6d3a47540f825a83473a3075410b93e3d11895d","f7923369558f68f3a36c4a818f7f9fb3d81f6253405c4ff5a27708ed8cf60ee5","bc6cb6081bc9b8cc6b837be8411352097d50a5c34e3a5d8704a889354381b551","2f4eed6ac83970cc015598ea39dff0ca79cd58476b1718952fb47487b692544b","0d0ae56c2f010697b4c19bc91c1e08dc4310f036f2282037abcd7e5f97f15c35","8b86d1de7ac5ad6b44fd70efdae61390830960125fdeea60570b32406adc690c","1423c8a62d371bfee428cec26ce0f4ef27f720902187cbf3008ed0cc2031078d","2e2836cf9c952cb344371e8365e1247c6a269c55f9dd2600e20834577c3c070a","3df19427ebf76b33c9c814c4c91df231aa14f015d28bf531676c22f4ecc3675c","93cc2bda34bf4d12669f2e2ddacbec4171422df4d198834bd9ec04d8186bc7d1","71bb88cdfe7b8f37eddb1d7d112d6239725c93434438550e8b4bb44ac5faca66","9ccb314419ff31e5c94aac6b55688b996a49be22484ea0902ff8aac2e03e3bbb","4d6dd9172337f9057a1da0c52eae77349522cad1eac371529cd9b21d1c4f9579","0ae30b375721557a1bd778436e2f996337c7a4b2a32c04ee3198ae8630996008","44b052e9b2cc60d46fb40872608f2a7b0a367499d7b5f404357486a93a82e6bc","516ef0b234d49a3042fb1f7c38a012ab169686f661fd20a6f9b9701626e6f8eb","4944dc4f759c4691f901f33370344f54746729a0f6f53ae48ee29031225a0ddc","297f11eb984fcec0d6784434cf4b8d98db610bb8a76b77645cae733a798532ec","2b891af3cf4c84d1fb7e4eb1abad1bddfd8111b40c581291aebce43be04988ba","f89d9a8898f6668d4235e26158006db4a9c3b581d759e71bf573d013f5c47806","392b72740628466b53e2fe921b8ad7894ac19cac4600cff111860b3384e57985","8ebef63b43544edb2bdd1e5d5ccf1c86b913f7c429e531c46f63904dd1b6fc7a","4a6788b247c76be6da268c44511eeeac1017f73682ffa376ee8fff1cfcafee61","4812cba4ced36a4da2096afd35b330980e2e65b960c5ab27a55bf79fa045acf4","ef419b93b16e834a21cbc32cee0caf1f23c0fa15ab2ff480ba490a15f5ed9dfc","e50d5d69b3462527a7af96c8abd4e86046b9a2ddd9509c285bf80c7af6aa9f9c","e1a111fb6a43005bedf7d5b31eebbba0374259e205ee32b12e71bf08599f56a4","bd330bc245a0d56571e0bf8bd245e93aba415104a648fce61b569a8caf602728","a9503ee5c1ab02db89fe42e928f59178243fbbfda0f3b109e10bdb26475fc091","6f89a704dff69ab0762ebcfbd9697385e22c326e1de728ac525486e8c57ba019","8b755eeef7c38e3bb474d8c6ffcb2fabb478b4aac58fa8a09002bcf4e6004770","4e0168cdf82b82e081533ef82e2c5ffd461c2700753b36b53e8a36ffdeb4d9b4","20dcb37141804282223deb7612d5d95a858baa698024c0025afb3f6304616f97","efdf0a2002ad6bc07550b29ebaba15c43f55b325837ee2204b16153e2a675834","6fb1ed93f88c5cbab5a0f7b099c7a1b21889e40dfb1b2c37f63b0ee8b7687d9d","0a709ff77c854e5038b2acfb3f2a2b492be4045f701a2d7d52235446c6dc484d","a1af398dcb6e0bf6fe956c94d43eac4502f369d53239b23b2275d60314ac1ba6","254b112814aff5b083e0b4eea81e7820fa14ac8f7c9643f1a67c87f7fb5f6b6c","4a750b376cc8a64353af3371af870b9322b864c420a627f6dfe21f51b4c3288c","29ba20a2eceb330bebcdc5ae4d07202740e409af480fd779fe26afbffe5e1b10","54c51b028c49d0368fc4cde61fa94f1a2716b35a2a16e7523cec206c0c81aeb7","cb492344cf39928c41b00503cbda90c013bf42cdb83e899ac6936853144a5f03"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",43,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"56c913e3eb7239a7c2f03b525b6c2dfee51b4642baf95e9e2bd336caaf25f281"}135{"parentUuid":"2f931ccf-8ddb-4bcb-8942-8c55169fca95","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvAzXNoKwMvSjj2JeTh","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":1338,"cache_read_input_tokens":60340,"output_tokens":691,"output_tokens_details":{"thinking_tokens":410},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1338},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3774,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXvAypU3LVFxTeHfKyes","requestRef":"2dafc16a-7b9c-4cbe-ba3c-a7618e2e1120","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f6121c0b-30ab-42d4-a868-91aacb05cb0e","timestamp":"2026-10-30T06:05:04.300Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}136{"parentUuid":"f6121c0b-30ab-42d4-a868-91aacb05cb0e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvAzXNoKwMvSjj2JeTh","type":"message","role":"assistant","content":[{"type":"text","text":"The failing check can't be passed without misstating the data. I'll confirm the current state and record it."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":1338,"cache_read_input_tokens":60340,"output_tokens":691,"output_tokens_details":{"thinking_tokens":410},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1338},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXvAypU3LVFxTeHfKyes","requestRef":"2dafc16a-7b9c-4cbe-ba3c-a7618e2e1120","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1c4594a6-8e82-49d3-ba39-d78fe11ec0ec","timestamp":"2026-10-30T06:05:04.898Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}137{"parentUuid":"1c4594a6-8e82-49d3-ba39-d78fe11ec0ec","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvAzXNoKwMvSjj2JeTh","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Ms2WxhM367Ak6vQxmpZYcK","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nF=pd.read_csv('out/forecasts.csv')\nb=F[F.target_date<=F.origin_date]\nprint(b[b.model=='naive'][['origin_date','target_date','horizon']].to_string(index=False))\"","description":"Re-run gate and list failing rows"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":1338,"cache_read_input_tokens":60340,"output_tokens":691,"output_tokens_details":{"thinking_tokens":410},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1338},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXvAypU3LVFxTeHfKyes","requestRef":"2dafc16a-7b9c-4cbe-ba3c-a7618e2e1120","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"706fb1ea-a88f-4086-9adf-6925d88c0b46","timestamp":"2026-10-30T06:05:06.474Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}138{"parentUuid":"706fb1ea-a88f-4086-9adf-6925d88c0b46","isSidechain":false,"promptId":"e4037483-4f26-4cdd-926b-c557ff004613","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Ms2WxhM367Ak6vQxmpZYcK","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060507.995429Z.json\norigin_date target_date horizon\n 2025-10-31 2025-09-01 1\n 2025-11-30 2025-10-01 1\n 2025-12-31 2025-11-01 1\n 2026-01-31 2025-12-01 1\n 2026-02-28 2026-01-01 1\n 2026-03-31 2026-02-01 1\n 2026-04-30 2026-04-01 1\n 2026-05-31 2026-05-01 1\n 2026-06-30 2026-06-01 1\n 2026-07-31 2026-07-01 1","is_error":false}]},"uuid":"2560e2e5-9ca5-46a9-9792-7698a647e5c2","timestamp":"2026-10-30T06:05:08.280Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060507.995429Z.json\norigin_date target_date horizon\n 2025-10-31 2025-09-01 1\n 2025-11-30 2025-10-01 1\n 2025-12-31 2025-11-01 1\n 2026-01-31 2025-12-01 1\n 2026-02-28 2026-01-01 1\n 2026-03-31 2026-02-01 1\n 2026-04-30 2026-04-01 1\n 2026-05-31 2026-05-01 1\n 2026-06-30 2026-06-01 1\n 2026-07-31 2026-07-01 1","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"706fb1ea-a88f-4086-9adf-6925d88c0b46","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}139{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"021bee48b17d945ed6e254500baac8b898eeb3a3f968f2832f633958c24c98d7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"The failing check can't be passed without misstating the data. I'll confirm the current state and record it."},{"type":"tool_use","id":"toolu_01Ms2WxhM367Ak6vQxmpZYcK","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nF=pd.read_csv('out/forecasts.csv')\nb=F[F.target_date<=F.origin_date]\nprint(b[b.model=='naive'][['origin_date','target_date','horizon']].to_string(index=False))\"","description":"Re-run gate and list failing rows"}}]}}140{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"64548e28-e1ba-4511-b53d-f9941e4e659a","timestamp":"2026-10-30T06:05:08.286Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"2dafc16a-7b9c-4cbe-ba3c-a7618e2e1120","keep":44,"tail":["021bee48b17d945ed6e254500baac8b898eeb3a3f968f2832f633958c24c98d7","a179a2de817dbd604d4cf5ac7628a8dbc7d3cdf3d3ebb0d1ece7274ab4755cfb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",45,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ca42d2dc4580e7a25da8178252843839113fa441e838ee5cebc74c780f1e55ff"}141{"parentUuid":"2560e2e5-9ca5-46a9-9792-7698a647e5c2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvBefKwR5m7nCvQbEV1","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1006,"cache_read_input_tokens":61678,"output_tokens":830,"output_tokens_details":{"thinking_tokens":82},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1006},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":528,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXvBe6qeGBLMHmgGVJsg","requestRef":"64548e28-e1ba-4511-b53d-f9941e4e659a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a1330725-902b-4bb8-94df-053c514e10d3","timestamp":"2026-10-30T06:05:10.435Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}142{"parentUuid":"a1330725-902b-4bb8-94df-053c514e10d3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvBefKwR5m7nCvQbEV1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01AwQpfZMv3jAeMS8SWerfmh","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\nnote=(\"gate run 3 (controller resume) receipt out/state/gate_receipts/20261030T060507.995429Z.json: only forecasts_chronology fails. \"\n \"Not fixable honestly: for every h=1 row the target month (last(V)+1, per TASK.md) lies entirely on or before the month-end origin \"\n \"(6 origins: whole target month before origin; 4 origins: target month = origin month). No date inside the target month satisfies origin_date < target_date, \"\n \"so passing would require writing a date outside the target month, which would falsify forecasts.csv.\")\np['P4']['checks'].append(note); p['P5']['checks'].append(note)\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ncat >> out/report.md <<'EOF'\n- **Controller resume (gate re-run).** The controller re-ran the gate and reported the same single failure (`forecasts_chronology`); I re-ran it again and got the same result (receipt `20261030T060507.995429Z`). For 6 of the 10 h = 1 rows (origins 2025-10-31 to 2026-03-31) the whole target month lies before the origin date. For the other 4 (2026-04-30 to 2026-07-31) the target month is the origin's own month. So no date inside the target month satisfies `origin_date < target_date`. To pass the check I would have to write a date outside the target month, for example the first-release date, into a column that TASK.md defines as the target month. That would falsify the deliverable, so I did not do it. Resolving this requires changing either the gate rule or the task's target definition.\nEOF\necho \"- 2026-10-30 Controller resume: gate re-run, same single failure; not fixable without falsifying target_date; documented in report and phases.json. Stopping.\" >> out/state/log.md","description":"Record resume outcome in ledger, report, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1006,"cache_read_input_tokens":61678,"output_tokens":830,"output_tokens_details":{"thinking_tokens":82},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1006},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXvBe6qeGBLMHmgGVJsg","requestRef":"64548e28-e1ba-4511-b53d-f9941e4e659a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aae9ba0c-c10d-46ee-8122-0bb746aac40f","timestamp":"2026-10-30T06:05:16.329Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}143{"parentUuid":"aae9ba0c-c10d-46ee-8122-0bb746aac40f","isSidechain":false,"promptId":"e4037483-4f26-4cdd-926b-c557ff004613","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01AwQpfZMv3jAeMS8SWerfmh","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"fd7423cc-198c-487b-8f53-f30b8e2132ae","timestamp":"2026-10-30T06:05:16.409Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"aae9ba0c-c10d-46ee-8122-0bb746aac40f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}144{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"5012479d5090f310fc6cf82088256eec83077bd44ba82f9578af964a13e32a21","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01AwQpfZMv3jAeMS8SWerfmh","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\nnote=(\"gate run 3 (controller resume) receipt out/state/gate_receipts/20261030T060507.995429Z.json: only forecasts_chronology fails. \"\n \"Not fixable honestly: for every h=1 row the target month (last(V)+1, per TASK.md) lies entirely on or before the month-end origin \"\n \"(6 origins: whole target month before origin; 4 origins: target month = origin month). No date inside the target month satisfies origin_date < target_date, \"\n \"so passing would require writing a date outside the target month, which would falsify forecasts.csv.\")\np['P4']['checks'].append(note); p['P5']['checks'].append(note)\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ncat >> out/report.md <<'EOF'\n- **Controller resume (gate re-run).** The controller re-ran the gate and reported the same single failure (`forecasts_chronology`); I re-ran it again and got the same result (receipt `20261030T060507.995429Z`). For 6 of the 10 h = 1 rows (origins 2025-10-31 to 2026-03-31) the whole target month lies before the origin date. For the other 4 (2026-04-30 to 2026-07-31) the target month is the origin's own month. So no date inside the target month satisfies `origin_date < target_date`. To pass the check I would have to write a date outside the target month, for example the first-release date, into a column that TASK.md defines as the target month. That would falsify the deliverable, so I did not do it. Resolving this requires changing either the gate rule or the task's target definition.\nEOF\necho \"- 2026-10-30 Controller resume: gate re-run, same single failure; not fixable without falsifying target_date; documented in report and phases.json. Stopping.\" >> out/state/log.md","description":"Record resume outcome in ledger, report, log"}}]}}145{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"12483dd0-9369-42bf-bddc-27d08233a7a7","timestamp":"2026-10-30T06:05:16.414Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"64548e28-e1ba-4511-b53d-f9941e4e659a","keep":46,"tail":["5012479d5090f310fc6cf82088256eec83077bd44ba82f9578af964a13e32a21","db374fda8664734ca19cff655ed4032e8c5df85af8d21f27d6ac52c1a01b1f2f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",47,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"434c002c017d88a50bbaad730c7a8c42a55e9f257f87353589dd96eb4b188728"}146{"parentUuid":"fd7423cc-198c-487b-8f53-f30b8e2132ae","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvCFBxjPRsVhK3FeJyK","type":"message","role":"assistant","content":[{"type":"text","text":"The gate still fails, and I can't make it pass without writing false dates into the results. I re-ran it (receipt `out/state/gate_receipts/20261030T060507.995429Z.json`): 64 of 65 checks pass, and the only failure is still `forecasts_chronology`.\n\n**Why I can't fix it honestly:**\n- `TASK.md` says each target month is the last published month plus h. For h = 1, that month always starts on or before the origin date:\n - For 6 of the 10 origins (2025-10-31 to 2026-03-31), the whole target month comes before the origin. For example, origin 2025-10-31 targets September 2025.\n - For the other 4 (2026-04-30 to 2026-07-31), the target is the origin's own month. For example, origin 2026-04-30 targets April 2026.\n- No date inside the target month satisfies `origin_date < target_date`. To pass, I would have to put a date outside the target month (such as the date the figure was first published) in the column `TASK.md` defines as the target month. That would make `forecasts.csv` false, so I didn't.\n- It isn't leakage. No forecast uses the value it is predicting, and that value was first published after the origin in all 80 rows.\n\n**What I changed:** I didn't change `data/` or any result. I added this explanation to the \"Limitations and open issues\" section of `out/report.md`, recorded the new receipt in `out/state/phases.json` (P4 and P5 stay \"blocked\"), and logged it in `out/state/log.md`.\n\nTo clear the check, either the gate rule has to change or the task has to define target dates differently."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":845,"cache_read_input_tokens":62684,"output_tokens":527,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":845},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXvCErcm2hH1XAUQ1MLe","requestRef":"12483dd0-9369-42bf-bddc-27d08233a7a7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"55776ec6-6deb-4d87-a542-addb43cb17a9","timestamp":"2026-10-30T06:05:22.353Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}147{"type":"last-prompt","lastPrompt":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/pha…","leafUuid":"55776ec6-6deb-4d87-a542-addb43cb17a9","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}148{"type":"mode","mode":"normal","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}149{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}150{"type":"cost-state","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","totalCostUSD":1.1136476,"totalAPIDuration":279484,"totalAPIDurationWithoutRetries":279471,"totalToolDuration":10393,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":293278,"startTime":1793340027530,"modelUsage":{"claude-opus-5-5":{"inputTokens":52,"outputTokens":30280,"thinkingTokens":5879,"cacheReadInputTokens":950973,"cacheCreationInputTokens":63529,"cacheCreationEphemeral5mInputTokens":63529,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.1136476}},"hasUnknownModelCost":false}151{"type":"tools-used","tools":["Bash","Read"],"sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}152{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T06:05:23.920Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","content":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/phases.json`, and stop when it passes. Do not change `data/`. Gate output:\n\nPGAR GATE — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80"}153{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T06:05:23.921Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}154{"parentUuid":"55776ec6-6deb-4d87-a542-addb43cb17a9","isSidechain":false,"promptId":"8ecc4fc8-cf8a-47a6-bb0f-1caace35a647","type":"user","message":{"role":"user","content":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/phases.json`, and stop when it passes. Do not change `data/`. Gate output:\n\nPGAR GATE — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80"},"uuid":"b3a1404c-4cd5-47aa-8d26-ec6db1fd714c","timestamp":"2026-10-30T06:05:23.925Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":3},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}155{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"8d544c2b-bda4-4c40-952c-f19b340e89c2","timestamp":"2026-10-30T06:05:23.939Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["6c04ea332e967905c33c745fc622389d61d9c85bed742510c97f7f1aacb07760","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","440fd780c0a58aac92cd8b1da6d3a47540f825a83473a3075410b93e3d11895d","f7923369558f68f3a36c4a818f7f9fb3d81f6253405c4ff5a27708ed8cf60ee5","bc6cb6081bc9b8cc6b837be8411352097d50a5c34e3a5d8704a889354381b551","2f4eed6ac83970cc015598ea39dff0ca79cd58476b1718952fb47487b692544b","0d0ae56c2f010697b4c19bc91c1e08dc4310f036f2282037abcd7e5f97f15c35","8b86d1de7ac5ad6b44fd70efdae61390830960125fdeea60570b32406adc690c","1423c8a62d371bfee428cec26ce0f4ef27f720902187cbf3008ed0cc2031078d","2e2836cf9c952cb344371e8365e1247c6a269c55f9dd2600e20834577c3c070a","3df19427ebf76b33c9c814c4c91df231aa14f015d28bf531676c22f4ecc3675c","93cc2bda34bf4d12669f2e2ddacbec4171422df4d198834bd9ec04d8186bc7d1","71bb88cdfe7b8f37eddb1d7d112d6239725c93434438550e8b4bb44ac5faca66","9ccb314419ff31e5c94aac6b55688b996a49be22484ea0902ff8aac2e03e3bbb","4d6dd9172337f9057a1da0c52eae77349522cad1eac371529cd9b21d1c4f9579","0ae30b375721557a1bd778436e2f996337c7a4b2a32c04ee3198ae8630996008","44b052e9b2cc60d46fb40872608f2a7b0a367499d7b5f404357486a93a82e6bc","516ef0b234d49a3042fb1f7c38a012ab169686f661fd20a6f9b9701626e6f8eb","4944dc4f759c4691f901f33370344f54746729a0f6f53ae48ee29031225a0ddc","297f11eb984fcec0d6784434cf4b8d98db610bb8a76b77645cae733a798532ec","2b891af3cf4c84d1fb7e4eb1abad1bddfd8111b40c581291aebce43be04988ba","f89d9a8898f6668d4235e26158006db4a9c3b581d759e71bf573d013f5c47806","392b72740628466b53e2fe921b8ad7894ac19cac4600cff111860b3384e57985","8ebef63b43544edb2bdd1e5d5ccf1c86b913f7c429e531c46f63904dd1b6fc7a","4a6788b247c76be6da268c44511eeeac1017f73682ffa376ee8fff1cfcafee61","4812cba4ced36a4da2096afd35b330980e2e65b960c5ab27a55bf79fa045acf4","ef419b93b16e834a21cbc32cee0caf1f23c0fa15ab2ff480ba490a15f5ed9dfc","e50d5d69b3462527a7af96c8abd4e86046b9a2ddd9509c285bf80c7af6aa9f9c","e1a111fb6a43005bedf7d5b31eebbba0374259e205ee32b12e71bf08599f56a4","bd330bc245a0d56571e0bf8bd245e93aba415104a648fce61b569a8caf602728","a9503ee5c1ab02db89fe42e928f59178243fbbfda0f3b109e10bdb26475fc091","6f89a704dff69ab0762ebcfbd9697385e22c326e1de728ac525486e8c57ba019","8b755eeef7c38e3bb474d8c6ffcb2fabb478b4aac58fa8a09002bcf4e6004770","4e0168cdf82b82e081533ef82e2c5ffd461c2700753b36b53e8a36ffdeb4d9b4","20dcb37141804282223deb7612d5d95a858baa698024c0025afb3f6304616f97","efdf0a2002ad6bc07550b29ebaba15c43f55b325837ee2204b16153e2a675834","6fb1ed93f88c5cbab5a0f7b099c7a1b21889e40dfb1b2c37f63b0ee8b7687d9d","0a709ff77c854e5038b2acfb3f2a2b492be4045f701a2d7d52235446c6dc484d","a1af398dcb6e0bf6fe956c94d43eac4502f369d53239b23b2275d60314ac1ba6","254b112814aff5b083e0b4eea81e7820fa14ac8f7c9643f1a67c87f7fb5f6b6c","4a750b376cc8a64353af3371af870b9322b864c420a627f6dfe21f51b4c3288c","29ba20a2eceb330bebcdc5ae4d07202740e409af480fd779fe26afbffe5e1b10","54c51b028c49d0368fc4cde61fa94f1a2716b35a2a16e7523cec206c0c81aeb7","cb492344cf39928c41b00503cbda90c013bf42cdb83e899ac6936853144a5f03","021bee48b17d945ed6e254500baac8b898eeb3a3f968f2832f633958c24c98d7","a179a2de817dbd604d4cf5ac7628a8dbc7d3cdf3d3ebb0d1ece7274ab4755cfb","5012479d5090f310fc6cf82088256eec83077bd44ba82f9578af964a13e32a21","db374fda8664734ca19cff655ed4032e8c5df85af8d21f27d6ac52c1a01b1f2f","1a56519e52701bd38a80297718d083d13a8f0c22c80284f336d7f0f94615183e","cb492344cf39928c41b00503cbda90c013bf42cdb83e899ac6936853144a5f03"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",49,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"30e66f3c0dbff18175bd491c7721bbb12e11b345a6a828ae1b7c7c2ced4ac434"}156{"parentUuid":"b3a1404c-4cd5-47aa-8d26-ec6db1fd714c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvCxYdd1RAdH7ee3CHx","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":678,"cache_read_input_tokens":63529,"output_tokens":455,"output_tokens_details":{"thinking_tokens":32},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":678},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":559,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXvCx75rKtp6CUkNZdhx","requestRef":"8d544c2b-bda4-4c40-952c-f19b340e89c2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"debc8034-5afd-4965-aa98-ef16bf250720","timestamp":"2026-10-30T06:05:31.030Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}157{"parentUuid":"debc8034-5afd-4965-aa98-ef16bf250720","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvCxYdd1RAdH7ee3CHx","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PmonygBKgnSCcAsHRZBYE5","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"; R=$(ls out/state/gate_receipts | tail -1); ~/wp29/venv/bin/python - \"$R\" <<'EOF'\nimport json,sys\np=json.load(open('out/state/phases.json'))\nn=f\"gate run 4 (second controller resume) receipt out/state/gate_receipts/{sys.argv[1]}: only forecasts_chronology fails; unchanged conflict with TASK.md target definition; not relabelled (would falsify target_date).\"\np['P4']['checks'].append(n); p['P5']['checks'].append(n)\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Second controller resume: gate re-run ($R), same single failure; no honest fix exists; stopping.\" >> out/state/log.md","description":"Re-run gate and record receipt"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":678,"cache_read_input_tokens":63529,"output_tokens":455,"output_tokens_details":{"thinking_tokens":32},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":678},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXvCx75rKtp6CUkNZdhx","requestRef":"8d544c2b-bda4-4c40-952c-f19b340e89c2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"af934ddb-047a-4cc1-9293-ff366c820446","timestamp":"2026-10-30T06:05:33.769Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}158{"parentUuid":"af934ddb-047a-4cc1-9293-ff366c820446","isSidechain":false,"promptId":"8ecc4fc8-cf8a-47a6-bb0f-1caace35a647","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PmonygBKgnSCcAsHRZBYE5","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060535.228254Z.json","is_error":false}]},"uuid":"205e05d1-4f12-4504-aa2c-fe5185132b6d","timestamp":"2026-10-30T06:05:35.264Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060535.228254Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"af934ddb-047a-4cc1-9293-ff366c820446","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}159{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"573f05b50b1571a31779d87a7a015265ea166d934bbfb489c78c96b17d7fa4f4","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01PmonygBKgnSCcAsHRZBYE5","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"; R=$(ls out/state/gate_receipts | tail -1); ~/wp29/venv/bin/python - \"$R\" <<'EOF'\nimport json,sys\np=json.load(open('out/state/phases.json'))\nn=f\"gate run 4 (second controller resume) receipt out/state/gate_receipts/{sys.argv[1]}: only forecasts_chronology fails; unchanged conflict with TASK.md target definition; not relabelled (would falsify target_date).\"\np['P4']['checks'].append(n); p['P5']['checks'].append(n)\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Second controller resume: gate re-run ($R), same single failure; no honest fix exists; stopping.\" >> out/state/log.md","description":"Re-run gate and record receipt"}}]}}160{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"7038af53-48ff-4823-96bf-f8e3a2d23030","timestamp":"2026-10-30T06:05:35.270Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"8d544c2b-bda4-4c40-952c-f19b340e89c2","keep":50,"tail":["573f05b50b1571a31779d87a7a015265ea166d934bbfb489c78c96b17d7fa4f4","1a285cd553cce9922180b8a6f6675d53d78972e3305a9bc98381df554f6cec2d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",51,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f3401c281c30c36b53ca337729dfb9790f33a9318d20978c1966e4050719bda5"}161{"parentUuid":"205e05d1-4f12-4504-aa2c-fe5185132b6d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvDdk4c9obBPkWRe2AN","type":"message","role":"assistant","content":[{"type":"text","text":"The gate still fails, and it will keep failing however many times this cycle repeats. I re-ran it (receipt `20261030T060535.228254Z`): 64 of 65 checks pass, and the only failure is still `forecasts_chronology`.\n\n`TASK.md` defines each target as the last published month plus h, with `target_date` written as the first day of that month. For h = 1, that date always falls on or before the month-end origin date. For 6 origins the whole target month comes before the origin; for the other 4 it is the origin's own month. No date inside the target month can satisfy the gate's rule `origin_date < target_date`. The only way to pass would be to put a date that isn't the target month into that column, which would falsify `out/forecasts.csv`, so I won't do it.\n\nIt isn't leakage: no forecast uses the value it predicts, and every actual was first published after its origin date.\n\nI recorded the new receipt in `out/state/phases.json`, where P4 and P5 stay \"blocked\" for this reason only, and logged it in `out/state/log.md`. The explanation is in the \"Limitations and open issues\" section of `out/report.md`. No results or data were changed.\n\nTo clear the check, either the gate rule needs to change (for example, requiring the target's first-release date to come after the origin, which holds for all 80 rows) or the task needs to define target dates differently. Until one of those happens, another resume will give the same result."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":588,"cache_read_input_tokens":64207,"output_tokens":455,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":588},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXvDdTT6wXmYsnwYd23i","requestRef":"7038af53-48ff-4823-96bf-f8e3a2d23030","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"177282a1-e66c-4971-91c1-c3a5c5ac6d00","timestamp":"2026-10-30T06:05:41.171Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}162{"type":"last-prompt","lastPrompt":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/pha…","leafUuid":"177282a1-e66c-4971-91c1-c3a5c5ac6d00","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}163{"type":"cost-state","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","totalCostUSD":1.1637487999999998,"totalAPIDuration":295237,"totalAPIDurationWithoutRetries":295222,"totalToolDuration":11878,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":310544,"startTime":1793340027530,"modelUsage":{"claude-opus-5-5":{"inputTokens":58,"outputTokens":31190,"thinkingTokens":5911,"cacheReadInputTokens":1078709,"cacheCreationInputTokens":64795,"cacheCreationEphemeral5mInputTokens":64795,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.1637487999999998}},"hasUnknownModelCost":false}164{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T06:05:42.934Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","content":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/phases.json`, and stop when it passes. Do not change `data/`. Gate output:\n\nPGAR GATE — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80"}165{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T06:05:42.935Z","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}166{"parentUuid":"177282a1-e66c-4971-91c1-c3a5c5ac6d00","isSidechain":false,"promptId":"61b032bb-6a61-4182-877c-c272995a730c","type":"user","message":{"role":"user","content":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/phases.json`, and stop when it passes. Do not change `data/`. Gate output:\n\nPGAR GATE — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80"},"uuid":"0c0f8184-c012-40e7-a30c-fe0d5bb9a530","timestamp":"2026-10-30T06:05:42.940Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":4},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}167{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"42cc711f-01a1-47ca-8915-db35e5eb8607","timestamp":"2026-10-30T06:05:42.957Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["6c04ea332e967905c33c745fc622389d61d9c85bed742510c97f7f1aacb07760","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","440fd780c0a58aac92cd8b1da6d3a47540f825a83473a3075410b93e3d11895d","f7923369558f68f3a36c4a818f7f9fb3d81f6253405c4ff5a27708ed8cf60ee5","bc6cb6081bc9b8cc6b837be8411352097d50a5c34e3a5d8704a889354381b551","2f4eed6ac83970cc015598ea39dff0ca79cd58476b1718952fb47487b692544b","0d0ae56c2f010697b4c19bc91c1e08dc4310f036f2282037abcd7e5f97f15c35","8b86d1de7ac5ad6b44fd70efdae61390830960125fdeea60570b32406adc690c","1423c8a62d371bfee428cec26ce0f4ef27f720902187cbf3008ed0cc2031078d","2e2836cf9c952cb344371e8365e1247c6a269c55f9dd2600e20834577c3c070a","3df19427ebf76b33c9c814c4c91df231aa14f015d28bf531676c22f4ecc3675c","93cc2bda34bf4d12669f2e2ddacbec4171422df4d198834bd9ec04d8186bc7d1","71bb88cdfe7b8f37eddb1d7d112d6239725c93434438550e8b4bb44ac5faca66","9ccb314419ff31e5c94aac6b55688b996a49be22484ea0902ff8aac2e03e3bbb","4d6dd9172337f9057a1da0c52eae77349522cad1eac371529cd9b21d1c4f9579","0ae30b375721557a1bd778436e2f996337c7a4b2a32c04ee3198ae8630996008","44b052e9b2cc60d46fb40872608f2a7b0a367499d7b5f404357486a93a82e6bc","516ef0b234d49a3042fb1f7c38a012ab169686f661fd20a6f9b9701626e6f8eb","4944dc4f759c4691f901f33370344f54746729a0f6f53ae48ee29031225a0ddc","297f11eb984fcec0d6784434cf4b8d98db610bb8a76b77645cae733a798532ec","2b891af3cf4c84d1fb7e4eb1abad1bddfd8111b40c581291aebce43be04988ba","f89d9a8898f6668d4235e26158006db4a9c3b581d759e71bf573d013f5c47806","392b72740628466b53e2fe921b8ad7894ac19cac4600cff111860b3384e57985","8ebef63b43544edb2bdd1e5d5ccf1c86b913f7c429e531c46f63904dd1b6fc7a","4a6788b247c76be6da268c44511eeeac1017f73682ffa376ee8fff1cfcafee61","4812cba4ced36a4da2096afd35b330980e2e65b960c5ab27a55bf79fa045acf4","ef419b93b16e834a21cbc32cee0caf1f23c0fa15ab2ff480ba490a15f5ed9dfc","e50d5d69b3462527a7af96c8abd4e86046b9a2ddd9509c285bf80c7af6aa9f9c","e1a111fb6a43005bedf7d5b31eebbba0374259e205ee32b12e71bf08599f56a4","bd330bc245a0d56571e0bf8bd245e93aba415104a648fce61b569a8caf602728","a9503ee5c1ab02db89fe42e928f59178243fbbfda0f3b109e10bdb26475fc091","6f89a704dff69ab0762ebcfbd9697385e22c326e1de728ac525486e8c57ba019","8b755eeef7c38e3bb474d8c6ffcb2fabb478b4aac58fa8a09002bcf4e6004770","4e0168cdf82b82e081533ef82e2c5ffd461c2700753b36b53e8a36ffdeb4d9b4","20dcb37141804282223deb7612d5d95a858baa698024c0025afb3f6304616f97","efdf0a2002ad6bc07550b29ebaba15c43f55b325837ee2204b16153e2a675834","6fb1ed93f88c5cbab5a0f7b099c7a1b21889e40dfb1b2c37f63b0ee8b7687d9d","0a709ff77c854e5038b2acfb3f2a2b492be4045f701a2d7d52235446c6dc484d","a1af398dcb6e0bf6fe956c94d43eac4502f369d53239b23b2275d60314ac1ba6","254b112814aff5b083e0b4eea81e7820fa14ac8f7c9643f1a67c87f7fb5f6b6c","4a750b376cc8a64353af3371af870b9322b864c420a627f6dfe21f51b4c3288c","29ba20a2eceb330bebcdc5ae4d07202740e409af480fd779fe26afbffe5e1b10","54c51b028c49d0368fc4cde61fa94f1a2716b35a2a16e7523cec206c0c81aeb7","cb492344cf39928c41b00503cbda90c013bf42cdb83e899ac6936853144a5f03","021bee48b17d945ed6e254500baac8b898eeb3a3f968f2832f633958c24c98d7","a179a2de817dbd604d4cf5ac7628a8dbc7d3cdf3d3ebb0d1ece7274ab4755cfb","5012479d5090f310fc6cf82088256eec83077bd44ba82f9578af964a13e32a21","db374fda8664734ca19cff655ed4032e8c5df85af8d21f27d6ac52c1a01b1f2f","1a56519e52701bd38a80297718d083d13a8f0c22c80284f336d7f0f94615183e","cb492344cf39928c41b00503cbda90c013bf42cdb83e899ac6936853144a5f03","573f05b50b1571a31779d87a7a015265ea166d934bbfb489c78c96b17d7fa4f4","1a285cd553cce9922180b8a6f6675d53d78972e3305a9bc98381df554f6cec2d","5c8c7c76e8cacb87d3b0e6b86455d92bd8f53254a5344f05a5d373b383e368a1","cb492344cf39928c41b00503cbda90c013bf42cdb83e899ac6936853144a5f03"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",53,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5c286f13d3358fa71a92df4b5501c46ad96ed22fdade3737d018c880f0f77e8e"}168{"parentUuid":"0c0f8184-c012-40e7-a30c-fe0d5bb9a530","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvEDb2RAjjBQ3jqFBMM","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":606,"cache_read_input_tokens":64795,"output_tokens":435,"output_tokens_details":{"thinking_tokens":25},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":606},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":544,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXvEDJAbpUhfCY5niZXY","requestRef":"42cc711f-01a1-47ca-8915-db35e5eb8607","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e86e21a5-1340-400f-975b-142ee95cefd5","timestamp":"2026-10-30T06:05:44.899Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}169{"parentUuid":"e86e21a5-1340-400f-975b-142ee95cefd5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvEDb2RAjjBQ3jqFBMM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018M5oher2hRSCrpNo1SeoH7","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"; R=$(ls out/state/gate_receipts | tail -1); ~/wp29/venv/bin/python - \"$R\" <<'EOF'\nimport json,sys\np=json.load(open('out/state/phases.json'))\nn=f\"gate run 5 (third controller resume) receipt out/state/gate_receipts/{sys.argv[1]}: only forecasts_chronology fails; same TASK.md/gate conflict; target_date not falsified.\"\np['P4']['checks'].append(n); p['P5']['checks'].append(n)\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Third controller resume: gate re-run ($R), same single failure; no honest fix; stopping.\" >> out/state/log.md","description":"Re-run gate and record receipt"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":606,"cache_read_input_tokens":64795,"output_tokens":435,"output_tokens_details":{"thinking_tokens":25},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":606},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXvEDJAbpUhfCY5niZXY","requestRef":"42cc711f-01a1-47ca-8915-db35e5eb8607","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c8a88565-efa9-45da-89f3-20d5b27b823a","timestamp":"2026-10-30T06:05:47.297Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}170{"parentUuid":"c8a88565-efa9-45da-89f3-20d5b27b823a","isSidechain":false,"promptId":"61b032bb-6a61-4182-877c-c272995a730c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018M5oher2hRSCrpNo1SeoH7","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060548.765750Z.json","is_error":false}]},"uuid":"01843165-fe4c-43e8-ae0f-261bfc997b2f","timestamp":"2026-10-30T06:05:48.807Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0026/out/state/gate_receipts/20261030T060548.765750Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c8a88565-efa9-45da-89f3-20d5b27b823a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}171{"type":"api-request-blob","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","hash":"b1c123e9ed522f1a853701e6120ba1b452a54909fe7b87aab4c5474da81fe5d9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_018M5oher2hRSCrpNo1SeoH7","name":"Bash","input":{"command":"cd ~/wp29/runs/RT0026; ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"; R=$(ls out/state/gate_receipts | tail -1); ~/wp29/venv/bin/python - \"$R\" <<'EOF'\nimport json,sys\np=json.load(open('out/state/phases.json'))\nn=f\"gate run 5 (third controller resume) receipt out/state/gate_receipts/{sys.argv[1]}: only forecasts_chronology fails; same TASK.md/gate conflict; target_date not falsified.\"\np['P4']['checks'].append(n); p['P5']['checks'].append(n)\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Third controller resume: gate re-run ($R), same single failure; no honest fix; stopping.\" >> out/state/log.md","description":"Re-run gate and record receipt"}}]}}172{"type":"api-request","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","id":"356002f7-6a38-4af4-b2fc-c3276724fcec","timestamp":"2026-10-30T06:05:48.813Z","version":"2.1.314","querySource":"sdk","shapeHash":"091cfd9746a160705e4f15c9a35fa78d0b3ac33725ba02163ae201f8c163c769","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"42cc711f-01a1-47ca-8915-db35e5eb8607","keep":54,"tail":["b1c123e9ed522f1a853701e6120ba1b452a54909fe7b87aab4c5474da81fe5d9","27f855db63d089f7d650be732743e537ef52560688c66c82d500ef77110967b0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",55,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"73f997c820533d0a266fe4d65c6f625bdf5d48ffbc41bf045eaf80221d8da7df"}173{"parentUuid":"01843165-fe4c-43e8-ae0f-261bfc997b2f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXvEdePSfWUqeUdqSncF","type":"message","role":"assistant","content":[{"type":"text","text":"The gate still fails, and I can't fix it without falsifying the forecast file. I re-ran it (receipt `20261030T060548.765750Z`): 64 of 65 checks pass, and the only failure is still `forecasts_chronology`.\n\nThe reason hasn't changed. `TASK.md` says the 1-month-ahead target is the month after the last published month, written as the first day of that month. That date always falls on or before the origin date. So for all 40 h = 1 rows, no date inside the target month can satisfy the gate's rule `origin_date < target_date`. Passing would mean writing a date outside the target month into `target_date` in `out/forecasts.csv`, and I won't do that.\n\nEvery actual was still first published after its origin date in all 80 rows, so the forecasts don't use future information.\n\nI added the new receipt to `out/state/phases.json` (P4 and P5 remain \"blocked\" for this reason only) and logged it in `out/state/log.md`. No results or data changed.\n\nRunning this cycle again will give the same result. To clear the check, someone has to change either the gate rule (for example, check that the actual's first-release date comes after the origin) or the task's definition of `target_date`."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":568,"cache_read_input_tokens":65401,"output_tokens":386,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":568},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXvEdN1rxnXtqYbgVG8N","requestRef":"356002f7-6a38-4af4-b2fc-c3276724fcec","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"02ea7aca-0272-46e6-beca-161e4c4b51ad","timestamp":"2026-10-30T06:05:52.992Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0026","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","version":"2.1.314","gitBranch":"HEAD"}174{"type":"last-prompt","lastPrompt":"The controller ran the gate program after your session ended and it did NOT pass. The gate output is below. Fix the reported problems in your workspace, re-run the gate yourself, update `out/state/pha…","leafUuid":"02ea7aca-0272-46e6-beca-161e4c4b51ad","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}175{"type":"mode","mode":"normal","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}176{"type":"atis-latch","atis":"","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946"}177{"type":"cost-state","sessionId":"f32ec930-60c3-42ca-aacc-4d86a04a6946","totalCostUSD":1.2121019999999998,"totalAPIDuration":303776,"totalAPIDurationWithoutRetries":303759,"totalToolDuration":13377,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":320618,"startTime":1793340027530,"modelUsage":{"claude-opus-5-5":{"inputTokens":64,"outputTokens":32011,"thinkingTokens":5936,"cacheReadInputTokens":1208905,"cacheCreationInputTokens":65969,"cacheCreationEphemeral5mInputTokens":65969,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.2121019999999998}},"hasUnknownModelCost":false}178