spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:31:31.332Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:31:31.339Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}4{"parentUuid":null,"isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":"Begin"},"uuid":"f83f5017-964a-4c27-8024-1f68b149b1c1","timestamp":"2026-10-30T05:31:31.344Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","timestamp":"2026-10-30T05:31:31.358Z","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/RT0009\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"}],"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":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"66cb4b03-1c44-46e8-b1bb-78ca7ab211c9","timestamp":"2026-10-30T05:31:31.358Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ab18703366dd09abce59a2469f9bd6138cd7338c831c4613486942d4a3bc4beb"}8{"parentUuid":"f83f5017-964a-4c27-8024-1f68b149b1c1","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"4ab1cd0c-02e2-490e-a2f7-6b1bda7c4c77","timestamp":"2026-10-30T05:31:31.349Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"4ab1cd0c-02e2-490e-a2f7-6b1bda7c4c77","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"994d9c30-8349-42f6-9753-24cb78c84322","timestamp":"2026-10-30T05:31:31.349Z","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/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"994d9c30-8349-42f6-9753-24cb78c84322","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":"7981892f-3d13-4169-ba37-a8e0a5b34426","timestamp":"2026-10-30T05:31:31.350Z","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/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}12{"parentUuid":"7981892f-3d13-4169-ba37-a8e0a5b34426","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXscyaCtk91hJp8v2Sjp","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":2603,"cache_read_input_tokens":1504,"output_tokens":128,"output_tokens_details":{"thinking_tokens":22},"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":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":542,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXscyHrA53KUsJHfPNHE","requestRef":"66cb4b03-1c44-46e8-b1bb-78ca7ab211c9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9e670c3c-ee38-430e-a6ab-96927313a3da","timestamp":"2026-10-30T05:31:32.562Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"9e670c3c-ee38-430e-a6ab-96927313a3da","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXscyaCtk91hJp8v2Sjp","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TuwxH6EeDNCkAi9ZaQDEkA","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":2603,"cache_read_input_tokens":1504,"output_tokens":128,"output_tokens_details":{"thinking_tokens":22},"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":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXscyHrA53KUsJHfPNHE","requestRef":"66cb4b03-1c44-46e8-b1bb-78ca7ab211c9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aeabb3f8-e881-4546-9772-25a4754c2dd5","timestamp":"2026-10-30T05:31:33.154Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"aeabb3f8-e881-4546-9772-25a4754c2dd5","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TuwxH6EeDNCkAi9ZaQDEkA","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  173 simon-pierreboucher  staff   5536 oct.  30 01:31 ..\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":"6fe7e8f2-9ce9-451c-9a9a-4215b3c75f0c","timestamp":"2026-10-30T05:31:33.270Z","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  173 simon-pierreboucher  staff   5536 oct.  30 01:31 ..\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":"aeabb3f8-e881-4546-9772-25a4754c2dd5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}15{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"6fe7e8f2-9ce9-451c-9a9a-4215b3c75f0c","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}16{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}17{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"f238ba95539a99d3daf0e29621276816d32ea65940ea86c52f086849de9fb1bd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSpAUKEAgTGAI4AUIIdGhpbmtpbmcSDNvnKL8+x5FUDgb/2BoMnRGsdpgFr+1kFfaEIjAJT5lp4EDisSPZ+Fw77/V3xOD01Zo+XGe8gppJH+n0sVYIoiKzPJA2Zy/zSoIoHooqwQQYOD3A8IxY5dzB4r/prPF5bHKlEJZ0I9+oUuGbnwfTWnxX1NFesVXeevfKR/RuGYy9OZ+zrxGFz6MDbP4CxyAtUnxO1beqJoRXHJkm7xBBh2/UHeA26L82WdJlipmrHDR43I3SbAy76dHjqXqOOOJeLy3AstEeARBgiZTCAi48H+V24fKKd2oKBPbX++pXxy2ZXt/MuUpG8Eq2FZjkIM68VQM/qrXqJiTOo+vP5GBvt810Sp8UJOIRybUZaZJh2ULCoT2oTzZmZmUMAh+Kf45ZrQCwiSQrHCKJu6uXd9mARtb3qPjAaIof97WJs3lU40rvHrl1fcDvbytZSsO0vhlWOkv/TadMfJFsEaz3rg7sot3KBuTtTUsmILh+DIi2VsZzG8GSDqpVEi4o4wJCrVS2oox7RlQI5XlpZtTR9iOJcevCy0mSGH7NNTPv1F4yXQ0p8ztwXSTjiOtHMEPG1JI5w2IsJ4tnDzmf8o81nfVvG8jIXAbc+4gT7wHWJpyV6mu3LWw/LRXxNAk1vjTD0+SVYeMgqezUNaM2Rsks3yK2nYiDPvFN7Iz3gUPAz6z2MPp+lRsrmbuvcyph5EEvDRwEp1jwcGvHBYfMSi8XZmQ8WUfpajupImO1CEwbP281FTaRSieE6ZciYKcrxsdNLQgOhnvN7WEk/1FDJ6gDwMw3OL02866ijRD9IQUpvjUlUF9I810rkxGGYrfgdvt/H8UKsnft28KTBducGYHG4sLL/AAZecD1F5ZFLYSHWWt8ccjpGAE="},{"type":"tool_use","id":"toolu_01TuwxH6EeDNCkAi9ZaQDEkA","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}18{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"0fc49b65-9764-4544-b9e3-247d5771e32e","timestamp":"2026-10-30T05:31:33.275Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"66cb4b03-1c44-46e8-b1bb-78ca7ab211c9","keep":2,"tail":["f238ba95539a99d3daf0e29621276816d32ea65940ea86c52f086849de9fb1bd","5091368c144595d34bc36632414133968c75ec8967ff421e2ebf06e79bfef535"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b908d2fe20b0e1747199385cff10d10467b52b6ab3c9f37fd6ea992fcd7b94f8"}19{"parentUuid":"6fe7e8f2-9ce9-451c-9a9a-4215b3c75f0c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsd7KY8LieFUsjb19Ka","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01523Mobkzcpg99dD6Z2ksT2","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json; cat bundle.json | head -50; cat data/first_release.csv; for f in data/vintages/*.csv; do echo \"$f $(wc -l <$f) $(head -1 $f) | $(tail -2 $f | tr '\\n' ' ')\"; done; head -3 data/RSAFS_current.csv; tail -3 data/RSAFS_current.csv; tail -14 data/UMCSENT.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":4878,"cache_read_input_tokens":4107,"output_tokens":231,"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":4878},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsd73BKPeDqk1no2SPi","requestRef":"0fc49b65-9764-4544-b9e3-247d5771e32e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ac3b14f2-fd30-430c-8ed1-a63146f1ca76","timestamp":"2026-10-30T05:31:35.333Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"ac3b14f2-fd30-430c-8ed1-a63146f1ca76","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01523Mobkzcpg99dD6Z2ksT2","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}target_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\ndata/vintages/PAYEMS_vintage_2025-10-31.csv     1041 observation_date,PAYEMS_20251031 | 2025-07-01,159518 2025-08-01,159540 \ndata/vintages/PAYEMS_vintage_2025-11-30.csv     1042 observation_date,PAYEMS_20251130 | 2025-08-01,159507 2025-09-01,159626 \ndata/vintages/PAYEMS_vintage_2025-12-31.csv     1044 observation_date,PAYEMS_20251231 | 2025-10-01,159488 2025-11-01,159552 \ndata/vintages/PAYEMS_vintage_2026-01-31.csv     1045 observation_date,PAYEMS_20260131 | 2025-11-01,159476 2025-12-01,159526 \ndata/vintages/PAYEMS_vintage_2026-02-28.csv     1046 observation_date,PAYEMS_20260228 | 2025-12-01,158497 2026-01-01,158627 \ndata/vintages/PAYEMS_vintage_2026-03-31.csv     1047 observation_date,PAYEMS_20260331 | 2026-01-01,158558 2026-02-01,158466 \ndata/vintages/PAYEMS_vintage_2026-04-30.csv     1048 observation_date,PAYEMS_20260430 | 2026-02-01,158459 2026-03-01,158637 \ndata/vintages/PAYEMS_vintage_2026-05-31.csv     1049 observation_date,PAYEMS_20260531 | 2026-03-01,158621 2026-04-01,158736 \ndata/vintages/PAYEMS_vintage_2026-06-30.csv     1050 observation_date,PAYEMS_20260630 | 2026-04-01,158829 2026-05-01,159001 \ndata/vintages/PAYEMS_vintage_2026-07-31.csv     1051 observation_date,PAYEMS_20260731 | 2026-05-01,158927 2026-06-01,158984 \ndata/vintages/RSAFS_vintage_2025-10-31.csv      405 observation_date,RSAFS_20251031 | 2025-07-01,727414 2025-08-01,732010 \ndata/vintages/RSAFS_vintage_2025-11-30.csv      406 observation_date,RSAFS_20251130 | 2025-08-01,732059 2025-09-01,733258 \ndata/vintages/RSAFS_vintage_2025-12-31.csv      407 observation_date,RSAFS_20251231 | 2025-09-01,732444 2025-10-01,732633 \ndata/vintages/RSAFS_vintage_2026-01-31.csv      408 observation_date,RSAFS_20260131 | 2025-10-01,731412 2025-11-01,735904 \ndata/vintages/RSAFS_vintage_2026-02-28.csv      409 observation_date,RSAFS_20260228 | 2025-11-01,735085 2025-12-01,734967 \ndata/vintages/RSAFS_vintage_2026-03-31.csv      410 observation_date,RSAFS_20260331 | 2025-12-01,734685 2026-01-01,733537 \ndata/vintages/RSAFS_vintage_2026-04-30.csv      412 observation_date,RSAFS_20260430 | 2026-02-01,739772 2026-03-01,752063 \ndata/vintages/RSAFS_vintage_2026-05-31.csv      413 observation_date,RSAFS_20260531 | 2026-03-01,753370 2026-04-01,757085 \ndata/vintages/RSAFS_vintage_2026-06-30.csv      414 observation_date,RSAFS_20260630 | 2026-04-01,757036 2026-05-01,763705 \ndata/vintages/RSAFS_vintage_2026-07-31.csv      415 observation_date,RSAFS_20260731 | 2026-05-01,766876 2026-06-01,768553 \nobservation_date,RSAFS\n1992-01-01,159177\n1992-02-01,159189\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n2025-08-01,58.2\n2025-09-01,55.1\n2025-10-01,53.6\n2025-11-01,51.0\n2025-12-01,52.9\n2026-01-01,56.4\n2026-02-01,56.6\n2026-03-01,53.3\n2026-04-01,49.8\n2026-05-01,44.8\n2026-06-01,49.5\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1","is_error":false}]},"uuid":"0b9e53b8-e8df-4d2f-80e1-6f545d83fc12","timestamp":"2026-10-30T05:31:35.518Z","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}target_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\ndata/vintages/PAYEMS_vintage_2025-10-31.csv     1041 observation_date,PAYEMS_20251031 | 2025-07-01,159518 2025-08-01,159540 \ndata/vintages/PAYEMS_vintage_2025-11-30.csv     1042 observation_date,PAYEMS_20251130 | 2025-08-01,159507 2025-09-01,159626 \ndata/vintages/PAYEMS_vintage_2025-12-31.csv     1044 observation_date,PAYEMS_20251231 | 2025-10-01,159488 2025-11-01,159552 \ndata/vintages/PAYEMS_vintage_2026-01-31.csv     1045 observation_date,PAYEMS_20260131 | 2025-11-01,159476 2025-12-01,159526 \ndata/vintages/PAYEMS_vintage_2026-02-28.csv     1046 observation_date,PAYEMS_20260228 | 2025-12-01,158497 2026-01-01,158627 \ndata/vintages/PAYEMS_vintage_2026-03-31.csv     1047 observation_date,PAYEMS_20260331 | 2026-01-01,158558 2026-02-01,158466 \ndata/vintages/PAYEMS_vintage_2026-04-30.csv     1048 observation_date,PAYEMS_20260430 | 2026-02-01,158459 2026-03-01,158637 \ndata/vintages/PAYEMS_vintage_2026-05-31.csv     1049 observation_date,PAYEMS_20260531 | 2026-03-01,158621 2026-04-01,158736 \ndata/vintages/PAYEMS_vintage_2026-06-30.csv     1050 observation_date,PAYEMS_20260630 | 2026-04-01,158829 2026-05-01,159001 \ndata/vintages/PAYEMS_vintage_2026-07-31.csv     1051 observation_date,PAYEMS_20260731 | 2026-05-01,158927 2026-06-01,158984 \ndata/vintages/RSAFS_vintage_2025-10-31.csv      405 observation_date,RSAFS_20251031 | 2025-07-01,727414 2025-08-01,732010 \ndata/vintages/RSAFS_vintage_2025-11-30.csv      406 observation_date,RSAFS_20251130 | 2025-08-01,732059 2025-09-01,733258 \ndata/vintages/RSAFS_vintage_2025-12-31.csv      407 observation_date,RSAFS_20251231 | 2025-09-01,732444 2025-10-01,732633 \ndata/vintages/RSAFS_vintage_2026-01-31.csv      408 observation_date,RSAFS_20260131 | 2025-10-01,731412 2025-11-01,735904 \ndata/vintages/RSAFS_vintage_2026-02-28.csv      409 observation_date,RSAFS_20260228 | 2025-11-01,735085 2025-12-01,734967 \ndata/vintages/RSAFS_vintage_2026-03-31.csv      410 observation_date,RSAFS_20260331 | 2025-12-01,734685 2026-01-01,733537 \ndata/vintages/RSAFS_vintage_2026-04-30.csv      412 observation_date,RSAFS_20260430 | 2026-02-01,739772 2026-03-01,752063 \ndata/vintages/RSAFS_vintage_2026-05-31.csv      413 observation_date,RSAFS_20260531 | 2026-03-01,753370 2026-04-01,757085 \ndata/vintages/RSAFS_vintage_2026-06-30.csv      414 observation_date,RSAFS_20260630 | 2026-04-01,757036 2026-05-01,763705 \ndata/vintages/RSAFS_vintage_2026-07-31.csv      415 observation_date,RSAFS_20260731 | 2026-05-01,766876 2026-06-01,768553 \nobservation_date,RSAFS\n1992-01-01,159177\n1992-02-01,159189\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n2025-08-01,58.2\n2025-09-01,55.1\n2025-10-01,53.6\n2025-11-01,51.0\n2025-12-01,52.9\n2026-01-01,56.4\n2026-02-01,56.6\n2026-03-01,53.3\n2026-04-01,49.8\n2026-05-01,44.8\n2026-06-01,49.5\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ac3b14f2-fd30-430c-8ed1-a63146f1ca76","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"8438fef5f84a18989cbb29a4c0351c587c98e428116f1cb53db60c9d7bf63bd7","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01523Mobkzcpg99dD6Z2ksT2","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json; cat bundle.json | head -50; cat data/first_release.csv; for f in data/vintages/*.csv; do echo \"$f $(wc -l <$f) $(head -1 $f) | $(tail -2 $f | tr '\\n' ' ')\"; done; head -3 data/RSAFS_current.csv; tail -3 data/RSAFS_current.csv; tail -14 data/UMCSENT.csv","description":"Inspect data files and specs"}}]}}22{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"dd905f00-1613-4e99-bd0c-5d309fcff6e5","timestamp":"2026-10-30T05:31:35.522Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"0fc49b65-9764-4544-b9e3-247d5771e32e","keep":4,"tail":["8438fef5f84a18989cbb29a4c0351c587c98e428116f1cb53db60c9d7bf63bd7","68f6a1ccfdc2ff86124a0f0cbaae87b0b300068d8994026f8ffa58c900e2045a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c9f863db1a6ff9a3c19ebeb0f4b86862b9cae83d79251829a7ea356d9a6a3c8d"}23{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"0b9e53b8-e8df-4d2f-80e1-6f545d83fc12","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}24{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}25{"parentUuid":"0b9e53b8-e8df-4d2f-80e1-6f545d83fc12","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsdGwEQzAY31CchH5D8","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":10685,"cache_read_input_tokens":8985,"output_tokens":1463,"output_tokens_details":{"thinking_tokens":1326},"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":10685},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":13166,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsdGdNnA4SgwcoWKQ2B","requestRef":"dd905f00-1613-4e99-bd0c-5d309fcff6e5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e3bcba3a-5c22-4460-8127-05d9210d5632","timestamp":"2026-10-30T05:31:49.733Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"e3bcba3a-5c22-4460-8127-05d9210d5632","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsdGwEQzAY31CchH5D8","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01B7YHaKPmiyvuh5di6eofUY","name":"Bash","input":{"command":"grep -n -i -A15 \"def.*exclusion\\|def.*phase_ledger\\|def.*claims\" ~/wp29/gates/pgar_gate.py | head -120","description":"Inspect gate ledger checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":10685,"cache_read_input_tokens":8985,"output_tokens":1463,"output_tokens_details":{"thinking_tokens":1326},"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":10685},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsdGdNnA4SgwcoWKQ2B","requestRef":"dd905f00-1613-4e99-bd0c-5d309fcff6e5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"34283a52-16f8-4dff-8778-18409762056d","timestamp":"2026-10-30T05:31:50.576Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}27{"parentUuid":"34283a52-16f8-4dff-8778-18409762056d","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01B7YHaKPmiyvuh5di6eofUY","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"253d7b19-dd01-4120-bdb2-b9ef5a80784a","timestamp":"2026-10-30T05:31:50.618Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"34283a52-16f8-4dff-8778-18409762056d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}28{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"f4e6ea532300daaa548e9cd54a20c45b9bd077a902cb307487eb9cced8455bd2","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01B7YHaKPmiyvuh5di6eofUY","name":"Bash","input":{"command":"grep -n -i -A15 \"def.*exclusion\\|def.*phase_ledger\\|def.*claims\" ~/wp29/gates/pgar_gate.py | head -120","description":"Inspect gate ledger checks"}}]}}29{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"f2068bba-4fca-41d3-a543-b424bb842b85","timestamp":"2026-10-30T05:31:50.622Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"dd905f00-1613-4e99-bd0c-5d309fcff6e5","keep":6,"tail":["f4e6ea532300daaa548e9cd54a20c45b9bd077a902cb307487eb9cced8455bd2","01c213379bdc93c1932320871e39662b9a500d29e92bc1a0d67b63231433f9db"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f7a8d4babed2c5cab97eff830bf75194ca5bec631fc7655b1f09070f910a370e"}30{"parentUuid":"253d7b19-dd01-4120-bdb2-b9ef5a80784a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsePTv9QxsgtLtebsxG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HYMwhBd1fKRPA16hNA2EM8","name":"Bash","input":{"command":"wc -l ~/wp29/gates/pgar_gate.py; grep -n -i \"exclusion\\|phases\\|receipt\" ~/wp29/gates/pgar_gate.py | head -40","description":"Search gate for ledger checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1478,"cache_read_input_tokens":19670,"output_tokens":142,"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":1478},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsePCJWVUhm5uKXS61B","requestRef":"f2068bba-4fca-41d3-a543-b424bb842b85","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8ff8cc0b-91ea-4eb6-81ef-27e3d99661bb","timestamp":"2026-10-30T05:31:52.205Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}31{"parentUuid":"8ff8cc0b-91ea-4eb6-81ef-27e3d99661bb","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HYMwhBd1fKRPA16hNA2EM8","type":"tool_result","content":"     249 /Users/simon-pierreboucher/wp29/gates/pgar_gate.py\n7:Writes a receipt to <workspace_dir>/out/state/gate_receipts/<utc>.json and exits 0 if passed, 1 otherwise.\n123:    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n127:            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n137:                bad.append(f\"phases not terminal: {not_done}\")\n139:    # 6. exclusion ledger\n140:    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n141:    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n153:            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n155:            add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n215:    receipt = {\"gate_version\": GATE_VERSION, \"workspace\": ws, \"utc\": datetime.datetime.now(datetime.timezone.utc).isoformat(),\n218:        d = os.path.join(ws, \"out\", \"state\", \"gate_receipts\"); os.makedirs(d, exist_ok=True)\n221:            json.dump(receipt, fh, indent=1)\n222:        receipt[\"receipt_path\"] = path\n223:        receipt[\"receipt_sha256\"] = hashlib.sha256(open(path, \"rb\").read()).hexdigest()\n225:        receipt[\"receipt_path\"] = None; receipt[\"receipt_error\"] = str(e)\n226:    return receipt\n245:        print(f\"receipt: {r.get('receipt_path')}\")","is_error":false}]},"uuid":"97b34b5b-06a2-4492-a04b-6af65331dd2f","timestamp":"2026-10-30T05:31:52.250Z","toolUseResult":{"stdout":"     249 /Users/simon-pierreboucher/wp29/gates/pgar_gate.py\n7:Writes a receipt to <workspace_dir>/out/state/gate_receipts/<utc>.json and exits 0 if passed, 1 otherwise.\n123:    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n127:            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n137:                bad.append(f\"phases not terminal: {not_done}\")\n139:    # 6. exclusion ledger\n140:    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n141:    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n153:            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n155:            add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n215:    receipt = {\"gate_version\": GATE_VERSION, \"workspace\": ws, \"utc\": datetime.datetime.now(datetime.timezone.utc).isoformat(),\n218:        d = os.path.join(ws, \"out\", \"state\", \"gate_receipts\"); os.makedirs(d, exist_ok=True)\n221:            json.dump(receipt, fh, indent=1)\n222:        receipt[\"receipt_path\"] = path\n223:        receipt[\"receipt_sha256\"] = hashlib.sha256(open(path, \"rb\").read()).hexdigest()\n225:        receipt[\"receipt_path\"] = None; receipt[\"receipt_error\"] = str(e)\n226:    return receipt\n245:        print(f\"receipt: {r.get('receipt_path')}\")","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8ff8cc0b-91ea-4eb6-81ef-27e3d99661bb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}32{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"36a9c257e015c440bb90392946dcc1e6b69a27df202196edc20a39c1ddb4d47a","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01HYMwhBd1fKRPA16hNA2EM8","name":"Bash","input":{"command":"wc -l ~/wp29/gates/pgar_gate.py; grep -n -i \"exclusion\\|phases\\|receipt\" ~/wp29/gates/pgar_gate.py | head -40","description":"Search gate for ledger checks"}}]}}33{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"fd865dbd-248b-4570-adf0-60d034826f26","timestamp":"2026-10-30T05:31:52.254Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"f2068bba-4fca-41d3-a543-b424bb842b85","keep":8,"tail":["36a9c257e015c440bb90392946dcc1e6b69a27df202196edc20a39c1ddb4d47a","aea356b8590f5a6069f7be2f38458783a7d2f9a529b03c3a1a516e295dd19657"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5c29a745e278ff35a0f19f4b8f9b9dc6906bfeaa043a5b10cddda0fdb1456577"}34{"parentUuid":"97b34b5b-06a2-4492-a04b-6af65331dd2f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXseWRddzau6KEZr2ckG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HUP8LXWbXcEwerCeqQaRCY","name":"Bash","input":{"command":"sed -n 115,160p ~/wp29/gates/pgar_gate.py","description":"Read phase and exclusion checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":734,"cache_read_input_tokens":21148,"output_tokens":104,"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":734},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXseWA1EfNB6UEyXpes8","requestRef":"fd865dbd-248b-4570-adf0-60d034826f26","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"11210577-8f49-4ce0-b0fa-94cabc11c6e1","timestamp":"2026-10-30T05:31:53.480Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}35{"parentUuid":"11210577-8f49-4ce0-b0fa-94cabc11c6e1","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HUP8LXWbXcEwerCeqQaRCY","type":"tool_result","content":"                    bad.append(f\"#{i}: missing fields\"); continue\n                if c[\"status\"] not in (\"supported\", \"unsupported\", \"not_evaluated\"):\n                    bad.append(f\"{c.get('id')}: bad status {c['status']!r}\")\n                missing = [k for k in (c.get(\"results_keys\") or []) if k not in res]\n                if missing:\n                    bad.append(f\"{c.get('id')}: results_keys not in results.json: {missing}\")\n            add(\"claims_json\", not bad, \"; \".join(bad) if bad else f\"{len(claims)} claims, all keys resolve\")\n    # 5. phase ledger\n    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n    if \"phase_ledger_consistent\" in fam and os.path.exists(pl_path):\n        pl, perr = _load_json(pl_path)\n        if not isinstance(pl, dict):\n            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n        else:\n            bad = []\n            for pid, st in pl.items():\n                if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n                    bad.append(f\"{pid}: invalid status\"); continue\n                if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n                    bad.append(f\"{pid}: passed without recorded checks\")\n            not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n            if not_done:\n                bad.append(f\"phases not terminal: {not_done}\")\n            add(\"phase_ledger\", not bad, \"; \".join(bad) if bad else \"consistent\")\n    # 6. exclusion ledger\n    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n        try:\n            rows = list(csv.DictReader(open(ex_path, newline=\"\")))\n            bad = []\n            prev_after = None\n            for i, r in enumerate(rows):\n                nb, na, nr = int(float(r[\"n_before\"])), int(float(r[\"n_after\"])), int(float(r[\"n_removed\"]))\n                if nb - nr != na:\n                    bad.append(f\"row {i}: n_before - n_removed != n_after\")\n                if prev_after is not None and nb != prev_after:\n                    bad.append(f\"row {i}: n_before != previous n_after\")\n                prev_after = na\n            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n        except Exception as e:  # noqa: BLE001\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)):","is_error":false}]},"uuid":"5e472756-4b1f-4acf-9e1e-8a4b1c237709","timestamp":"2026-10-30T05:31:53.520Z","toolUseResult":{"stdout":"                    bad.append(f\"#{i}: missing fields\"); continue\n                if c[\"status\"] not in (\"supported\", \"unsupported\", \"not_evaluated\"):\n                    bad.append(f\"{c.get('id')}: bad status {c['status']!r}\")\n                missing = [k for k in (c.get(\"results_keys\") or []) if k not in res]\n                if missing:\n                    bad.append(f\"{c.get('id')}: results_keys not in results.json: {missing}\")\n            add(\"claims_json\", not bad, \"; \".join(bad) if bad else f\"{len(claims)} claims, all keys resolve\")\n    # 5. phase ledger\n    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n    if \"phase_ledger_consistent\" in fam and os.path.exists(pl_path):\n        pl, perr = _load_json(pl_path)\n        if not isinstance(pl, dict):\n            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n        else:\n            bad = []\n            for pid, st in pl.items():\n                if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n                    bad.append(f\"{pid}: invalid status\"); continue\n                if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n                    bad.append(f\"{pid}: passed without recorded checks\")\n            not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n            if not_done:\n                bad.append(f\"phases not terminal: {not_done}\")\n            add(\"phase_ledger\", not bad, \"; \".join(bad) if bad else \"consistent\")\n    # 6. exclusion ledger\n    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n        try:\n            rows = list(csv.DictReader(open(ex_path, newline=\"\")))\n            bad = []\n            prev_after = None\n            for i, r in enumerate(rows):\n                nb, na, nr = int(float(r[\"n_before\"])), int(float(r[\"n_after\"])), int(float(r[\"n_removed\"]))\n                if nb - nr != na:\n                    bad.append(f\"row {i}: n_before - n_removed != n_after\")\n                if prev_after is not None and nb != prev_after:\n                    bad.append(f\"row {i}: n_before != previous n_after\")\n                prev_after = na\n            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n        except Exception as e:  # noqa: BLE001\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)):","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"11210577-8f49-4ce0-b0fa-94cabc11c6e1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}36{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"7c72da023afce629b656536d5387503899a0eadce866e4545dc07b079e6a47dc","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01HUP8LXWbXcEwerCeqQaRCY","name":"Bash","input":{"command":"sed -n 115,160p ~/wp29/gates/pgar_gate.py","description":"Read phase and exclusion checks"}}]}}37{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"b872c209-e752-4423-a04a-08e8d251c23c","timestamp":"2026-10-30T05:31:53.524Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"fd865dbd-248b-4570-adf0-60d034826f26","keep":10,"tail":["7c72da023afce629b656536d5387503899a0eadce866e4545dc07b079e6a47dc","92f239d200a5ea5911719c2dbd9d54b47fe6af2c6caf2c21511ca749ff805780"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c1cf19b9ea736d1386ef6df989aa557849d02ca38bc5418fc51a37a422a39079"}38{"parentUuid":"5e472756-4b1f-4acf-9e1e-8a4b1c237709","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsebrYfmzFqb7HLgGgj","type":"message","role":"assistant","content":[{"type":"text","text":"P0: contract and ledger."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1181,"cache_read_input_tokens":21882,"output_tokens":1093,"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":1181},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsebbvFtw4y5h82CUw3","requestRef":"b872c209-e752-4423-a04a-08e8d251c23c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a2157e29-ee19-452b-8769-a1f2e5e93b1e","timestamp":"2026-10-30T05:31:54.359Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}39{"parentUuid":"a2157e29-ee19-452b-8769-a1f2e5e93b1e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsebrYfmzFqb7HLgGgj","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Uahm2ws2jhgYTnjTKQcM1m","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — T1-forecast\n\n**Question.** In real time (only data published at each of 10 month-end origins 2025-10-31 … 2026-07-31), how accurately could US retail & food services sales (RSAFS) YoY growth g_m = 100·ln(L_m/L_{m-12}) be forecast h=1 and h=3 months beyond the last published month last(V), and does my own model beat the naive (no-change) forecast, judged against first-release actuals?\n\n**Estimands.** (a) RMSE and MAE (percentage points) of naive, seasonal naive, AR(1) and my model, h∈{1,3}, n=10 origins each; (b) 1 − RMSE_model/RMSE_naive; (c) DM statistic model vs naive, squared loss, d_t = e²_naive − e²_model, Bartlett LRV with truncation lag h−1, no HLN correction, two-sided normal p-value; (d) mean |g_current_T − yoy_first_release_T| over the 10 h=1 targets.\nAssumptions: first-release YoY is the \"truth\"; with n=10 the DM asymptotic normal approximation is at best rough; errors at h=3 overlap.\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (all keys in TASK.md table), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md (6 sections), out/analysis.py, out/claims.json, plus protocol files (state/, exclusions.csv).\n\n**Information rules.** Origin V uses only RSAFS_vintage_V, PAYEMS_vintage_V, UMCSENT months ≤ month(V). Target = last(V)+h where last(V) is the last month in that RSAFS vintage (not calendar). Actual = yoy_first_release. RSAFS_current only for (d). No model selection using evaluation outcomes from future origins.\n\n**Invalidity/impossibility.** Missing vintage files, target months absent from first_release.csv, use of current-vintage RSAFS or future UMCSENT in forecasts, vintage_used > origin_date or target ≤ origin.\nEOF\ncat > 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).\" > 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":1181,"cache_read_input_tokens":21882,"output_tokens":1093,"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":1181},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsebbvFtw4y5h82CUw3","requestRef":"b872c209-e752-4423-a04a-08e8d251c23c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"132011d3-bf7e-4407-abb5-651e4d1fb1cb","timestamp":"2026-10-30T05:32:02.963Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}40{"parentUuid":"132011d3-bf7e-4407-abb5-651e4d1fb1cb","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Uahm2ws2jhgYTnjTKQcM1m","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"b5ddb446-3d6e-42b4-8c34-b524ba68652a","timestamp":"2026-10-30T05:32:03.016Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"132011d3-bf7e-4407-abb5-651e4d1fb1cb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009/out/state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}41{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"1e1ef5a29991faab8d6a521d20f7c999155d986a9c2cd15476ee12e33bbc201d","message":{"role":"assistant","content":[{"type":"text","text":"P0: contract and ledger."},{"type":"tool_use","id":"toolu_01Uahm2ws2jhgYTnjTKQcM1m","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — T1-forecast\n\n**Question.** In real time (only data published at each of 10 month-end origins 2025-10-31 … 2026-07-31), how accurately could US retail & food services sales (RSAFS) YoY growth g_m = 100·ln(L_m/L_{m-12}) be forecast h=1 and h=3 months beyond the last published month last(V), and does my own model beat the naive (no-change) forecast, judged against first-release actuals?\n\n**Estimands.** (a) RMSE and MAE (percentage points) of naive, seasonal naive, AR(1) and my model, h∈{1,3}, n=10 origins each; (b) 1 − RMSE_model/RMSE_naive; (c) DM statistic model vs naive, squared loss, d_t = e²_naive − e²_model, Bartlett LRV with truncation lag h−1, no HLN correction, two-sided normal p-value; (d) mean |g_current_T − yoy_first_release_T| over the 10 h=1 targets.\nAssumptions: first-release YoY is the \"truth\"; with n=10 the DM asymptotic normal approximation is at best rough; errors at h=3 overlap.\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (all keys in TASK.md table), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md (6 sections), out/analysis.py, out/claims.json, plus protocol files (state/, exclusions.csv).\n\n**Information rules.** Origin V uses only RSAFS_vintage_V, PAYEMS_vintage_V, UMCSENT months ≤ month(V). Target = last(V)+h where last(V) is the last month in that RSAFS vintage (not calendar). Actual = yoy_first_release. RSAFS_current only for (d). No model selection using evaluation outcomes from future origins.\n\n**Invalidity/impossibility.** Missing vintage files, target months absent from first_release.csv, use of current-vintage RSAFS or future UMCSENT in forecasts, vintage_used > origin_date or target ≤ origin.\nEOF\ncat > 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).\" > log.md","description":"Write contract, phase ledger, log"}}]}}42{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"cb52ef32-37f5-4bdd-852b-cd01ed02b1f5","timestamp":"2026-10-30T05:32:03.020Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"b872c209-e752-4423-a04a-08e8d251c23c","keep":12,"tail":["1e1ef5a29991faab8d6a521d20f7c999155d986a9c2cd15476ee12e33bbc201d","47b5e144e20c734de67d86193414fd86eacc43db2e4c3cfa6a872e4524aa304e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e711c719e974c9de665542ce33f5d0b57a7230076d505f09080e3036deea85fe"}43{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b5ddb446-3d6e-42b4-8c34-b524ba68652a","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}44{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}45{"parentUuid":"b5ddb446-3d6e-42b4-8c34-b524ba68652a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsfJS5jSTcAxHWcsEaS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018wJq5wCzpxxGCS13M3WU5a","name":"Bash","input":{"command":"cat > /tmp/audit.py <<'EOF'\nimport pandas as pd, hashlib, glob, os\nfiles = sorted(glob.glob('data/*.csv')+glob.glob('data/vintages/*.csv'))\nfor f in files:\n    h=hashlib.sha256(open(f,'rb').read()).hexdigest()\n    d=pd.read_csv(f)\n    c=d.columns[1] if d.shape[1]>1 else None\n    dates=pd.to_datetime(d.iloc[:,0])\n    gaps=(dates.dt.to_period('M').diff().dropna().apply(lambda x:x.n)!=1).sum() if 'first' not in f else 'n/a'\n    print(f\"| {f} | {h[:16]}… | {len(d)} | {d.shape[1]} | {dates.min().date()} | {dates.max().date()} | {int(d.isna().sum().sum())} | {int(d.duplicated(d.columns[0]).sum())} | {gaps} |\")\nu=pd.read_csv('data/UMCSENT.csv'); print(u[u.UMCSENT.isna()].observation_date.max(), u.UMCSENT.isna().sum())\nEOF\n~/wp29/venv/bin/python /tmp/audit.py","description":"Audit all data files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1108,"cache_read_input_tokens":23063,"output_tokens":500,"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":1108},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsfJAxfiWrCyTtwwM1i","requestRef":"cb52ef32-37f5-4bdd-852b-cd01ed02b1f5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4912c685-5b03-41a3-8bba-7251c3d409dd","timestamp":"2026-10-30T05:32:07.518Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009/out/state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"4912c685-5b03-41a3-8bba-7251c3d409dd","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nTraceback (most recent call last):\n  File \"/tmp/audit.py\", line 10, in <module>\n    u=pd.read_csv('data/UMCSENT.csv'); print(u[u.UMCSENT.isna()].observation_date.max(), u.UMCSENT.isna().sum())\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n    return _read(filepath_or_buffer, kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n    parser = TextFileReader(filepath_or_buffer, **kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n    self._engine = self._make_engine(f, self.engine)\n                   ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n    self.handles = get_handle(\n                   ~~~~~~~~~~^\n        f,\n        ^^\n    ...<6 lines>...\n        storage_options=self.options.get(\"storage_options\", None),\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n    handle = open(\n        handle,\n    ...<3 lines>...\n        newline=\"\",\n    )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/UMCSENT.csv'","is_error":true,"tool_use_id":"toolu_018wJq5wCzpxxGCS13M3WU5a"}]},"uuid":"70118cd7-2b7b-4379-a423-98090e6225b3","timestamp":"2026-10-30T05:32:07.800Z","toolUseResult":"Error: Exit code 1\nTraceback (most recent call last):\n  File \"/tmp/audit.py\", line 10, in <module>\n    u=pd.read_csv('data/UMCSENT.csv'); print(u[u.UMCSENT.isna()].observation_date.max(), u.UMCSENT.isna().sum())\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n    return _read(filepath_or_buffer, kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n    parser = TextFileReader(filepath_or_buffer, **kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n    self._engine = self._make_engine(f, self.engine)\n                   ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n    self.handles = get_handle(\n                   ~~~~~~~~~~^\n        f,\n        ^^\n    ...<6 lines>...\n        storage_options=self.options.get(\"storage_options\", None),\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n    handle = open(\n        handle,\n    ...<3 lines>...\n        newline=\"\",\n    )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/UMCSENT.csv'","sandboxed":false,"sourceToolAssistantUUID":"4912c685-5b03-41a3-8bba-7251c3d409dd","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009/out/state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}47{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"e4380dae6e5f08e15aab0a154a427e6ef4f84cc46c2357861daf6ac40354ca91","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_018wJq5wCzpxxGCS13M3WU5a","name":"Bash","input":{"command":"cat > /tmp/audit.py <<'EOF'\nimport pandas as pd, hashlib, glob, os\nfiles = sorted(glob.glob('data/*.csv')+glob.glob('data/vintages/*.csv'))\nfor f in files:\n    h=hashlib.sha256(open(f,'rb').read()).hexdigest()\n    d=pd.read_csv(f)\n    c=d.columns[1] if d.shape[1]>1 else None\n    dates=pd.to_datetime(d.iloc[:,0])\n    gaps=(dates.dt.to_period('M').diff().dropna().apply(lambda x:x.n)!=1).sum() if 'first' not in f else 'n/a'\n    print(f\"| {f} | {h[:16]}… | {len(d)} | {d.shape[1]} | {dates.min().date()} | {dates.max().date()} | {int(d.isna().sum().sum())} | {int(d.duplicated(d.columns[0]).sum())} | {gaps} |\")\nu=pd.read_csv('data/UMCSENT.csv'); print(u[u.UMCSENT.isna()].observation_date.max(), u.UMCSENT.isna().sum())\nEOF\n~/wp29/venv/bin/python /tmp/audit.py","description":"Audit all data files"}}]}}48{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"f884e0fd-9593-4307-8f81-64536234178c","timestamp":"2026-10-30T05:32:07.803Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"cb52ef32-37f5-4bdd-852b-cd01ed02b1f5","keep":14,"tail":["e4380dae6e5f08e15aab0a154a427e6ef4f84cc46c2357861daf6ac40354ca91","14da83b08e106624de757637c9473b33a914972516fb20ba41b1389333b58ae0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"db7625a90ba910767ed0ce6659c4a80cf6ebcf6c5081007d289f9f564f86a44a"}49{"parentUuid":"70118cd7-2b7b-4379-a423-98090e6225b3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsfexNDRo1ssqjtQjtn","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":1232,"cache_read_input_tokens":24171,"output_tokens":186,"output_tokens_details":{"thinking_tokens":56},"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":1232},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":515,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsfeeWKjTVe3VPwweHT","requestRef":"f884e0fd-9593-4307-8f81-64536234178c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0e174b93-a1ad-4df3-a311-a9c57a54c858","timestamp":"2026-10-30T05:32:10.754Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009/out/state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}50{"parentUuid":"0e174b93-a1ad-4df3-a311-a9c57a54c858","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsfexNDRo1ssqjtQjtn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ACqo4hZX89BhKNVX6sMrEq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0009 && ~/wp29/venv/bin/python /tmp/audit.py","description":"Rerun audit from workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1232,"cache_read_input_tokens":24171,"output_tokens":186,"output_tokens_details":{"thinking_tokens":56},"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":1232},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsfeeWKjTVe3VPwweHT","requestRef":"f884e0fd-9593-4307-8f81-64536234178c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6320050a-644e-4017-89e7-1a3827cf970f","timestamp":"2026-10-30T05:32:11.131Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009/out/state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}51{"parentUuid":"6320050a-644e-4017-89e7-1a3827cf970f","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ACqo4hZX89BhKNVX6sMrEq","type":"tool_result","content":"| data/RSAFS_current.csv | 627d8bb386ac80f4… | 417 | 2 | 1992-01-01 | 2026-09-01 | 0 | 0 | 0 |\n| data/UMCSENT.csv | 3076277f9f21f4bd… | 887 | 2 | 1952-11-01 | 2026-09-01 | 210 | 0 | 0 |\n| data/first_release.csv | 1d1ae8b3cacf7799… | 28 | 5 | 2024-06-01 | 2026-09-01 | 0 | 0 | n/a |\n| data/vintages/PAYEMS_vintage_2025-10-31.csv | d4b4c909ed321fbf… | 1040 | 2 | 1939-01-01 | 2025-08-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2025-11-30.csv | a05ef7fc50cfc339… | 1041 | 2 | 1939-01-01 | 2025-09-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2025-12-31.csv | 829dae087af61916… | 1043 | 2 | 1939-01-01 | 2025-11-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-01-31.csv | 8fd01c5d2740e869… | 1044 | 2 | 1939-01-01 | 2025-12-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-02-28.csv | 4a913e67ac5ffbb4… | 1045 | 2 | 1939-01-01 | 2026-01-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-03-31.csv | 919de86b07be9046… | 1046 | 2 | 1939-01-01 | 2026-02-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-04-30.csv | 06a8d663d9aaa61c… | 1047 | 2 | 1939-01-01 | 2026-03-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-05-31.csv | e2a152e874139acd… | 1048 | 2 | 1939-01-01 | 2026-04-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-06-30.csv | 19fbc6cd3547ffad… | 1049 | 2 | 1939-01-01 | 2026-05-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-07-31.csv | 3a3a6603fcc31c6e… | 1050 | 2 | 1939-01-01 | 2026-06-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2025-10-31.csv | 3ecb0832a391e726… | 404 | 2 | 1992-01-01 | 2025-08-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2025-11-30.csv | 4a683d85374690f1… | 405 | 2 | 1992-01-01 | 2025-09-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2025-12-31.csv | 436df4b5509b1dfe… | 406 | 2 | 1992-01-01 | 2025-10-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-01-31.csv | b92ab6a5c1dbdc56… | 407 | 2 | 1992-01-01 | 2025-11-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-02-28.csv | 2af0a3aaeeba81ef… | 408 | 2 | 1992-01-01 | 2025-12-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-03-31.csv | 0316fdf238d55d9f… | 409 | 2 | 1992-01-01 | 2026-01-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-04-30.csv | 02dcc697a1db3475… | 411 | 2 | 1992-01-01 | 2026-03-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-05-31.csv | 8c3fe35302135896… | 412 | 2 | 1992-01-01 | 2026-04-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-06-30.csv | 2f103157f4a9b7a3… | 413 | 2 | 1992-01-01 | 2026-05-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-07-31.csv | 52c04a8fce2effa7… | 414 | 2 | 1992-01-01 | 2026-06-01 | 0 | 0 | 0 |\n1977-12-01 210","is_error":false}]},"uuid":"1c6c1c43-ba06-40b6-b31f-27e6576ab4a5","timestamp":"2026-10-30T05:32:11.436Z","toolUseResult":{"stdout":"| data/RSAFS_current.csv | 627d8bb386ac80f4… | 417 | 2 | 1992-01-01 | 2026-09-01 | 0 | 0 | 0 |\n| data/UMCSENT.csv | 3076277f9f21f4bd… | 887 | 2 | 1952-11-01 | 2026-09-01 | 210 | 0 | 0 |\n| data/first_release.csv | 1d1ae8b3cacf7799… | 28 | 5 | 2024-06-01 | 2026-09-01 | 0 | 0 | n/a |\n| data/vintages/PAYEMS_vintage_2025-10-31.csv | d4b4c909ed321fbf… | 1040 | 2 | 1939-01-01 | 2025-08-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2025-11-30.csv | a05ef7fc50cfc339… | 1041 | 2 | 1939-01-01 | 2025-09-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2025-12-31.csv | 829dae087af61916… | 1043 | 2 | 1939-01-01 | 2025-11-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-01-31.csv | 8fd01c5d2740e869… | 1044 | 2 | 1939-01-01 | 2025-12-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-02-28.csv | 4a913e67ac5ffbb4… | 1045 | 2 | 1939-01-01 | 2026-01-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-03-31.csv | 919de86b07be9046… | 1046 | 2 | 1939-01-01 | 2026-02-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-04-30.csv | 06a8d663d9aaa61c… | 1047 | 2 | 1939-01-01 | 2026-03-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-05-31.csv | e2a152e874139acd… | 1048 | 2 | 1939-01-01 | 2026-04-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-06-30.csv | 19fbc6cd3547ffad… | 1049 | 2 | 1939-01-01 | 2026-05-01 | 0 | 0 | 0 |\n| data/vintages/PAYEMS_vintage_2026-07-31.csv | 3a3a6603fcc31c6e… | 1050 | 2 | 1939-01-01 | 2026-06-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2025-10-31.csv | 3ecb0832a391e726… | 404 | 2 | 1992-01-01 | 2025-08-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2025-11-30.csv | 4a683d85374690f1… | 405 | 2 | 1992-01-01 | 2025-09-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2025-12-31.csv | 436df4b5509b1dfe… | 406 | 2 | 1992-01-01 | 2025-10-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-01-31.csv | b92ab6a5c1dbdc56… | 407 | 2 | 1992-01-01 | 2025-11-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-02-28.csv | 2af0a3aaeeba81ef… | 408 | 2 | 1992-01-01 | 2025-12-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-03-31.csv | 0316fdf238d55d9f… | 409 | 2 | 1992-01-01 | 2026-01-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-04-30.csv | 02dcc697a1db3475… | 411 | 2 | 1992-01-01 | 2026-03-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-05-31.csv | 8c3fe35302135896… | 412 | 2 | 1992-01-01 | 2026-04-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-06-30.csv | 2f103157f4a9b7a3… | 413 | 2 | 1992-01-01 | 2026-05-01 | 0 | 0 | 0 |\n| data/vintages/RSAFS_vintage_2026-07-31.csv | 52c04a8fce2effa7… | 414 | 2 | 1992-01-01 | 2026-06-01 | 0 | 0 | 0 |\n1977-12-01 210","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6320050a-644e-4017-89e7-1a3827cf970f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}52{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"948ce94b8e2a0fa9a1528901c4a0b29257a06e7960df93b8e6f53a23207c53a9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01ACqo4hZX89BhKNVX6sMrEq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0009 && ~/wp29/venv/bin/python /tmp/audit.py","description":"Rerun audit from workspace root"}}]}}53{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"636d60e8-7aac-41c5-99fd-63f05ca61261","timestamp":"2026-10-30T05:32:11.440Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"f884e0fd-9593-4307-8f81-64536234178c","keep":16,"tail":["948ce94b8e2a0fa9a1528901c4a0b29257a06e7960df93b8e6f53a23207c53a9","8c84a42f432fcd4eff1c0f43f1bcb00702eb4970398e74531bb6463f6fad62e0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4f11b1d5297e26f5cc17ffac8afff8d5bb93c9d9ac225fdc3d793942bacbfd44"}54{"parentUuid":"1c6c1c43-ba06-40b6-b31f-27e6576ab4a5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsfvVFsqkCfpTwwddsT","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":2012,"cache_read_input_tokens":25403,"output_tokens":1111,"output_tokens_details":{"thinking_tokens":684},"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":2012},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6076,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsfvCt5t4PMasGLgvct","requestRef":"636d60e8-7aac-41c5-99fd-63f05ca61261","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"01162fe5-0458-4d9d-8a8b-e467cb8a0acf","timestamp":"2026-10-30T05:32:18.973Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}55{"parentUuid":"01162fe5-0458-4d9d-8a8b-e467cb8a0acf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsfvVFsqkCfpTwwddsT","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GJ6FnM8gJNmHpnuNXJ8HbH","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd\nc=pd.read_csv('data/RSAFS_current.csv',parse_dates=[0]).set_index('observation_date').RSAFS\nfr=pd.read_csv('data/first_release.csv')\nprint(c['2025-06':])\n# compare vintages overlap: revisions between consecutive vintages, max abs pct\nimport glob\nprev=None\nfor f in sorted(glob.glob('data/vintages/RSAFS*')):\n    v=pd.read_csv(f,parse_dates=[0]).set_index('observation_date').iloc[:,0]\n    if prev is not None:\n        com=v.index.intersection(prev.index); r=(v[com]/prev[com]-1)*100\n        print(f[-14:-4], len(r[r.abs()>1e-9]), round(r.abs().max(),3), r.abs().idxmax().date())\n    prev=v\nEOF","description":"Check revisions across vintages"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2012,"cache_read_input_tokens":25403,"output_tokens":1111,"output_tokens_details":{"thinking_tokens":684},"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":2012},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsfvCt5t4PMasGLgvct","requestRef":"636d60e8-7aac-41c5-99fd-63f05ca61261","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ac2266f4-5052-44ad-9b50-ba9031c75971","timestamp":"2026-10-30T05:32:22.609Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}56{"parentUuid":"ac2266f4-5052-44ad-9b50-ba9031c75971","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01GJ6FnM8gJNmHpnuNXJ8HbH","type":"tool_result","content":"observation_date\n2025-06-01    691883\n2025-07-01    698280\n2025-08-01    700407\n2025-09-01    700948\n2025-10-01    700790\n2025-11-01    705453\n2025-12-01    706264\n2026-01-01    701860\n2026-02-01    707959\n2026-03-01    719700\n2026-04-01    723921\n2026-05-01    731415\n2026-06-01    732898\n2026-07-01    729915\n2026-08-01    739322\n2026-09-01    745021\nName: RSAFS, dtype: int64\n2025-11-30 4 0.043 2025-07-01\n2025-12-31 4 0.111 2025-09-01\n2026-01-31 4 0.167 2025-10-01\n2026-02-28 4 0.111 2025-11-01\n2026-03-31 4 0.051 2025-01-01\n2026-04-30 5 0.132 2026-01-01\n2026-05-31 4 0.204 2026-02-01\n2026-06-30 4 0.214 2025-05-01\n2026-07-31 4 0.415 2026-05-01","is_error":false}]},"uuid":"67ea1790-568b-4efa-90f7-7dab76b82409","timestamp":"2026-10-30T05:32:22.920Z","toolUseResult":{"stdout":"observation_date\n2025-06-01    691883\n2025-07-01    698280\n2025-08-01    700407\n2025-09-01    700948\n2025-10-01    700790\n2025-11-01    705453\n2025-12-01    706264\n2026-01-01    701860\n2026-02-01    707959\n2026-03-01    719700\n2026-04-01    723921\n2026-05-01    731415\n2026-06-01    732898\n2026-07-01    729915\n2026-08-01    739322\n2026-09-01    745021\nName: RSAFS, dtype: int64\n2025-11-30 4 0.043 2025-07-01\n2025-12-31 4 0.111 2025-09-01\n2026-01-31 4 0.167 2025-10-01\n2026-02-28 4 0.111 2025-11-01\n2026-03-31 4 0.051 2025-01-01\n2026-04-30 5 0.132 2026-01-01\n2026-05-31 4 0.204 2026-02-01\n2026-06-30 4 0.214 2025-05-01\n2026-07-31 4 0.415 2026-05-01","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ac2266f4-5052-44ad-9b50-ba9031c75971","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}57{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"5d8dd5af61be70b26897e365048f26653491a7ffd53ba8d8f89333b0f0f36e89","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01GJ6FnM8gJNmHpnuNXJ8HbH","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd\nc=pd.read_csv('data/RSAFS_current.csv',parse_dates=[0]).set_index('observation_date').RSAFS\nfr=pd.read_csv('data/first_release.csv')\nprint(c['2025-06':])\n# compare vintages overlap: revisions between consecutive vintages, max abs pct\nimport glob\nprev=None\nfor f in sorted(glob.glob('data/vintages/RSAFS*')):\n    v=pd.read_csv(f,parse_dates=[0]).set_index('observation_date').iloc[:,0]\n    if prev is not None:\n        com=v.index.intersection(prev.index); r=(v[com]/prev[com]-1)*100\n        print(f[-14:-4], len(r[r.abs()>1e-9]), round(r.abs().max(),3), r.abs().idxmax().date())\n    prev=v\nEOF","description":"Check revisions across vintages"}}]}}58{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"be3b9b84-31fc-47f2-b5e8-860d06b75c19","timestamp":"2026-10-30T05:32:22.924Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"636d60e8-7aac-41c5-99fd-63f05ca61261","keep":18,"tail":["5d8dd5af61be70b26897e365048f26653491a7ffd53ba8d8f89333b0f0f36e89","cef84bd49238289238976b7037065b8f46f02225299c8ef1b9428378c9b05304"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8110a7cc59b87bd218e19ff214b0169a617620d238177f5b6398bb20da440646"}59{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"67ea1790-568b-4efa-90f7-7dab76b82409","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}60{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}61{"parentUuid":"67ea1790-568b-4efa-90f7-7dab76b82409","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsgmscvvRHkzA4yTPSV","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":1446,"cache_read_input_tokens":27415,"output_tokens":1446,"output_tokens_details":{"thinking_tokens":112},"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":1446},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":910,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsgmJ8YCopYQVQ9hbHG","requestRef":"be3b9b84-31fc-47f2-b5e8-860d06b75c19","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0a17a23d-fb73-43e5-9d79-8eedfd7cb1d8","timestamp":"2026-10-30T05:32:25.133Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"0a17a23d-fb73-43e5-9d79-8eedfd7cb1d8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsgmscvvRHkzA4yTPSV","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01B6dDs2UR6gzeNpg3yky9rY","name":"Bash","input":{"command":"{ echo \"# Data audit (P1)\"; echo; echo \"All SHA-256 values below (first 16 hex shown; full hashes computed and identical to data/README.md and bundle.json). Rows = data rows after header.\"; echo; echo \"| file | sha256 | rows | cols | first obs | last obs | missing | dup dates | month gaps |\"; echo \"|---|---|---|---|---|---|---|---|---|\"; ~/wp29/venv/bin/python /tmp/audit.py | head -23; } > out/state/data_audit.md\ncat >> out/state/data_audit.md <<'EOF'\n\nUnits: RSAFS millions USD SA; PAYEMS thousands of persons SA; UMCSENT index 1966Q1=100; first_release levels in millions USD, yoy in percent (log ×100).\n\n## Findings / anomalies\n1. **Irregular publication timing (RSAFS)**: last(V) = 2025-08 for V=2025-10-31 (two months lag; 2025-09 first appears 2025-11-30), 2026-01 for V=2026-03-31 (two-month lag), and V=2026-04-30 adds two months (2026-02, 2026-03). All other vintages end the month before V. Handled per task rule: targets are last(V)+h, not calendar-based.\n2. **PAYEMS timing**: vintage 2025-10-31 ends 2025-08, 2025-11-30 ends 2025-09, 2025-12-31 ends 2025-11 (no missing month; 2025-10 present from 2025-12-31). PAYEMS vintage 2026-02-28 shows a benchmark revision (2025-12 level 159,526 → 158,497). PAYEMS is not used in my model (see method), so no handling needed beyond documentation.\n3. **UMCSENT**: 210 empty values, all before 1978-01 (survey quarterly/not conducted). Not used in my model.\n4. **Level break between last shipped vintage and current RSAFS**: current file levels for 2025–2026 are ~4–5% below the vintage levels (e.g. 2026-06: 768,553 in vintage 2026-07-31 vs 732,898 now) — a large annual/benchmark revision after 2026-07-31. first_release.csv shows the break between target months 2026-07 (vintage 2026-08-31) and 2026-08 (vintage 2026-09-30). YoY rates are computed within a single vintage, so levels are consistent within each YoY; the break affects (i) the h=3 actuals of the last two origins (targets 2026-08, 2026-09, first released post-revision) and (ii) estimand (d). Documented; no adjustment.\n5. Revisions between consecutive shipped vintages are small (≤0.42% in level), affecting typically 4–5 recent months.\n6. No duplicates, no missing values in RSAFS/PAYEMS/first_release; no month gaps.\n\n## Availability-rule compliance\n- RSAFS_current.csv is used only for estimand (d).\n- UMCSENT current vintage is not used in forecasts (allowed only months ≤ month(V); not needed).\n- first_release.csv used only as evaluation actuals.\nEOF\nprintf \"step,rule,n_before,n_after,n_removed,rationale\\n1,forecast-actual pairs: 10 origins x 2 horizons x 4 models; keep pairs whose target month exists in first_release.csv,80,80,0,all 20 target months (10 per horizon) are present in first_release.csv\\n2,drop pairs with non-finite forecast,80,80,0,no missing forecasts\\n\" > out/exclusions.csv\ncat out/exclusions.csv","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":1446,"cache_read_input_tokens":27415,"output_tokens":1446,"output_tokens_details":{"thinking_tokens":112},"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":1446},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsgmJ8YCopYQVQ9hbHG","requestRef":"be3b9b84-31fc-47f2-b5e8-860d06b75c19","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1ae4cf1d-abbc-44e6-bae9-33bb099f4a7a","timestamp":"2026-10-30T05:32:36.711Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}63{"parentUuid":"1ae4cf1d-abbc-44e6-bae9-33bb099f4a7a","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01B6dDs2UR6gzeNpg3yky9rY","type":"tool_result","content":"step,rule,n_before,n_after,n_removed,rationale\n1,forecast-actual pairs: 10 origins x 2 horizons x 4 models; keep pairs whose target month exists in first_release.csv,80,80,0,all 20 target months (10 per horizon) are present in first_release.csv\n2,drop pairs with non-finite forecast,80,80,0,no missing forecasts","is_error":false}]},"uuid":"cca57f90-e911-4d47-814f-70f4b2786453","timestamp":"2026-10-30T05:32:37.039Z","toolUseResult":{"stdout":"step,rule,n_before,n_after,n_removed,rationale\n1,forecast-actual pairs: 10 origins x 2 horizons x 4 models; keep pairs whose target month exists in first_release.csv,80,80,0,all 20 target months (10 per horizon) are present in first_release.csv\n2,drop pairs with non-finite forecast,80,80,0,no missing forecasts","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1ae4cf1d-abbc-44e6-bae9-33bb099f4a7a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}64{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"d321fa92f4080957e2ceb1b81a8334167c6b08c2d793cc45bbc55ea51defa113","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSpAgKEAgTGAI4AUIIdGhpbmtpbmcSDJACozCxsd8rKc9laxoMkbhBSAyLeIOFNFjOIjCCeAORLdWy6cy1JnVTaz85tChEmc5esgrLtj9YpJjSG3pFfmbRxtUgtjTc5OeDDlwqwQeWPBgwG2XCFlmFtlUhCfImMLqt/4ptjtJ++dlANF/ovBJQ5szceJdm7bPvEKwRa9WkLW++mZNTF/wNPWtYQrpEFF9qY+zN5k1jTxnXCoxPRdg7jOShEzhNMC+Vl+sMxX7nqDrx+lYBkSa4/za1hdb/vEAdRDT9SKIsOO1zyAcJlbn5dRTq8emDZ2vnzZxxJOS9GQY86ED5h8MIU4u4cH+QNlJewL0hcycjpfIRkBv3/Zd+XqRAoaSKsT3NksBWa8kQiNFb7cZXG/EVPGoYNMpsOMgN59akgkbaAVf4+co+B3GRfP2eE3aNra9hwo8dP8VnMCG4H2VKOHadAkXGVGzFSOYI+S1b3G+aYKRb/lPEMzNtw0hC29iLRHGaeqVA+AEaGDUPzFHB6+z3r5f36IedIVX8ioJA+9H18tzzcgHzGYjl3XAvrQxB5iw1vWleMeLiBQ8kx5Ve7DUcAkRz2fKlwr8P+lP+bEsq8hs8NaJhjn1rzZ3vyIxURvfIfWCX04e59rxo2PohGEJ5mFuGp/K3uRr+GqEYyxDV+mxIZpI1IAnegEy/ha/YPS1tQEHL2hr7O1cwDJpv5WLIkVkonIKHpzhaetUB8y/8YvKjpNTH2MaQjGvw3PkjYK/f9XnztF8KUNVLPYIPBs/BDzSihxb+HtR+roBFCTqFZ6mAQV8vrVQx8eMbuIEMNUgZSssyM9JUMtwvIg3B//33uGDTfSEoJOxaAHbt+MmP0qhrrJpjZICVlsufo+Z4OPIc5kIzwyK+gZSRI15mNy42vja70QtwCVeF4nd+dXCPyqjiQTbetoa6Uf8zwJxzrvsNijI5AmHJfp2WBlqknVsR2ttLpwWCS2xyA3NMcOu44oxjvE40FsfTZ/3qcEepk6TM99d67JMSlnYK7LnLrBaqNZ+uNKCHKpvOGjnokI+zHqEUcYFLVdvf1Tp9XQuLtegKWg39NKvYStW/4nGzFX2VlTTBL7I4AmEbeWtY6NqfPJAiKBKANzS9tWrSGSQnHBvOOyegmO5s0/3uVTq+kqvUygqVjJeoiuULDbkz8zS1kxG/FZt7Q7/Ql7EX7rEs/kJRx1NW5xpfl3cm/D1PaOJ61w7xJCBLDG1VIjD0tb2r4XWuBd7UTwUFFIzVGQm/M1bFRDkZHywitdVWaW2/4wBmF1KwBHqXE01oHxyKOKdl56kIraXhwa4I2OOyinAyOQzMFm2BcmlVVoZ2pOX4hEPevhz75o0G6Ca24mxyh+fOessS0nF9fxfIFXNRdZrW86rqCt+BbDJ4GAE="},{"type":"tool_use","id":"toolu_01B6dDs2UR6gzeNpg3yky9rY","name":"Bash","input":{"command":"{ echo \"# Data audit (P1)\"; echo; echo \"All SHA-256 values below (first 16 hex shown; full hashes computed and identical to data/README.md and bundle.json). Rows = data rows after header.\"; echo; echo \"| file | sha256 | rows | cols | first obs | last obs | missing | dup dates | month gaps |\"; echo \"|---|---|---|---|---|---|---|---|---|\"; ~/wp29/venv/bin/python /tmp/audit.py | head -23; } > out/state/data_audit.md\ncat >> out/state/data_audit.md <<'EOF'\n\nUnits: RSAFS millions USD SA; PAYEMS thousands of persons SA; UMCSENT index 1966Q1=100; first_release levels in millions USD, yoy in percent (log ×100).\n\n## Findings / anomalies\n1. **Irregular publication timing (RSAFS)**: last(V) = 2025-08 for V=2025-10-31 (two months lag; 2025-09 first appears 2025-11-30), 2026-01 for V=2026-03-31 (two-month lag), and V=2026-04-30 adds two months (2026-02, 2026-03). All other vintages end the month before V. Handled per task rule: targets are last(V)+h, not calendar-based.\n2. **PAYEMS timing**: vintage 2025-10-31 ends 2025-08, 2025-11-30 ends 2025-09, 2025-12-31 ends 2025-11 (no missing month; 2025-10 present from 2025-12-31). PAYEMS vintage 2026-02-28 shows a benchmark revision (2025-12 level 159,526 → 158,497). PAYEMS is not used in my model (see method), so no handling needed beyond documentation.\n3. **UMCSENT**: 210 empty values, all before 1978-01 (survey quarterly/not conducted). Not used in my model.\n4. **Level break between last shipped vintage and current RSAFS**: current file levels for 2025–2026 are ~4–5% below the vintage levels (e.g. 2026-06: 768,553 in vintage 2026-07-31 vs 732,898 now) — a large annual/benchmark revision after 2026-07-31. first_release.csv shows the break between target months 2026-07 (vintage 2026-08-31) and 2026-08 (vintage 2026-09-30). YoY rates are computed within a single vintage, so levels are consistent within each YoY; the break affects (i) the h=3 actuals of the last two origins (targets 2026-08, 2026-09, first released post-revision) and (ii) estimand (d). Documented; no adjustment.\n5. Revisions between consecutive shipped vintages are small (≤0.42% in level), affecting typically 4–5 recent months.\n6. No duplicates, no missing values in RSAFS/PAYEMS/first_release; no month gaps.\n\n## Availability-rule compliance\n- RSAFS_current.csv is used only for estimand (d).\n- UMCSENT current vintage is not used in forecasts (allowed only months ≤ month(V); not needed).\n- first_release.csv used only as evaluation actuals.\nEOF\nprintf \"step,rule,n_before,n_after,n_removed,rationale\\n1,forecast-actual pairs: 10 origins x 2 horizons x 4 models; keep pairs whose target month exists in first_release.csv,80,80,0,all 20 target months (10 per horizon) are present in first_release.csv\\n2,drop pairs with non-finite forecast,80,80,0,no missing forecasts\\n\" > out/exclusions.csv\ncat out/exclusions.csv","description":"Write data audit and exclusion ledger"}}]}}65{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"d2cbda17-4cad-4595-a643-0b178a58a4e8","timestamp":"2026-10-30T05:32:37.042Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"be3b9b84-31fc-47f2-b5e8-860d06b75c19","keep":20,"tail":["d321fa92f4080957e2ceb1b81a8334167c6b08c2d793cc45bbc55ea51defa113","3c6de7af70c37c7076ca4cbe59eb8994e4412bb3e2833d30136a73521149633a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a112da2f6c128a3e3060c874c389a79d89297a9664e24d37381a0826e777ebb6"}66{"parentUuid":"cca57f90-e911-4d47-814f-70f4b2786453","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXshovv6HagmAprXYave","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":1553,"cache_read_input_tokens":28861,"output_tokens":5498,"output_tokens_details":{"thinking_tokens":96},"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":1553},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":844,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXshofYgo2riP6WmJ6fq","requestRef":"d2cbda17-4cad-4595-a643-0b178a58a4e8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"04dc85cd-4927-4381-99dc-45e947f131e7","timestamp":"2026-10-30T05:32:38.939Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}67{"parentUuid":"04dc85cd-4927-4381-99dc-45e947f131e7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXshovv6HagmAprXYave","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013YZpTmWyn6m9qTSo8N89AG","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\nRun from 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.\nDeterministic (no randomness except the seeded bootstrap below).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nSEED = 20261030\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\"]\nn_input_rows = {}\n\n\ndef read_series(path, key):\n    df = pd.read_csv(path)\n    n_input_rows[key] = int(len(df))\n    s = df.set_index(pd.PeriodIndex(pd.to_datetime(df.iloc[:, 0]), freq=\"M\")).iloc[:, 1].astype(float)\n    return s\n\n\ndef yoy(level):\n    lg = np.log(level)\n    return 100.0 * (lg - lg.shift(12, freq=\"M\").reindex(lg.index))\n\n\ndef nw_dm(d, h):\n    \"\"\"DM stat with Bartlett long-run variance, truncation lag h-1, no HLN factor.\"\"\"\n    d = np.asarray(d, float); n = len(d); dbar = d.mean(); u = d - dbar\n    lrv = np.sum(u * u) / n\n    L = h - 1\n    for k in range(1, L + 1):\n        w = 1.0 - k / (L + 1.0)\n        lrv += 2.0 * w * np.sum(u[k:] * u[:-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(lrv)\n\n\n# ---------------------------------------------------------------- inputs\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"))\nn_input_rows[\"first_release.csv\"] = int(len(fr))\nactual = pd.Series(fr[\"yoy_first_release\"].values,\n                   index=pd.PeriodIndex(pd.to_datetime(fr[\"target_month\"]), freq=\"M\"))\nrs_vint = {V: read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"),\n                          f\"vintages/RSAFS_vintage_{V}.csv\") for V in ORIGINS}\n# PAYEMS / UMCSENT are read only for the audit row counts; they are not inputs to any forecast.\nfor V in ORIGINS:\n    read_series(os.path.join(DATA, \"vintages\", f\"PAYEMS_vintage_{V}.csv\"), f\"vintages/PAYEMS_vintage_{V}.csv\")\nread_series(os.path.join(DATA, \"UMCSENT.csv\"), \"UMCSENT.csv\")\nrs_current = read_series(os.path.join(DATA, \"RSAFS_current.csv\"), \"RSAFS_current.csv\")  # estimand (d) only\n\n# ---------------------------------------------------------------- forecasts\nrows, ar_info, lastmonths = [], {}, {}\nfor V in ORIGINS:\n    L = rs_vint[V]\n    assert L.index.max() < pd.Period(V, \"M\") or L.index.max() <= pd.Period(V, \"M\")\n    g = yoy(L).dropna()\n    last = L.index.max(); lastmonths[V] = str(last)\n    lnL = np.log(L)\n    # AR(1): g_m on const, g_{m-1}, 1993-02 <= m <= last\n    y = g.loc[pd.Period(\"1993-02\", \"M\"):last]\n    x = g.shift(1, freq=\"M\").reindex(y.index)\n    X = np.column_stack([np.ones(len(y)), x.values])\n    c, phi = np.linalg.lstsq(X, y.values, rcond=None)[0]\n    ar_info[V] = {\"const\": float(c), \"phi\": float(phi), \"n\": int(len(y))}\n    for h in HORIZONS:\n        T = last + h\n        fc = {}\n        fc[\"naive\"] = g[last]\n        fc[\"snaive\"] = g[T - 12]\n        f = g[last]\n        for _ in range(h):\n            f = c + phi * f\n        fc[\"ar1\"] = f\n        # Own model: base-effect random walk with drift in log level.\n        # ln L_T forecast = ln L_last + h * drift, drift = g_last/12 (avg monthly log growth over last 12 months);\n        # YoY forecast = 100*(ln L_T_hat - ln L_{T-12}), with L_{T-12} known in the same vintage.\n        drift = g[last] / 100.0 / 12.0\n        fc[\"model\"] = 100.0 * (lnL[last] + h * drift - lnL[T - 12])\n        for m in MODELS:\n            rows.append({\"origin_date\": V, \"target_date\": T.to_timestamp().strftime(\"%Y-%m-%d\"),\n                         \"horizon\": h, \"forecast\": float(fc[m]),\n                         \"actual_first_release\": float(actual[T]) if T in actual.index else np.nan,\n                         \"model\": m, \"vintage_used\": V})\nfc_df = pd.DataFrame(rows)\nfc_df[\"error\"] = fc_df[\"actual_first_release\"] - fc_df[\"forecast\"]\nfc_df[[\"origin_date\", \"target_date\", \"horizon\", \"forecast\", \"actual_first_release\", \"model\", \"vintage_used\"]] \\\n    .to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False, float_format=\"%.6f\")\n\n# ---------------------------------------------------------------- evaluation\nres = {\"task_id\": \"T1-forecast\",\n       \"model_name\": \"BE-RWD (base-effect random walk with drift in log level)\",\n       \"model_description\": (\n           \"Univariate real-time model on the RSAFS vintage dated V only. The log level is forecast as a random walk \"\n           \"with drift: ln L_hat(last+h) = ln L(last) + h*d, with d = g_last/1200, i.e. the average monthly log growth \"\n           \"over the 12 months ending at last(V) in that vintage. The YoY forecast is 100*(ln L_hat(T) - ln L(T-12)), \"\n           \"where L(T-12) is read from the same vintage, so the forecast equals the naive forecast plus a known \"\n           \"base-effect correction (the change in the year-earlier comparison level) and drift. No parameters are \"\n           \"estimated; PAYEMS and UMCSENT are not used. Specification fixed before looking at any evaluation outcome; \"\n           \"no alternative models were tried on the evaluation sample.\"),\n       \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\ntable = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc_df.query(\"model==@m and horizon==@h\")[\"error\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        table.append({\"model\": m, \"horizon\": h, \"rmse\": rmse, \"mae\": mae, \"n\": int(len(e))})\npd.DataFrame(table).to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nextra = {}\nrng = np.random.default_rng(SEED)\nfor h in HORIZONS:\n    en = fc_df.query(\"model=='naive' and horizon==@h\").sort_values(\"origin_date\")[\"error\"].values\n    em = fc_df.query(\"model=='model' and 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    d = en ** 2 - em ** 2\n    s, p, lrv = nw_dm(d, h)\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = s, p\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{'significant' if p < 0.05 else 'not_significant'}\"\n    # supplementary: moving-block bootstrap (block length max(h,2)) of RMSE_naive - RMSE_model\n    B, bl, n = 5000, max(h, 2), len(d)\n    diffs = []\n    for _ in range(B):\n        starts = rng.integers(0, n - bl + 1, size=int(np.ceil(n / bl)))\n        idx = np.concatenate([np.arange(s0, s0 + bl) for s0 in starts])[:n]\n        diffs.append(np.sqrt(np.mean(en[idx] ** 2)) - np.sqrt(np.mean(em[idx] ** 2)))\n    lo, hi = np.percentile(diffs, [2.5, 97.5])\n    extra[f\"h{h}\"] = {\"dm_lrv\": lrv, \"mean_loss_diff\": float(d.mean()),\n                      \"rmse_diff_naive_minus_model\": res[f\"rmse_naive_h{h}\"] - res[f\"rmse_model_h{h}\"],\n                      \"boot_rmse_diff_ci95\": [float(lo), float(hi)], \"boot_B\": B, \"boot_block\": bl,\n                      \"share_origins_model_smaller_sq_error\": float(np.mean(d > 0))}\n\n# (d) revisions: h=1 targets, current-vintage YoY vs first release\ng_cur = yoy(rs_current)\nt1 = fc_df.query(\"model=='naive' and horizon==1\")\ntm = pd.PeriodIndex(pd.to_datetime(t1[\"target_date\"]), freq=\"M\")\nrev = np.abs(g_cur.reindex(tm).values - actual.reindex(tm).values)\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(rev))\nextra[\"revision_by_target\"] = {str(k): float(v) for k, v in zip(tm, g_cur.reindex(tm).values - actual.reindex(tm).values)}\nextra[\"ar1_params\"] = ar_info\nextra[\"last_month_by_origin\"] = lastmonths\n\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nres[\"data_issues\"] = [\n    {\"issue\": \"Irregular RSAFS publication timing: last(V)=2025-08 at V=2025-10-31 and 2026-01 at V=2026-03-31 (two-month lag); V=2026-04-30 adds two months at once.\",\n     \"handling\": \"Targets defined as last(V)+h per task rule; the 2025-10-31 and 2026-03-31 origins therefore forecast months that are 2 and 4 months past the last calendar month.\"},\n    {\"issue\": \"Two h=1 and h=3 targets coincide across origins (e.g. 2026-01 is h=3 of 2025-12-31... see forecasts.csv) and h=3 errors overlap, inducing serial correlation.\",\n     \"handling\": \"DM long-run variance uses Bartlett kernel with truncation lag h-1 as specified.\"},\n    {\"issue\": \"Large level revision of RSAFS after the 2026-07-31 vintage (current levels ~4-5% below vintage levels); first_release.csv shows the break between targets 2026-07 and 2026-08.\",\n     \"handling\": \"YoY always computed within one vintage; h=3 actuals for targets 2026-08/2026-09 are post-revision first releases, used as given; estimand (d) reflects this revision.\"},\n    {\"issue\": \"PAYEMS benchmark revision visible in the 2026-02-28 vintage; PAYEMS 2025-10 first appears in the 2025-12-31 vintage.\",\n     \"handling\": \"PAYEMS not used in any forecast; documented only.\"},\n    {\"issue\": \"UMCSENT has 210 empty values before 1978-01.\",\n     \"handling\": \"UMCSENT not used in any forecast; documented only.\"},\n]\nres[\"n_input_rows\"] = dict(sorted(n_input_rows.items()))\nres[\"n_analysed\"] = int(fc_df.query(\"model=='model'\")[\"error\"].notna().sum())\nres[\"random_seed\"] = SEED\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=1)\nwith open(os.path.join(OUT, \"supplementary.json\"), \"w\") as fh:\n    json.dump(extra, fh, indent=1)\n\n# ---------------------------------------------------------------- figure\nfig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc_df.query(\"horizon==@h\")\n    for m, sty in [(\"naive\", \"s--\"), (\"model\", \"o-\"), (\"ar1\", \"^:\")]:\n        s = sub.query(\"model==@m\").sort_values(\"target_date\")\n        ax.plot(pd.to_datetime(s[\"target_date\"]), s[\"forecast\"], sty, label=m, alpha=.8)\n    s = sub.query(\"model=='naive'\").sort_values(\"target_date\")\n    ax.plot(pd.to_datetime(s[\"target_date\"]), s[\"actual_first_release\"], \"k-\", lw=2.2, label=\"first release\")\n    ax.set_title(f\"h = {h}: RSAFS YoY growth (%), real-time forecasts\")\n    ax.set_xlabel(\"target month\"); ax.grid(alpha=.3); ax.tick_params(axis=\"x\", rotation=45)\naxes[0].set_ylabel(\"percent\"); axes[0].legend()\nfig.tight_layout(); fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(pd.DataFrame(table).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.4f} p={res[f'dm_pvalue_h{h}']:.4f} {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets\", round(res[\"mean_abs_revision_h1_targets\"], 4))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/supplementary.json && cat out/forecasts.csv | grep -E \"naive|model$|,model,\" | head -0; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('out/forecasts.csv'); print(d.pivot_table(index=['horizon','origin_date','target_date','actual_first_release'],columns='model',values='forecast').round(2))\"","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":1553,"cache_read_input_tokens":28861,"output_tokens":5498,"output_tokens_details":{"thinking_tokens":96},"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":1553},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXshofYgo2riP6WmJ6fq","requestRef":"d2cbda17-4cad-4595-a643-0b178a58a4e8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a8e68b38-8443-479b-b2da-2fde27feddb8","timestamp":"2026-10-30T05:33:19.371Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}68{"parentUuid":"a8e68b38-8443-479b-b2da-2fde27feddb8","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013YZpTmWyn6m9qTSo8N89AG","type":"tool_result","content":" model  horizon     rmse      mae  n\n naive        1 0.996874 0.848722 10\n naive        3 1.420040 1.200449 10\nsnaive        1 1.674543 1.306670 10\nsnaive        3 1.316079 1.065869 10\n   ar1        1 0.940524 0.797651 10\n   ar1        3 1.187118 0.952690 10\n model        1 0.550298 0.486332 10\n model        3 1.142220 0.933977 10\nh=1: rel_impr=0.4480 DM=2.4290 p=0.0151 model_better_significant\nh=3: rel_impr=0.1956 DM=1.5466 p=0.1220 model_better_not_significant\nmean_abs_revision_h1_targets 0.5482\n{\n \"h1\": {\n  \"dm_lrv\": 0.8091371398245399,\n  \"mean_loss_diff\": 0.6909309111104219,\n  \"rmse_diff_naive_minus_model\": 0.4465766485333519,\n  \"boot_rmse_diff_ci95\": [\n   0.2615951068646396,\n   0.6987722437362641\n  ],\n  \"boot_B\": 5000,\n  \"boot_block\": 2,\n  \"share_origins_model_smaller_sq_error\": 0.8\n },\n \"h3\": {\n  \"dm_lrv\": 2.1185192376081026,\n  \"mean_loss_diff\": 0.7118487020783464,\n  \"rmse_diff_naive_minus_model\": 0.27782062212475767,\n  \"boot_rmse_diff_ci95\": [\n   -0.14490476470017666,\n   0.6265360274461692\n  ],\n  \"boot_B\": 5000,\n  \"boot_block\": 3,\n  \"share_origins_model_smaller_sq_error\": 0.6\n },\n \"revision_by_target\": {\n  \"2025-09\": -0.5502167925401169,\n  \"2025-10\": -0.6641763167215546,\n  \"2025-11\": -0.43891998227811113,\n  \"2025-12\": -0.32862681655441595,\n  \"2026-01\": -0.9756759757612712,\n  \"2026-02\": -0.4099556308938235,\n  \"2026-04\": -0.7481728291013168,\n  \"2026-05\": -0.16533992600872516,\n  \"2026-06\": -0.7440888135517616,\n  \"2026-07\": -0.4570249449779187\n },\n \"ar1_params\": {\n  \"2025-10-31\": {\n   \"const\": 0.7245195130966369,\n   \"phi\": 0.8398849523075356,\n   \"n\": 391\n  },\n  \"2025-11-30\": {\n   \"const\": 0.7230146850375044,\n   \"phi\": 0.8398593258796581,\n   \"n\": 392\n  },\n  \"2025-12-31\": {\n   \"const\": 0.7207145937397748,\n   \"phi\": 0.8398988453218994,\n   \"n\": 393\n  },\n  \"2026-01-31\": {\n   \"const\": 0.7197147078017161,\n   \"phi\": 0.839929613490428,\n   \"n\": 394\n  },\n  \"2026-02-28\": {\n   \"const\": 0.7161329757524207,\n   \"phi\": 0.840103885059219,\n   \"n\": 395\n  },\n  \"2026-03-31\": {\n   \"const\": 0.7173993115367638,\n   \"phi\": 0.8400215083855623,\n   \"n\": 396\n  },\n  \"2026-04-30\": {\n   \"const\": 0.7192001736723118,\n   \"phi\": 0.8399036982121751,\n   \"n\": 398\n  },\n  \"2026-05-31\": {\n   \"const\": 0.7216117313802095,\n   \"phi\": 0.8398320190588064,\n   \"n\": 399\n  },\n  \"2026-06-30\": {\n   \"const\": 0.7265261438714329,\n   \"phi\": 0.8398016339053244,\n   \"n\": 400\n  },\n  \"2026-07-31\": {\n   \"const\": 0.7268024118912031,\n   \"phi\": 0.839871473088339,\n   \"n\": 401\n  }\n },\n \"last_month_by_origin\": {\n  \"2025-10-31\": \"2025-08\",\n  \"2025-11-30\": \"2025-09\",\n  \"2025-12-31\": \"2025-10\",\n  \"2026-01-31\": \"2025-11\",\n  \"2026-02-28\": \"2025-12\",\n  \"2026-03-31\": \"2026-01\",\n  \"2026-04-30\": \"2026-03\",\n  \"2026-05-31\": \"2026-04\",\n  \"2026-06-30\": \"2026-05\",\n  \"2026-07-31\": \"2026-06\"\n }\n}head: illegal line count -- 0\nmodel                                                  ar1  ...  snaive\nhorizon origin_date target_date actual_first_release        ...        \n1       2025-10-31  2025-09-01  4.173540              4.82  ...    1.96\n        2025-11-30  2025-10-01  3.410194              4.23  ...    3.08\n        2025-12-31  2025-11-01  3.277601              3.58  ...    3.84\n        2026-01-31  2025-12-01  2.398715              3.47  ...    4.47\n        2026-02-28  2026-01-01  3.107200              2.73  ...    4.46\n        2026-03-31  2026-02-01  3.886121              3.33  ...    3.79\n        2026-04-30  2026-04-01  4.758475              3.99  ...    4.85\n        2026-05-31  2026-05-01  6.650342              4.72  ...    3.31\n        2026-06-30  2026-06-01  6.503056              6.31  ...    4.32\n        2026-07-31  2026-07-01  4.887817              6.19  ...    4.05\n3       2025-10-31  2025-11-01  3.277601              4.73  ...    3.84\n        2025-11-30  2025-12-01  2.398715              4.31  ...    4.47\n        2025-12-31  2026-01-01  3.107200              3.85  ...    4.46\n        2026-01-31  2026-02-01  3.886121              3.77  ...    3.79\n        2026-02-28  2026-03-01  3.892690              3.25  ...    4.96\n        2026-03-31  2026-04-01  4.758475              3.67  ...    4.85\n        2026-04-30  2026-06-01  6.503056              4.14  ...    4.32\n        2026-05-31  2026-07-01  4.887817              4.66  ...    4.05\n        2026-06-30  2026-08-01  5.223092              5.79  ...    4.85\n        2026-07-31  2026-09-01  6.097870              5.70  ...    4.06\n\n[20 rows x 4 columns]","is_error":false}]},"uuid":"7458eff7-5f69-4860-bfae-b1884268e736","timestamp":"2026-10-30T05:33:20.907Z","toolUseResult":{"stdout":" model  horizon     rmse      mae  n\n naive        1 0.996874 0.848722 10\n naive        3 1.420040 1.200449 10\nsnaive        1 1.674543 1.306670 10\nsnaive        3 1.316079 1.065869 10\n   ar1        1 0.940524 0.797651 10\n   ar1        3 1.187118 0.952690 10\n model        1 0.550298 0.486332 10\n model        3 1.142220 0.933977 10\nh=1: rel_impr=0.4480 DM=2.4290 p=0.0151 model_better_significant\nh=3: rel_impr=0.1956 DM=1.5466 p=0.1220 model_better_not_significant\nmean_abs_revision_h1_targets 0.5482\n{\n \"h1\": {\n  \"dm_lrv\": 0.8091371398245399,\n  \"mean_loss_diff\": 0.6909309111104219,\n  \"rmse_diff_naive_minus_model\": 0.4465766485333519,\n  \"boot_rmse_diff_ci95\": [\n   0.2615951068646396,\n   0.6987722437362641\n  ],\n  \"boot_B\": 5000,\n  \"boot_block\": 2,\n  \"share_origins_model_smaller_sq_error\": 0.8\n },\n \"h3\": {\n  \"dm_lrv\": 2.1185192376081026,\n  \"mean_loss_diff\": 0.7118487020783464,\n  \"rmse_diff_naive_minus_model\": 0.27782062212475767,\n  \"boot_rmse_diff_ci95\": [\n   -0.14490476470017666,\n   0.6265360274461692\n  ],\n  \"boot_B\": 5000,\n  \"boot_block\": 3,\n  \"share_origins_model_smaller_sq_error\": 0.6\n },\n \"revision_by_target\": {\n  \"2025-09\": -0.5502167925401169,\n  \"2025-10\": -0.6641763167215546,\n  \"2025-11\": -0.43891998227811113,\n  \"2025-12\": -0.32862681655441595,\n  \"2026-01\": -0.9756759757612712,\n  \"2026-02\": -0.4099556308938235,\n  \"2026-04\": -0.7481728291013168,\n  \"2026-05\": -0.16533992600872516,\n  \"2026-06\": -0.7440888135517616,\n  \"2026-07\": -0.4570249449779187\n },\n \"ar1_params\": {\n  \"2025-10-31\": {\n   \"const\": 0.7245195130966369,\n   \"phi\": 0.8398849523075356,\n   \"n\": 391\n  },\n  \"2025-11-30\": {\n   \"const\": 0.7230146850375044,\n   \"phi\": 0.8398593258796581,\n   \"n\": 392\n  },\n  \"2025-12-31\": {\n   \"const\": 0.7207145937397748,\n   \"phi\": 0.8398988453218994,\n   \"n\": 393\n  },\n  \"2026-01-31\": {\n   \"const\": 0.7197147078017161,\n   \"phi\": 0.839929613490428,\n   \"n\": 394\n  },\n  \"2026-02-28\": {\n   \"const\": 0.7161329757524207,\n   \"phi\": 0.840103885059219,\n   \"n\": 395\n  },\n  \"2026-03-31\": {\n   \"const\": 0.7173993115367638,\n   \"phi\": 0.8400215083855623,\n   \"n\": 396\n  },\n  \"2026-04-30\": {\n   \"const\": 0.7192001736723118,\n   \"phi\": 0.8399036982121751,\n   \"n\": 398\n  },\n  \"2026-05-31\": {\n   \"const\": 0.7216117313802095,\n   \"phi\": 0.8398320190588064,\n   \"n\": 399\n  },\n  \"2026-06-30\": {\n   \"const\": 0.7265261438714329,\n   \"phi\": 0.8398016339053244,\n   \"n\": 400\n  },\n  \"2026-07-31\": {\n   \"const\": 0.7268024118912031,\n   \"phi\": 0.839871473088339,\n   \"n\": 401\n  }\n },\n \"last_month_by_origin\": {\n  \"2025-10-31\": \"2025-08\",\n  \"2025-11-30\": \"2025-09\",\n  \"2025-12-31\": \"2025-10\",\n  \"2026-01-31\": \"2025-11\",\n  \"2026-02-28\": \"2025-12\",\n  \"2026-03-31\": \"2026-01\",\n  \"2026-04-30\": \"2026-03\",\n  \"2026-05-31\": \"2026-04\",\n  \"2026-06-30\": \"2026-05\",\n  \"2026-07-31\": \"2026-06\"\n }\n}head: illegal line count -- 0\nmodel                                                  ar1  ...  snaive\nhorizon origin_date target_date actual_first_release        ...        \n1       2025-10-31  2025-09-01  4.173540              4.82  ...    1.96\n        2025-11-30  2025-10-01  3.410194              4.23  ...    3.08\n        2025-12-31  2025-11-01  3.277601              3.58  ...    3.84\n        2026-01-31  2025-12-01  2.398715              3.47  ...    4.47\n        2026-02-28  2026-01-01  3.107200              2.73  ...    4.46\n        2026-03-31  2026-02-01  3.886121              3.33  ...    3.79\n        2026-04-30  2026-04-01  4.758475              3.99  ...    4.85\n        2026-05-31  2026-05-01  6.650342              4.72  ...    3.31\n        2026-06-30  2026-06-01  6.503056              6.31  ...    4.32\n        2026-07-31  2026-07-01  4.887817              6.19  ...    4.05\n3       2025-10-31  2025-11-01  3.277601              4.73  ...    3.84\n        2025-11-30  2025-12-01  2.398715              4.31  ...    4.47\n        2025-12-31  2026-01-01  3.107200              3.85  ...    4.46\n        2026-01-31  2026-02-01  3.886121              3.77  ...    3.79\n        2026-02-28  2026-03-01  3.892690              3.25  ...    4.96\n        2026-03-31  2026-04-01  4.758475              3.67  ...    4.85\n        2026-04-30  2026-06-01  6.503056              4.14  ...    4.32\n        2026-05-31  2026-07-01  4.887817              4.66  ...    4.05\n        2026-06-30  2026-08-01  5.223092              5.79  ...    4.85\n        2026-07-31  2026-09-01  6.097870              5.70  ...    4.06\n\n[20 rows x 4 columns]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a8e68b38-8443-479b-b2da-2fde27feddb8","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}69{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"845812d5e831599b3f84f6d402c5bdaeb946b342af8433627467cb6e9a674439","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_013YZpTmWyn6m9qTSo8N89AG","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\nRun from 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.\nDeterministic (no randomness except the seeded bootstrap below).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nSEED = 20261030\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\"]\nn_input_rows = {}\n\n\ndef read_series(path, key):\n    df = pd.read_csv(path)\n    n_input_rows[key] = int(len(df))\n    s = df.set_index(pd.PeriodIndex(pd.to_datetime(df.iloc[:, 0]), freq=\"M\")).iloc[:, 1].astype(float)\n    return s\n\n\ndef yoy(level):\n    lg = np.log(level)\n    return 100.0 * (lg - lg.shift(12, freq=\"M\").reindex(lg.index))\n\n\ndef nw_dm(d, h):\n    \"\"\"DM stat with Bartlett long-run variance, truncation lag h-1, no HLN factor.\"\"\"\n    d = np.asarray(d, float); n = len(d); dbar = d.mean(); u = d - dbar\n    lrv = np.sum(u * u) / n\n    L = h - 1\n    for k in range(1, L + 1):\n        w = 1.0 - k / (L + 1.0)\n        lrv += 2.0 * w * np.sum(u[k:] * u[:-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(lrv)\n\n\n# ---------------------------------------------------------------- inputs\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"))\nn_input_rows[\"first_release.csv\"] = int(len(fr))\nactual = pd.Series(fr[\"yoy_first_release\"].values,\n                   index=pd.PeriodIndex(pd.to_datetime(fr[\"target_month\"]), freq=\"M\"))\nrs_vint = {V: read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"),\n                          f\"vintages/RSAFS_vintage_{V}.csv\") for V in ORIGINS}\n# PAYEMS / UMCSENT are read only for the audit row counts; they are not inputs to any forecast.\nfor V in ORIGINS:\n    read_series(os.path.join(DATA, \"vintages\", f\"PAYEMS_vintage_{V}.csv\"), f\"vintages/PAYEMS_vintage_{V}.csv\")\nread_series(os.path.join(DATA, \"UMCSENT.csv\"), \"UMCSENT.csv\")\nrs_current = read_series(os.path.join(DATA, \"RSAFS_current.csv\"), \"RSAFS_current.csv\")  # estimand (d) only\n\n# ---------------------------------------------------------------- forecasts\nrows, ar_info, lastmonths = [], {}, {}\nfor V in ORIGINS:\n    L = rs_vint[V]\n    assert L.index.max() < pd.Period(V, \"M\") or L.index.max() <= pd.Period(V, \"M\")\n    g = yoy(L).dropna()\n    last = L.index.max(); lastmonths[V] = str(last)\n    lnL = np.log(L)\n    # AR(1): g_m on const, g_{m-1}, 1993-02 <= m <= last\n    y = g.loc[pd.Period(\"1993-02\", \"M\"):last]\n    x = g.shift(1, freq=\"M\").reindex(y.index)\n    X = np.column_stack([np.ones(len(y)), x.values])\n    c, phi = np.linalg.lstsq(X, y.values, rcond=None)[0]\n    ar_info[V] = {\"const\": float(c), \"phi\": float(phi), \"n\": int(len(y))}\n    for h in HORIZONS:\n        T = last + h\n        fc = {}\n        fc[\"naive\"] = g[last]\n        fc[\"snaive\"] = g[T - 12]\n        f = g[last]\n        for _ in range(h):\n            f = c + phi * f\n        fc[\"ar1\"] = f\n        # Own model: base-effect random walk with drift in log level.\n        # ln L_T forecast = ln L_last + h * drift, drift = g_last/12 (avg monthly log growth over last 12 months);\n        # YoY forecast = 100*(ln L_T_hat - ln L_{T-12}), with L_{T-12} known in the same vintage.\n        drift = g[last] / 100.0 / 12.0\n        fc[\"model\"] = 100.0 * (lnL[last] + h * drift - lnL[T - 12])\n        for m in MODELS:\n            rows.append({\"origin_date\": V, \"target_date\": T.to_timestamp().strftime(\"%Y-%m-%d\"),\n                         \"horizon\": h, \"forecast\": float(fc[m]),\n                         \"actual_first_release\": float(actual[T]) if T in actual.index else np.nan,\n                         \"model\": m, \"vintage_used\": V})\nfc_df = pd.DataFrame(rows)\nfc_df[\"error\"] = fc_df[\"actual_first_release\"] - fc_df[\"forecast\"]\nfc_df[[\"origin_date\", \"target_date\", \"horizon\", \"forecast\", \"actual_first_release\", \"model\", \"vintage_used\"]] \\\n    .to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False, float_format=\"%.6f\")\n\n# ---------------------------------------------------------------- evaluation\nres = {\"task_id\": \"T1-forecast\",\n       \"model_name\": \"BE-RWD (base-effect random walk with drift in log level)\",\n       \"model_description\": (\n           \"Univariate real-time model on the RSAFS vintage dated V only. The log level is forecast as a random walk \"\n           \"with drift: ln L_hat(last+h) = ln L(last) + h*d, with d = g_last/1200, i.e. the average monthly log growth \"\n           \"over the 12 months ending at last(V) in that vintage. The YoY forecast is 100*(ln L_hat(T) - ln L(T-12)), \"\n           \"where L(T-12) is read from the same vintage, so the forecast equals the naive forecast plus a known \"\n           \"base-effect correction (the change in the year-earlier comparison level) and drift. No parameters are \"\n           \"estimated; PAYEMS and UMCSENT are not used. Specification fixed before looking at any evaluation outcome; \"\n           \"no alternative models were tried on the evaluation sample.\"),\n       \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\ntable = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc_df.query(\"model==@m and horizon==@h\")[\"error\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        table.append({\"model\": m, \"horizon\": h, \"rmse\": rmse, \"mae\": mae, \"n\": int(len(e))})\npd.DataFrame(table).to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nextra = {}\nrng = np.random.default_rng(SEED)\nfor h in HORIZONS:\n    en = fc_df.query(\"model=='naive' and horizon==@h\").sort_values(\"origin_date\")[\"error\"].values\n    em = fc_df.query(\"model=='model' and 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    d = en ** 2 - em ** 2\n    s, p, lrv = nw_dm(d, h)\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = s, p\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{'significant' if p < 0.05 else 'not_significant'}\"\n    # supplementary: moving-block bootstrap (block length max(h,2)) of RMSE_naive - RMSE_model\n    B, bl, n = 5000, max(h, 2), len(d)\n    diffs = []\n    for _ in range(B):\n        starts = rng.integers(0, n - bl + 1, size=int(np.ceil(n / bl)))\n        idx = np.concatenate([np.arange(s0, s0 + bl) for s0 in starts])[:n]\n        diffs.append(np.sqrt(np.mean(en[idx] ** 2)) - np.sqrt(np.mean(em[idx] ** 2)))\n    lo, hi = np.percentile(diffs, [2.5, 97.5])\n    extra[f\"h{h}\"] = {\"dm_lrv\": lrv, \"mean_loss_diff\": float(d.mean()),\n                      \"rmse_diff_naive_minus_model\": res[f\"rmse_naive_h{h}\"] - res[f\"rmse_model_h{h}\"],\n                      \"boot_rmse_diff_ci95\": [float(lo), float(hi)], \"boot_B\": B, \"boot_block\": bl,\n                      \"share_origins_model_smaller_sq_error\": float(np.mean(d > 0))}\n\n# (d) revisions: h=1 targets, current-vintage YoY vs first release\ng_cur = yoy(rs_current)\nt1 = fc_df.query(\"model=='naive' and horizon==1\")\ntm = pd.PeriodIndex(pd.to_datetime(t1[\"target_date\"]), freq=\"M\")\nrev = np.abs(g_cur.reindex(tm).values - actual.reindex(tm).values)\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(rev))\nextra[\"revision_by_target\"] = {str(k): float(v) for k, v in zip(tm, g_cur.reindex(tm).values - actual.reindex(tm).values)}\nextra[\"ar1_params\"] = ar_info\nextra[\"last_month_by_origin\"] = lastmonths\n\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nres[\"data_issues\"] = [\n    {\"issue\": \"Irregular RSAFS publication timing: last(V)=2025-08 at V=2025-10-31 and 2026-01 at V=2026-03-31 (two-month lag); V=2026-04-30 adds two months at once.\",\n     \"handling\": \"Targets defined as last(V)+h per task rule; the 2025-10-31 and 2026-03-31 origins therefore forecast months that are 2 and 4 months past the last calendar month.\"},\n    {\"issue\": \"Two h=1 and h=3 targets coincide across origins (e.g. 2026-01 is h=3 of 2025-12-31... see forecasts.csv) and h=3 errors overlap, inducing serial correlation.\",\n     \"handling\": \"DM long-run variance uses Bartlett kernel with truncation lag h-1 as specified.\"},\n    {\"issue\": \"Large level revision of RSAFS after the 2026-07-31 vintage (current levels ~4-5% below vintage levels); first_release.csv shows the break between targets 2026-07 and 2026-08.\",\n     \"handling\": \"YoY always computed within one vintage; h=3 actuals for targets 2026-08/2026-09 are post-revision first releases, used as given; estimand (d) reflects this revision.\"},\n    {\"issue\": \"PAYEMS benchmark revision visible in the 2026-02-28 vintage; PAYEMS 2025-10 first appears in the 2025-12-31 vintage.\",\n     \"handling\": \"PAYEMS not used in any forecast; documented only.\"},\n    {\"issue\": \"UMCSENT has 210 empty values before 1978-01.\",\n     \"handling\": \"UMCSENT not used in any forecast; documented only.\"},\n]\nres[\"n_input_rows\"] = dict(sorted(n_input_rows.items()))\nres[\"n_analysed\"] = int(fc_df.query(\"model=='model'\")[\"error\"].notna().sum())\nres[\"random_seed\"] = SEED\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=1)\nwith open(os.path.join(OUT, \"supplementary.json\"), \"w\") as fh:\n    json.dump(extra, fh, indent=1)\n\n# ---------------------------------------------------------------- figure\nfig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc_df.query(\"horizon==@h\")\n    for m, sty in [(\"naive\", \"s--\"), (\"model\", \"o-\"), (\"ar1\", \"^:\")]:\n        s = sub.query(\"model==@m\").sort_values(\"target_date\")\n        ax.plot(pd.to_datetime(s[\"target_date\"]), s[\"forecast\"], sty, label=m, alpha=.8)\n    s = sub.query(\"model=='naive'\").sort_values(\"target_date\")\n    ax.plot(pd.to_datetime(s[\"target_date\"]), s[\"actual_first_release\"], \"k-\", lw=2.2, label=\"first release\")\n    ax.set_title(f\"h = {h}: RSAFS YoY growth (%), real-time forecasts\")\n    ax.set_xlabel(\"target month\"); ax.grid(alpha=.3); ax.tick_params(axis=\"x\", rotation=45)\naxes[0].set_ylabel(\"percent\"); axes[0].legend()\nfig.tight_layout(); fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(pd.DataFrame(table).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.4f} p={res[f'dm_pvalue_h{h}']:.4f} {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets\", round(res[\"mean_abs_revision_h1_targets\"], 4))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/supplementary.json && cat out/forecasts.csv | grep -E \"naive|model$|,model,\" | head -0; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('out/forecasts.csv'); print(d.pivot_table(index=['horizon','origin_date','target_date','actual_first_release'],columns='model',values='forecast').round(2))\"","description":"Write and run analysis script"}}]}}70{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"b469c535-b726-4d7f-aa58-702ab4d810e0","timestamp":"2026-10-30T05:33:20.910Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"d2cbda17-4cad-4595-a643-0b178a58a4e8","keep":22,"tail":["845812d5e831599b3f84f6d402c5bdaeb946b342af8433627467cb6e9a674439","a8ab1160734602524e306dfb776f3d4adac31792a6fbca416676b509f6c43bd2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"918d3dac78a9cc10d102c3a6bd8fc04d019923a0e386a573a75502116d2a7248"}71{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"7458eff7-5f69-4860-bfae-b1884268e736","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}72{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}73{"parentUuid":"7458eff7-5f69-4860-bfae-b1884268e736","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsm3TqYhXJC56eTv2TL","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":7683,"cache_read_input_tokens":30414,"output_tokens":1068,"output_tokens_details":{"thinking_tokens":380},"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":7683},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3451,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsm3Cxyseo41optYMBM","requestRef":"b469c535-b726-4d7f-aa58-702ab4d810e0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9f1c3ea2-dcc8-48f1-a06e-d14989ba10d9","timestamp":"2026-10-30T05:33:25.400Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}74{"parentUuid":"9f1c3ea2-dcc8-48f1-a06e-d14989ba10d9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsm3TqYhXJC56eTv2TL","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QcUHeJC2PYjt2BzQqAkF1c","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    assert L.index.max() < pd.Period(V, \"M\") or L.index.max() <= pd.Period(V, \"M\")\\n''','''    assert L.index.max() < pd.Period(V, \"M\")  # last published month precedes the origin month\\n''')\ns=s.replace('''{\"issue\": \"Two h=1 and h=3 targets coincide across origins (e.g. 2026-01 is h=3 of 2025-12-31... see forecasts.csv) and h=3 errors overlap, inducing serial correlation.\",''','''{\"issue\": \"h=3 forecast errors of consecutive origins overlap (and some h=1 and h=3 target months coincide), inducing serial correlation in the loss differentials; only 10 origins are available.\",''')\ns=s.replace('''    extra[f\"h{h}\"] = {''','''    res[f\"boot_rmse_diff_ci95_lo_h{h}\"], res[f\"boot_rmse_diff_ci95_hi_h{h}\"] = float(lo), float(hi)\n    res[f\"share_origins_model_smaller_sq_error_h{h}\"] = float(np.mean(d > 0))\n    extra[f\"h{h}\"] = {''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r1.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; grep -E \"boot|share\" out/results.json","description":"Patch script, rerun twice, compare"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7683,"cache_read_input_tokens":30414,"output_tokens":1068,"output_tokens_details":{"thinking_tokens":380},"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":7683},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsm3Cxyseo41optYMBM","requestRef":"b469c535-b726-4d7f-aa58-702ab4d810e0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a2b32f3d-2885-4efc-ac65-08818c090ee5","timestamp":"2026-10-30T05:33:29.999Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}75{"parentUuid":"a2b32f3d-2885-4efc-ac65-08818c090ee5","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QcUHeJC2PYjt2BzQqAkF1c","type":"tool_result","content":"IDENTICAL\n \"boot_rmse_diff_ci95_lo_h1\": 0.2615951068646396,\n \"boot_rmse_diff_ci95_hi_h1\": 0.6987722437362641,\n \"share_origins_model_smaller_sq_error_h1\": 0.8,\n \"boot_rmse_diff_ci95_lo_h3\": -0.14490476470017666,\n \"boot_rmse_diff_ci95_hi_h3\": 0.6265360274461692,\n \"share_origins_model_smaller_sq_error_h3\": 0.6,","is_error":false}]},"uuid":"915c8319-beef-4647-8094-fab865f9a62b","timestamp":"2026-10-30T05:33:32.533Z","toolUseResult":{"stdout":"IDENTICAL\n \"boot_rmse_diff_ci95_lo_h1\": 0.2615951068646396,\n \"boot_rmse_diff_ci95_hi_h1\": 0.6987722437362641,\n \"share_origins_model_smaller_sq_error_h1\": 0.8,\n \"boot_rmse_diff_ci95_lo_h3\": -0.14490476470017666,\n \"boot_rmse_diff_ci95_hi_h3\": 0.6265360274461692,\n \"share_origins_model_smaller_sq_error_h3\": 0.6,","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a2b32f3d-2885-4efc-ac65-08818c090ee5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}76{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"b082dbe6bcd02e8bdfb73389ad2be4588e50bf98797fe9d1b8909cd57efd18d1","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01QcUHeJC2PYjt2BzQqAkF1c","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    assert L.index.max() < pd.Period(V, \"M\") or L.index.max() <= pd.Period(V, \"M\")\\n''','''    assert L.index.max() < pd.Period(V, \"M\")  # last published month precedes the origin month\\n''')\ns=s.replace('''{\"issue\": \"Two h=1 and h=3 targets coincide across origins (e.g. 2026-01 is h=3 of 2025-12-31... see forecasts.csv) and h=3 errors overlap, inducing serial correlation.\",''','''{\"issue\": \"h=3 forecast errors of consecutive origins overlap (and some h=1 and h=3 target months coincide), inducing serial correlation in the loss differentials; only 10 origins are available.\",''')\ns=s.replace('''    extra[f\"h{h}\"] = {''','''    res[f\"boot_rmse_diff_ci95_lo_h{h}\"], res[f\"boot_rmse_diff_ci95_hi_h{h}\"] = float(lo), float(hi)\n    res[f\"share_origins_model_smaller_sq_error_h{h}\"] = float(np.mean(d > 0))\n    extra[f\"h{h}\"] = {''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r1.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; grep -E \"boot|share\" out/results.json","description":"Patch script, rerun twice, compare"}}]}}77{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"0a6d2d63-7f14-487e-9a52-5a475f6ba177","timestamp":"2026-10-30T05:33:32.537Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"b469c535-b726-4d7f-aa58-702ab4d810e0","keep":24,"tail":["b082dbe6bcd02e8bdfb73389ad2be4588e50bf98797fe9d1b8909cd57efd18d1","3df3d5a37e0e66f003e45dc16b0d1ca17eaed2d3b2fac20b340997d2e9541b3b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5347eb2be1199689759599d89f0bf2dc2f125608d1ae4eb496aaed814b273232"}78{"parentUuid":"915c8319-beef-4647-8094-fab865f9a62b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmuAHxgkskRDmzAwsi","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":1236,"cache_read_input_tokens":38097,"output_tokens":1493,"output_tokens_details":{"thinking_tokens":71},"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":1236},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":619,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsmtuRYzoPZv5pcxVDG","requestRef":"0a6d2d63-7f14-487e-9a52-5a475f6ba177","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"74057b50-3db5-48be-ab2d-a88b8a946e25","timestamp":"2026-10-30T05:33:34.169Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}79{"parentUuid":"74057b50-3db5-48be-ab2d-a88b8a946e25","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmuAHxgkskRDmzAwsi","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PVkcZECafPWzpVkTxBeQna","name":"Bash","input":{"command":"rm -rf /tmp/clean && mkdir /tmp/clean && cp -r data out /tmp/clean/ && cd /tmp/clean && rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /Users/simon-pierreboucher/wp29/runs/RT0009/out/results.json && echo CLEAN_IDENTICAL; cd /Users/simon-pierreboucher/wp29/runs/RT0009 && ~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd, numpy as np, json, statsmodels.api as sm\nfrom scipy.stats import norm\nr=json.load(open('out/results.json')); f=pd.read_csv('out/forecasts.csv')\nprint('rows',len(f), f.groupby(['model','horizon']).size().unique())\nprint('chronology ok', (f.vintage_used<=f.origin_date).all() and (pd.to_datetime(f.origin_date)<pd.to_datetime(f.target_date)).all())\nfr=pd.read_csv('data/first_release.csv').set_index('target_month').yoy_first_release\nprint('actuals match', np.allclose(f.actual_first_release, fr.loc[f.target_date].values))\n# independent DM\nfor h in [1,3]:\n    a=f[(f.horizon==h)].pivot(index='origin_date',columns='model',values='forecast'); y=f[(f.horizon==h)&(f.model=='naive')].set_index('origin_date').actual_first_release\n    d=(y-a.naive)**2-(y-a.model)**2; u=d-d.mean(); n=len(d)\n    g=lambda k:(u.values[k:]*u.values[:n-k]).sum()/n\n    lrv=g(0)+ (2*(2/3)*g(1)+2*(1/3)*g(2) if h==3 else 0)\n    s=d.mean()/np.sqrt(lrv/n); print(h,'DM',round(s,6),round(r[f'dm_stat_h{h}'],6),'p',round(2*norm.sf(abs(s)),6),round(r[f'dm_pvalue_h{h}'],6))\n    print(' rmse naive', np.sqrt(((y-a.naive)**2).mean()), r[f'rmse_naive_h{h}'])\n# AR1 check with statsmodels for last origin\nv=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',index_col=0,parse_dates=True).iloc[:,0]\ng=100*np.log(v/v.shift(12)); df=pd.DataFrame({'y':g,'x':g.shift(1)}).loc['1993-02':].dropna()\nprint(sm.OLS(df.y,sm.add_constant(df.x)).fit().params.values, len(df))\n# revision check\nc=pd.read_csv('data/RSAFS_current.csv',index_col=0,parse_dates=True).RSAFS; gc=100*np.log(c/c.shift(12))\nt=f[(f.horizon==1)&(f.model=='naive')].target_date\nprint('rev', np.mean(np.abs(gc.loc[t].values-fr.loc[t].values)), r['mean_abs_revision_h1_targets'])\nprint('rmse>0', all(r[k]>0 for k in r if k.startswith('rmse')), 'mae<=rmse', all(r['mae'+k[4:]]<=r[k] for k in r if k.startswith('rmse')))\nprint('boot CI contains point', [r[f'boot_rmse_diff_ci95_lo_h{h}']<=r[f'rmse_naive_h{h}']-r[f'rmse_model_h{h}']<=r[f'boot_rmse_diff_ci95_hi_h{h}'] for h in [1,3]])\nEOF","description":"Clean rerun and independent consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1236,"cache_read_input_tokens":38097,"output_tokens":1493,"output_tokens_details":{"thinking_tokens":71},"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":1236},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsmtuRYzoPZv5pcxVDG","requestRef":"0a6d2d63-7f14-487e-9a52-5a475f6ba177","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"50ea6b7d-084d-4c64-b5f6-22e5081dadfb","timestamp":"2026-10-30T05:33:43.914Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}80{"parentUuid":"50ea6b7d-084d-4c64-b5f6-22e5081dadfb","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PVkcZECafPWzpVkTxBeQna","type":"tool_result","content":"CLEAN_IDENTICAL\nrows 80 [10]\nchronology ok False\nactuals match True\n1 DM 2.428978 2.428978 p 0.015141 0.015141\n rmse naive 0.996874361153601 0.9968743518607954\n3 DM 1.546577 1.546577 p 0.121965 0.121965\n rmse naive 1.4200403019751233 1.4200403737520462\n[0.72680241 0.83987147] 401\nrev 0.5482198028388884 0.5482198028389015\nrmse>0 True mae<=rmse True\nboot CI contains point [True, True]","is_error":false}]},"uuid":"caa9e905-080b-4f72-a0d1-98cb775adc8a","timestamp":"2026-10-30T05:33:46.178Z","toolUseResult":{"stdout":"CLEAN_IDENTICAL\nrows 80 [10]\nchronology ok False\nactuals match True\n1 DM 2.428978 2.428978 p 0.015141 0.015141\n rmse naive 0.996874361153601 0.9968743518607954\n3 DM 1.546577 1.546577 p 0.121965 0.121965\n rmse naive 1.4200403019751233 1.4200403737520462\n[0.72680241 0.83987147] 401\nrev 0.5482198028388884 0.5482198028389015\nrmse>0 True mae<=rmse True\nboot CI contains point [True, True]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"50ea6b7d-084d-4c64-b5f6-22e5081dadfb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}81{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"390a79f878bb3d6ce42f1884e1fa457076bb6951a7c0b787cbf98f1dfe8a3d7f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS3QcKEAgTGAI4AUIIdGhpbmtpbmcSDF9/QqZP68oCPuOSLBoMHEZ1w4CX8MN609/qIjCVjlDxdHZcxcsEKzdPZOtp6e09leLfYr9JA+RFLZL1eprDpWb7yUY2p01jjtt1PZkq+gaa+6qNkCkgeHeGfIqIJG/gpks4pPi9yvrKrB0dDxhUm+fA75gsulLxbgIjP31Mg6vJap6HlhvQKxfUu3n/HOZoNfkoEfW4Pku8RnqqfKnQ7yqMGCEPfh4BWJy98RcC974ktNt6KwFdt/6xbXeRCQGfW+7MGFX0ywSwNARrFin8gOl5AeMdjRfrj3qP3UCBc5V2cRF0MlDbHBsk5ekbX8EllSELs6ZS4JYdIGqRSqB/V16P7B+osKQDcDLZlqC1KS4LHnpHJafIFTR3uFM61YoIvEJWLivBsOKGUG2uuk0dwwvb8jCx7bFrRos7K3pK724T6hUlBvw8npfGfXyEEwHX3nSQZ4tWoJtKq9h6Ny3xg51rzzcby0jLQDMD8KZwS+69P+nT3wsl5/dfk0UPvekB7AN0PrNq7Dgs2OE01BMDJBY7w+ZffDh2CEUSK2vTB+fpc1KE0qxnwNric5keEZsuMXOMvKp8a9xtJG7pW1r0nfdALpVwiIcBFRjV946CsMozejhx5qMzHstf4gg5tH2YBT5sE0ONbJifPte2r4EZVxOW4vcLKc76AJDZeqcx2pmbpW47yHluWgOi9hpgovRiP8sCT1N2Q7f+8ciNAxBWl/nFmTykKRxSUQmk7R2CUqC+//zPh/CD+Qg767VGi9euFykXrnQb6s+qKzmVZDtKRHWVDJVX5Vcq8selHsYLA168mAXFY6IBNgI5pmDBDD8B22fd0sRPhafnYTp5dnQA7y485sTYuEuWVglilPYKaPwSrGVozpE9Wny+wP4JJXYeFSTYNQeZ1Gqze2gaxecDf8d6dySkae0GLbkI6hkmySzJS9WfJNRLAzDJ60T6RPBw8i7KOgMz3wDQboqm2aG4321Ok7nGwyPbLN4BU4gvrcSBUKTyiL9DEKM/n55ljpRGItmyjPcv2v4KKvcQVP38aXWUJN9GWwVQTPP8/+y+fNJYE/izkGY7fnMnCLbAL8IUCGiFsC4QzueSP2k4pTK5jEe+iLMGttrvLMlEoxv6CY1MfC7VqArz9sEDNcgZKf5o3YIMcYi6giAnkVEXZaTcqdfzXOmjECPXpCcDC+t3MP0RTw5YCDoYvk4uW5ElhpiUh81gygMGLdplNktPDTHxkec08c1lleh6U5NOjkrIW5geNnB0ivI4fDiTThZ5hI02vr8YUGIL6XaJBxgB"},{"type":"tool_use","id":"toolu_01PVkcZECafPWzpVkTxBeQna","name":"Bash","input":{"command":"rm -rf /tmp/clean && mkdir /tmp/clean && cp -r data out /tmp/clean/ && cd /tmp/clean && rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /Users/simon-pierreboucher/wp29/runs/RT0009/out/results.json && echo CLEAN_IDENTICAL; cd /Users/simon-pierreboucher/wp29/runs/RT0009 && ~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd, numpy as np, json, statsmodels.api as sm\nfrom scipy.stats import norm\nr=json.load(open('out/results.json')); f=pd.read_csv('out/forecasts.csv')\nprint('rows',len(f), f.groupby(['model','horizon']).size().unique())\nprint('chronology ok', (f.vintage_used<=f.origin_date).all() and (pd.to_datetime(f.origin_date)<pd.to_datetime(f.target_date)).all())\nfr=pd.read_csv('data/first_release.csv').set_index('target_month').yoy_first_release\nprint('actuals match', np.allclose(f.actual_first_release, fr.loc[f.target_date].values))\n# independent DM\nfor h in [1,3]:\n    a=f[(f.horizon==h)].pivot(index='origin_date',columns='model',values='forecast'); y=f[(f.horizon==h)&(f.model=='naive')].set_index('origin_date').actual_first_release\n    d=(y-a.naive)**2-(y-a.model)**2; u=d-d.mean(); n=len(d)\n    g=lambda k:(u.values[k:]*u.values[:n-k]).sum()/n\n    lrv=g(0)+ (2*(2/3)*g(1)+2*(1/3)*g(2) if h==3 else 0)\n    s=d.mean()/np.sqrt(lrv/n); print(h,'DM',round(s,6),round(r[f'dm_stat_h{h}'],6),'p',round(2*norm.sf(abs(s)),6),round(r[f'dm_pvalue_h{h}'],6))\n    print(' rmse naive', np.sqrt(((y-a.naive)**2).mean()), r[f'rmse_naive_h{h}'])\n# AR1 check with statsmodels for last origin\nv=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',index_col=0,parse_dates=True).iloc[:,0]\ng=100*np.log(v/v.shift(12)); df=pd.DataFrame({'y':g,'x':g.shift(1)}).loc['1993-02':].dropna()\nprint(sm.OLS(df.y,sm.add_constant(df.x)).fit().params.values, len(df))\n# revision check\nc=pd.read_csv('data/RSAFS_current.csv',index_col=0,parse_dates=True).RSAFS; gc=100*np.log(c/c.shift(12))\nt=f[(f.horizon==1)&(f.model=='naive')].target_date\nprint('rev', np.mean(np.abs(gc.loc[t].values-fr.loc[t].values)), r['mean_abs_revision_h1_targets'])\nprint('rmse>0', all(r[k]>0 for k in r if k.startswith('rmse')), 'mae<=rmse', all(r['mae'+k[4:]]<=r[k] for k in r if k.startswith('rmse')))\nprint('boot CI contains point', [r[f'boot_rmse_diff_ci95_lo_h{h}']<=r[f'rmse_naive_h{h}']-r[f'rmse_model_h{h}']<=r[f'boot_rmse_diff_ci95_hi_h{h}'] for h in [1,3]])\nEOF","description":"Clean rerun and independent consistency checks"}}]}}82{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"b9dfb75e-d004-4421-a4f1-368a48592b74","timestamp":"2026-10-30T05:33:46.182Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"0a6d2d63-7f14-487e-9a52-5a475f6ba177","keep":26,"tail":["390a79f878bb3d6ce42f1884e1fa457076bb6951a7c0b787cbf98f1dfe8a3d7f","9d7f0913e488103e35d4e91dc58662820d15c01082d6dea85c9b2fd24533f4fd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9b92f40748533c97eb9b73d83053d3edd14c16d495095a3db9e731078184d93f"}83{"parentUuid":"caa9e905-080b-4f72-a0d1-98cb775adc8a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnuSSpUDtr6WwgyRAt","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":1702,"cache_read_input_tokens":39333,"output_tokens":486,"output_tokens_details":{"thinking_tokens":356},"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":1702},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2952,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsnuFYBSVr7RCAabgiB","requestRef":"b9dfb75e-d004-4421-a4f1-368a48592b74","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"abd4f409-61de-4c94-9a4a-feb8a017ee35","timestamp":"2026-10-30T05:33:50.842Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}84{"parentUuid":"abd4f409-61de-4c94-9a4a-feb8a017ee35","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnuSSpUDtr6WwgyRAt","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016ZFrobSzKYDYQVBzmSw2Bp","name":"Bash","input":{"command":"grep -n -B3 -A25 \"forecasts_csv_chronology\" ~/wp29/gates/pgar_gate.py | sed -n 1,60p","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":1702,"cache_read_input_tokens":39333,"output_tokens":486,"output_tokens_details":{"thinking_tokens":356},"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":1702},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsnuFYBSVr7RCAabgiB","requestRef":"b9dfb75e-d004-4421-a4f1-368a48592b74","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7221bcf0-9cee-4b3c-afcc-5d0e9dadef61","timestamp":"2026-10-30T05:33:51.589Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}85{"parentUuid":"7221bcf0-9cee-4b3c-afcc-5d0e9dadef61","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016ZFrobSzKYDYQVBzmSw2Bp","type":"tool_result","content":"171-        for a, b in spec.get(\"chronology_pairs\", []):\n172-            da, db = _parse_date(res.get(a)), _parse_date(res.get(b))\n173-            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)}\")\n174:    if \"forecasts_csv_chronology\" in fam:\n175-        fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n176-        try:\n177-            rows = list(csv.DictReader(open(fp, newline=\"\")))\n178-            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\"])))\n179-            add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n180-        except Exception as e:  # noqa: BLE001\n181-            add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n182-    # 8. reproducibility\n183-    if do_repro and os.path.isfile(os.path.join(ws, \"out\", \"analysis.py\")) and isinstance(res, dict) and res:\n184-        py = python or sys.executable\n185-        tmp = tempfile.mkdtemp(prefix=\"pgar_repro_\")\n186-        try:\n187-            shutil.copytree(os.path.join(ws, \"data\"), os.path.join(tmp, \"data\"))\n188-            shutil.copytree(os.path.join(ws, \"out\"), os.path.join(tmp, \"out\"), ignore=shutil.ignore_patterns(\"results.json\", \"state\", \"review\"))\n189-            for extra in (\"TASK.md\", \"gate_spec.json\"):\n190-                if os.path.exists(os.path.join(ws, extra)):\n191-                    shutil.copy(os.path.join(ws, extra), tmp)\n192-            t0 = datetime.datetime.now()\n193-            proc = subprocess.run([py, \"out/analysis.py\"], cwd=tmp, capture_output=True, text=True, timeout=int(spec.get(\"analysis_timeout_s\", 300)))\n194-            dur = (datetime.datetime.now() - t0).total_seconds()\n195-            new, nerr = _load_json(os.path.join(tmp, \"out\", \"results.json\"))\n196-            if proc.returncode != 0:\n197-                add(\"reproducibility\", False, f\"analysis.py exit {proc.returncode} after {dur:.1f}s; stderr tail: {proc.stderr[-600:]}\")\n198-            elif not isinstance(new, dict):\n199-                add(\"reproducibility\", False, f\"analysis.py did not regenerate out/results.json ({nerr})\")","is_error":false}]},"uuid":"31862ea5-bfd6-4b36-9158-0e359614d2fc","timestamp":"2026-10-30T05:33:51.631Z","toolUseResult":{"stdout":"171-        for a, b in spec.get(\"chronology_pairs\", []):\n172-            da, db = _parse_date(res.get(a)), _parse_date(res.get(b))\n173-            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)}\")\n174:    if \"forecasts_csv_chronology\" in fam:\n175-        fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n176-        try:\n177-            rows = list(csv.DictReader(open(fp, newline=\"\")))\n178-            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\"])))\n179-            add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n180-        except Exception as e:  # noqa: BLE001\n181-            add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n182-    # 8. reproducibility\n183-    if do_repro and os.path.isfile(os.path.join(ws, \"out\", \"analysis.py\")) and isinstance(res, dict) and res:\n184-        py = python or sys.executable\n185-        tmp = tempfile.mkdtemp(prefix=\"pgar_repro_\")\n186-        try:\n187-            shutil.copytree(os.path.join(ws, \"data\"), os.path.join(tmp, \"data\"))\n188-            shutil.copytree(os.path.join(ws, \"out\"), os.path.join(tmp, \"out\"), ignore=shutil.ignore_patterns(\"results.json\", \"state\", \"review\"))\n189-            for extra in (\"TASK.md\", \"gate_spec.json\"):\n190-                if os.path.exists(os.path.join(ws, extra)):\n191-                    shutil.copy(os.path.join(ws, extra), tmp)\n192-            t0 = datetime.datetime.now()\n193-            proc = subprocess.run([py, \"out/analysis.py\"], cwd=tmp, capture_output=True, text=True, timeout=int(spec.get(\"analysis_timeout_s\", 300)))\n194-            dur = (datetime.datetime.now() - t0).total_seconds()\n195-            new, nerr = _load_json(os.path.join(tmp, \"out\", \"results.json\"))\n196-            if proc.returncode != 0:\n197-                add(\"reproducibility\", False, f\"analysis.py exit {proc.returncode} after {dur:.1f}s; stderr tail: {proc.stderr[-600:]}\")\n198-            elif not isinstance(new, dict):\n199-                add(\"reproducibility\", False, f\"analysis.py did not regenerate out/results.json ({nerr})\")","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"7221bcf0-9cee-4b3c-afcc-5d0e9dadef61","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}86{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"1284e0edeb9bd29ecf74a82631ae88a617c495f967a1bc3e1624e2efab669af0","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016ZFrobSzKYDYQVBzmSw2Bp","name":"Bash","input":{"command":"grep -n -B3 -A25 \"forecasts_csv_chronology\" ~/wp29/gates/pgar_gate.py | sed -n 1,60p","description":"Inspect gate chronology check"}}]}}87{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"32b2bf3a-cefa-48f1-8f08-71c81b3a89a5","timestamp":"2026-10-30T05:33:51.634Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"b9dfb75e-d004-4421-a4f1-368a48592b74","keep":28,"tail":["1284e0edeb9bd29ecf74a82631ae88a617c495f967a1bc3e1624e2efab669af0","6cd2edb0a7a3a4f7b814ed35d3cdaa957cf5072fdce8fdba11c38087836a5d7a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"354112c6c84ab2d8d8e75b923820b8b1af7a5101c4bbfe73958489301b3be72e"}88{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"31862ea5-bfd6-4b36-9158-0e359614d2fc","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}89{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}90{"parentUuid":"31862ea5-bfd6-4b36-9158-0e359614d2fc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoJs6fqAcmQyFtLHHg","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":1460,"cache_read_input_tokens":41035,"output_tokens":1476,"output_tokens_details":{"thinking_tokens":1354},"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":1460},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":14087,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsoJaUnzZSxgqYXUY76","requestRef":"32b2bf3a-cefa-48f1-8f08-71c81b3a89a5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f8e85ddc-4bed-4dee-a9dd-c3082ca63119","timestamp":"2026-10-30T05:34:06.813Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}91{"parentUuid":"f8e85ddc-4bed-4dee-a9dd-c3082ca63119","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoJs6fqAcmQyFtLHHg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VRqt2xRoea14rrUcrGH3DA","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -30","description":"Run the gate (P4 first run)"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1460,"cache_read_input_tokens":41035,"output_tokens":1476,"output_tokens_details":{"thinking_tokens":1354},"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":1460},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsoJaUnzZSxgqYXUY76","requestRef":"32b2bf3a-cefa-48f1-8f08-71c81b3a89a5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"afbb1924-860d-4056-bdf0-a96123a75bf5","timestamp":"2026-10-30T05:34:07.548Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}92{"parentUuid":"afbb1924-860d-4056-bdf0-a96123a75bf5","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VRqt2xRoea14rrUcrGH3DA","type":"tool_result","content":"  [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: 2 steps consistent\n  [ok] positive:rmse_naive_h1: 0.9968743518607954\n  [ok] positive:rmse_naive_h3: 1.4200403737520462\n  [ok] positive:rmse_snaive_h1: 1.6745428991342943\n  [ok] positive:rmse_snaive_h3: 1.3160788989552372\n  [ok] positive:rmse_ar1_h1: 0.9405244111185227\n  [ok] positive:rmse_ar1_h3: 1.1871178147422958\n  [ok] positive:rmse_model_h1: 0.5502977033274435\n  [ok] positive:rmse_model_h3: 1.1422197516272885\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 1.1s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0009/out/state/gate_receipts/20261030T053408.762973Z.json","is_error":false}]},"uuid":"cb926b09-9f8e-432a-a4f8-bd154498841a","timestamp":"2026-10-30T05:34:08.771Z","toolUseResult":{"stdout":"  [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: 2 steps consistent\n  [ok] positive:rmse_naive_h1: 0.9968743518607954\n  [ok] positive:rmse_naive_h3: 1.4200403737520462\n  [ok] positive:rmse_snaive_h1: 1.6745428991342943\n  [ok] positive:rmse_snaive_h3: 1.3160788989552372\n  [ok] positive:rmse_ar1_h1: 0.9405244111185227\n  [ok] positive:rmse_ar1_h3: 1.1871178147422958\n  [ok] positive:rmse_model_h1: 0.5502977033274435\n  [ok] positive:rmse_model_h3: 1.1422197516272885\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 1.1s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0009/out/state/gate_receipts/20261030T053408.762973Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"afbb1924-860d-4056-bdf0-a96123a75bf5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}93{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"e8db9af22c852b3d6a0749b94b21e887da566a9e0f3da56fe6cddd4ad519c6fa","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01VRqt2xRoea14rrUcrGH3DA","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -30","description":"Run the gate (P4 first run)"}}]}}94{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"d98f32b7-d401-4f3e-9147-32dbeaae7ce5","timestamp":"2026-10-30T05:34:08.774Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"32b2bf3a-cefa-48f1-8f08-71c81b3a89a5","keep":30,"tail":["e8db9af22c852b3d6a0749b94b21e887da566a9e0f3da56fe6cddd4ad519c6fa","ed04d6386a8ea75e07267855d67231864e2d43246b885a4ab2d414276c350ee6"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c3bf1d4b8ad801620d6c45a80ad1bfcf5edd6ef979c277b83ac1268fb49083e5"}95{"parentUuid":"cb926b09-9f8e-432a-a4f8-bd154498841a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspa6faL1csUAgPWQkD","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":2234,"cache_read_input_tokens":42495,"output_tokens":2190,"output_tokens_details":{"thinking_tokens":74},"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":2234},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":572,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXspZs26o1v6EMFwivt9","requestRef":"d98f32b7-d401-4f3e-9147-32dbeaae7ce5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ed84b60b-d532-45e8-b459-743538add80b","timestamp":"2026-10-30T05:34:10.423Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}96{"parentUuid":"ed84b60b-d532-45e8-b459-743538add80b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspa6faL1csUAgPWQkD","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WhRtLBfwjHdT7E5cHV2tCi","name":"Bash","input":{"command":"ls out/state/gate_receipts/; cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n\n| # | check | outcome |\n|---|---|---|\n| 1 | Re-run `out/analysis.py` twice in workspace; `cmp` results.json | PASS (byte-identical) |\n| 2 | Clean-state rerun in /tmp/clean (outputs deleted first); cmp results.json | PASS (byte-identical) |\n| 3 | forecasts.csv has 80 rows, 10 per (model,horizon) | PASS |\n| 4 | actual_first_release equals first_release.csv yoy for each target_date | PASS |\n| 5 | vintage_used <= origin_date for all rows; vintage_used == origin_date | PASS |\n| 6 | Target month > last(V) (asserted in script: last(V) < month(V), target = last(V)+h) | PASS |\n| 7 | origin_date < target_date (gate rule, comparing month-START date of target) | FAIL for 40/40 h=1 rows — see note below |\n| 8 | Independent recomputation of DM statistics/p-values (h=1: 2.428978/0.015141; h=3: 1.546577/0.121965) | PASS (match to 6 dp) |\n| 9 | AR(1) params at origin 2026-07-31 re-estimated with statsmodels OLS (0.72680, 0.83987, n=401) | PASS |\n| 10 | mean_abs_revision_h1_targets recomputed independently (0.548220) | PASS |\n| 11 | All RMSE > 0; MAE <= RMSE for every model/horizon | PASS |\n| 12 | Bootstrap 95% intervals for RMSE_naive − RMSE_model contain the point estimate | PASS |\n| 13 | Exclusion ledger: 80 − 0 = 80 = 4 × n_analysed(20) | PASS |\n| 14 | Magnitudes: model RMSE vs naive baseline plausible (0.55 vs 1.00 at h=1; 1.14 vs 1.42 at h=3), AR(1) close to naive as expected given phi≈0.84 | PASS |\n| 15 | Gate run 1 (20261030T053408.762973Z): all key/type/positivity/reproducibility checks ok; failures = report/claims/phase ledger not yet written (expected at this stage) + forecasts_chronology (40 rows) | partial |\n\n## Note on check 7 (unresolvable conflict between TASK.md and the gate rule)\nTASK.md requires `target_date` in YYYY-MM-01 format and defines the target as last(V)+h, where last(V) is the last month in the vintage dated V. Because a month-end vintage always contains at most the month before V, the h=1 target month is at latest the month containing V, so its first day (YYYY-MM-01) is always on or before the month-end origin date (e.g. origin 2026-05-31, last 2026-04, target 2026-05-01). The gate's literal rule `origin_date < target_date` therefore cannot hold for any h=1 row under the TASK.md definitions. The substantive information rule — the target month's value is not yet published in the vintage used — holds for all 80 rows (check 6). I keep the TASK.md format (authoritative) rather than relabelling target dates to make the gate pass.\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; ph=json.load(open(p))\nph['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of all 23 data files computed and match README/bundle\",\"rows/cols/date ranges/missing/duplicates/gaps recorded in data_audit.md\",\"exclusions.csv written; ledger sums verified (80-0=80)\",\"availability-rule review: RSAFS_current only for (d); PAYEMS/UMCSENT unused in forecasts\"],\"notes\":\"Irregular publication timing, post-2026-07 level revision documented.\"}\nph['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) computed per vintage and evaluated vs first release (rmse/mae_*_h1/h3 in results.json)\",\"AR(1) params cross-checked with statsmodels\"],\"notes\":\"\"}\nph['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png, supplementary.json\",\"seed 20261030 recorded (bootstrap only)\",\"model specification fixed a priori, no alternatives tried\"],\"notes\":\"Model BE-RWD.\"}\nph['P4']={\"status\":\"blocked\",\"checks\":[\"clean-state rerun: results.json byte-identical\",\"checks.md items 1-14 PASS\",\"independent DM/revision recomputation PASS\",\"gate run receipt out/state/gate_receipts/20261030T053408.762973Z.json: passed=false (report/claims not yet written; forecasts_chronology 40 rows)\"],\"notes\":\"Blocked only by forecasts_chronology gate rule (origin_date < target_date) which is incompatible with TASK.md's YYYY-MM-01 target_date format for every h=1 target; see checks.md. All substantive checks pass.\"}\njson.dump(ph,open(p,'w'),indent=1)\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30: P1 passed (audit, exclusions). Decision: own model = base-effect random walk with drift (univariate, no estimation), fixed before evaluation.\n- 2026-10-30: P2/P3 passed (baselines + model in out/analysis.py; seed 20261030).\n- 2026-10-30: P4 gate run 1: forecasts_chronology fails for all 40 h=1 rows because TASK.md requires target_date=YYYY-MM-01 of target month, which precedes the month-end origin. Decision: keep TASK.md format, mark P4 blocked by this rule, report honestly. Proceeding to P5 per stopping rule (write all files).\nEOF","description":"Write checks, update phases and log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2234,"cache_read_input_tokens":42495,"output_tokens":2190,"output_tokens_details":{"thinking_tokens":74},"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":2234},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXspZs26o1v6EMFwivt9","requestRef":"d98f32b7-d401-4f3e-9147-32dbeaae7ce5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a63044ff-c005-4f08-8547-0c57c8629de7","timestamp":"2026-10-30T05:34:27.900Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}97{"parentUuid":"a63044ff-c005-4f08-8547-0c57c8629de7","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WhRtLBfwjHdT7E5cHV2tCi","type":"tool_result","content":"20261030T053408.762973Z.json","is_error":false}]},"uuid":"7a0fa54e-dbb5-4539-8876-ae47335733d2","timestamp":"2026-10-30T05:34:27.974Z","toolUseResult":{"stdout":"20261030T053408.762973Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a63044ff-c005-4f08-8547-0c57c8629de7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}98{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"436f75ba33ed879bc68e9c46a2db99d7c7ba9e94ab290d41e6b668317d7a027d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WhRtLBfwjHdT7E5cHV2tCi","name":"Bash","input":{"command":"ls out/state/gate_receipts/; cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n\n| # | check | outcome |\n|---|---|---|\n| 1 | Re-run `out/analysis.py` twice in workspace; `cmp` results.json | PASS (byte-identical) |\n| 2 | Clean-state rerun in /tmp/clean (outputs deleted first); cmp results.json | PASS (byte-identical) |\n| 3 | forecasts.csv has 80 rows, 10 per (model,horizon) | PASS |\n| 4 | actual_first_release equals first_release.csv yoy for each target_date | PASS |\n| 5 | vintage_used <= origin_date for all rows; vintage_used == origin_date | PASS |\n| 6 | Target month > last(V) (asserted in script: last(V) < month(V), target = last(V)+h) | PASS |\n| 7 | origin_date < target_date (gate rule, comparing month-START date of target) | FAIL for 40/40 h=1 rows — see note below |\n| 8 | Independent recomputation of DM statistics/p-values (h=1: 2.428978/0.015141; h=3: 1.546577/0.121965) | PASS (match to 6 dp) |\n| 9 | AR(1) params at origin 2026-07-31 re-estimated with statsmodels OLS (0.72680, 0.83987, n=401) | PASS |\n| 10 | mean_abs_revision_h1_targets recomputed independently (0.548220) | PASS |\n| 11 | All RMSE > 0; MAE <= RMSE for every model/horizon | PASS |\n| 12 | Bootstrap 95% intervals for RMSE_naive − RMSE_model contain the point estimate | PASS |\n| 13 | Exclusion ledger: 80 − 0 = 80 = 4 × n_analysed(20) | PASS |\n| 14 | Magnitudes: model RMSE vs naive baseline plausible (0.55 vs 1.00 at h=1; 1.14 vs 1.42 at h=3), AR(1) close to naive as expected given phi≈0.84 | PASS |\n| 15 | Gate run 1 (20261030T053408.762973Z): all key/type/positivity/reproducibility checks ok; failures = report/claims/phase ledger not yet written (expected at this stage) + forecasts_chronology (40 rows) | partial |\n\n## Note on check 7 (unresolvable conflict between TASK.md and the gate rule)\nTASK.md requires `target_date` in YYYY-MM-01 format and defines the target as last(V)+h, where last(V) is the last month in the vintage dated V. Because a month-end vintage always contains at most the month before V, the h=1 target month is at latest the month containing V, so its first day (YYYY-MM-01) is always on or before the month-end origin date (e.g. origin 2026-05-31, last 2026-04, target 2026-05-01). The gate's literal rule `origin_date < target_date` therefore cannot hold for any h=1 row under the TASK.md definitions. The substantive information rule — the target month's value is not yet published in the vintage used — holds for all 80 rows (check 6). I keep the TASK.md format (authoritative) rather than relabelling target dates to make the gate pass.\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; ph=json.load(open(p))\nph['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of all 23 data files computed and match README/bundle\",\"rows/cols/date ranges/missing/duplicates/gaps recorded in data_audit.md\",\"exclusions.csv written; ledger sums verified (80-0=80)\",\"availability-rule review: RSAFS_current only for (d); PAYEMS/UMCSENT unused in forecasts\"],\"notes\":\"Irregular publication timing, post-2026-07 level revision documented.\"}\nph['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) computed per vintage and evaluated vs first release (rmse/mae_*_h1/h3 in results.json)\",\"AR(1) params cross-checked with statsmodels\"],\"notes\":\"\"}\nph['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png, supplementary.json\",\"seed 20261030 recorded (bootstrap only)\",\"model specification fixed a priori, no alternatives tried\"],\"notes\":\"Model BE-RWD.\"}\nph['P4']={\"status\":\"blocked\",\"checks\":[\"clean-state rerun: results.json byte-identical\",\"checks.md items 1-14 PASS\",\"independent DM/revision recomputation PASS\",\"gate run receipt out/state/gate_receipts/20261030T053408.762973Z.json: passed=false (report/claims not yet written; forecasts_chronology 40 rows)\"],\"notes\":\"Blocked only by forecasts_chronology gate rule (origin_date < target_date) which is incompatible with TASK.md's YYYY-MM-01 target_date format for every h=1 target; see checks.md. All substantive checks pass.\"}\njson.dump(ph,open(p,'w'),indent=1)\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30: P1 passed (audit, exclusions). Decision: own model = base-effect random walk with drift (univariate, no estimation), fixed before evaluation.\n- 2026-10-30: P2/P3 passed (baselines + model in out/analysis.py; seed 20261030).\n- 2026-10-30: P4 gate run 1: forecasts_chronology fails for all 40 h=1 rows because TASK.md requires target_date=YYYY-MM-01 of target month, which precedes the month-end origin. Decision: keep TASK.md format, mark P4 blocked by this rule, report honestly. Proceeding to P5 per stopping rule (write all files).\nEOF","description":"Write checks, update phases and log"}}]}}99{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"ddaf2c3d-501c-478e-8660-baee4deeaa47","timestamp":"2026-10-30T05:34:27.978Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"d98f32b7-d401-4f3e-9147-32dbeaae7ce5","keep":32,"tail":["436f75ba33ed879bc68e9c46a2db99d7c7ba9e94ab290d41e6b668317d7a027d","596141c29617965557573c38d820b1a706da09d213c9963eb7c353789620740c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"653e8072e75897f482a38fe1640e5a8ca23442d432580c2f82b1f8a945c787bb"}100{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"7a0fa54e-dbb5-4539-8876-ae47335733d2","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}101{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}102{"parentUuid":"7a0fa54e-dbb5-4539-8876-ae47335733d2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqzCmsinWSh6qyLhkT","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":2208,"cache_read_input_tokens":44729,"output_tokens":164,"output_tokens_details":{"thinking_tokens":19},"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":2208},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":453,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsqyw9dkvDxxDFMe9SB","requestRef":"ddaf2c3d-501c-478e-8660-baee4deeaa47","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"42118d09-cd29-4ed1-a178-fa447f8a1a7d","timestamp":"2026-10-30T05:34:29.158Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}103{"parentUuid":"42118d09-cd29-4ed1-a178-fa447f8a1a7d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqzCmsinWSh6qyLhkT","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TrmiGAjL5QTVYXmXdffXrV","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n  if isinstance(v,float): print(k, round(v,4))\n\"","description":"Print numeric results rounded"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2208,"cache_read_input_tokens":44729,"output_tokens":164,"output_tokens_details":{"thinking_tokens":19},"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":2208},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsqyw9dkvDxxDFMe9SB","requestRef":"ddaf2c3d-501c-478e-8660-baee4deeaa47","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"41f0c39f-fa7d-41e0-a8fa-388e3d91d102","timestamp":"2026-10-30T05:34:29.645Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}104{"parentUuid":"41f0c39f-fa7d-41e0-a8fa-388e3d91d102","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TrmiGAjL5QTVYXmXdffXrV","type":"tool_result","content":"rmse_naive_h1 0.9969\nmae_naive_h1 0.8487\nrmse_naive_h3 1.42\nmae_naive_h3 1.2004\nrmse_snaive_h1 1.6745\nmae_snaive_h1 1.3067\nrmse_snaive_h3 1.3161\nmae_snaive_h3 1.0659\nrmse_ar1_h1 0.9405\nmae_ar1_h1 0.7977\nrmse_ar1_h3 1.1871\nmae_ar1_h3 0.9527\nrmse_model_h1 0.5503\nmae_model_h1 0.4863\nrmse_model_h3 1.1422\nmae_model_h3 0.934\nrel_improvement_rmse_h1 0.448\ndm_stat_h1 2.429\ndm_pvalue_h1 0.0151\nboot_rmse_diff_ci95_lo_h1 0.2616\nboot_rmse_diff_ci95_hi_h1 0.6988\nshare_origins_model_smaller_sq_error_h1 0.8\nrel_improvement_rmse_h3 0.1956\ndm_stat_h3 1.5466\ndm_pvalue_h3 0.122\nboot_rmse_diff_ci95_lo_h3 -0.1449\nboot_rmse_diff_ci95_hi_h3 0.6265\nshare_origins_model_smaller_sq_error_h3 0.6\nmean_abs_revision_h1_targets 0.5482","is_error":false}]},"uuid":"fcfe5be0-2f56-43aa-ad9a-bac7431a2e1d","timestamp":"2026-10-30T05:34:29.707Z","toolUseResult":{"stdout":"rmse_naive_h1 0.9969\nmae_naive_h1 0.8487\nrmse_naive_h3 1.42\nmae_naive_h3 1.2004\nrmse_snaive_h1 1.6745\nmae_snaive_h1 1.3067\nrmse_snaive_h3 1.3161\nmae_snaive_h3 1.0659\nrmse_ar1_h1 0.9405\nmae_ar1_h1 0.7977\nrmse_ar1_h3 1.1871\nmae_ar1_h3 0.9527\nrmse_model_h1 0.5503\nmae_model_h1 0.4863\nrmse_model_h3 1.1422\nmae_model_h3 0.934\nrel_improvement_rmse_h1 0.448\ndm_stat_h1 2.429\ndm_pvalue_h1 0.0151\nboot_rmse_diff_ci95_lo_h1 0.2616\nboot_rmse_diff_ci95_hi_h1 0.6988\nshare_origins_model_smaller_sq_error_h1 0.8\nrel_improvement_rmse_h3 0.1956\ndm_stat_h3 1.5466\ndm_pvalue_h3 0.122\nboot_rmse_diff_ci95_lo_h3 -0.1449\nboot_rmse_diff_ci95_hi_h3 0.6265\nshare_origins_model_smaller_sq_error_h3 0.6\nmean_abs_revision_h1_targets 0.5482","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"41f0c39f-fa7d-41e0-a8fa-388e3d91d102","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}105{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"327998b0a8535c4f3ef6ef4886e78cada63a7f359683e10a091afb060ca78ded","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01TrmiGAjL5QTVYXmXdffXrV","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n  if isinstance(v,float): print(k, round(v,4))\n\"","description":"Print numeric results rounded"}}]}}106{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"b24c7be2-67d7-4647-a032-244eaaa65e71","timestamp":"2026-10-30T05:34:29.710Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"ddaf2c3d-501c-478e-8660-baee4deeaa47","keep":34,"tail":["327998b0a8535c4f3ef6ef4886e78cada63a7f359683e10a091afb060ca78ded","754b3fce2ca416258ab82984e79e3d862c6dcc1385f4c8d9e8319389a43e3b02"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e459904541a27291a2b2b0d787880112ad6d774bbb23277b90ab6262183ca7ec"}107{"parentUuid":"fcfe5be0-2f56-43aa-ad9a-bac7431a2e1d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsr7YYKdkFF4gQXv4b3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XH2xRdtns971Yfcuah8LmW","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from ALFRED vintages\n\n## Question\nCould the year-over-year growth of US retail and food services sales (RSAFS, g_m = 100·ln(L_m/L_{m−12})) have been forecast in real time, 1 and 3 months beyond the last published month, better than the no-change (naive) forecast, when forecast errors are measured against the first published value of each target month? We evaluate 10 month-end origins from 2025-10-31 (`first_origin`) to 2026-07-31 (`last_origin`), `n_origins` = 10.\n\n## Data and exclusions\n- Inputs (row counts in `n_input_rows`): 10 RSAFS and 10 PAYEMS ALFRED vintages, the current UMCSENT and RSAFS files, and `first_release.csv`. All SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`).\n- **Real-time design.** The forecast made at origin V uses only `RSAFS_vintage_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 in that vintage. Observed publication delays: last(V) = 2025-08 at V = 2025-10-31 and 2026-01 at V = 2026-03-31 (two months before the vintage date); the 2026-04-30 vintage adds two months (2026-02 and 2026-03) at once. For every other origin last(V) is the month before V. As a result, the h=1 targets are 2025-09, 2025-10, 2025-11, 2025-12, 2026-01, 2026-02, 2026-04, 2026-05, 2026-06 and 2026-07, and the h=3 targets run from 2025-11 to 2026-09. 2026-03 is not an h=1 target, and 2026-05 is not an h=3 target.\n- Actuals are `yoy_first_release` from `first_release.csv`. The h=3 actuals for 2026-08 and 2026-09 come after a large level revision of RSAFS (current levels are about 4–5% below the vintage levels). YoY is always computed within a single vintage, so the actuals stay internally consistent.\n- PAYEMS and UMCSENT were audited but are not used by any forecast. `RSAFS_current.csv` is used only for the revision estimand.\n- Exclusions (`out/exclusions.csv`): 80 forecast–actual pairs were planned and 80 were analysed, with 0 removed. `n_analysed` = 20 pairs for my model (10 per horizon).\n- Data problems and how each was handled are listed in `data_issues`.\n\n## Method\n- **Baselines** (computed from the vintage dated V): naive (g_last for both horizons); seasonal naive (g_{T−12} from the vintage); AR(1) (OLS of g_m on a constant and g_{m−1} over 1993-02 ≤ m ≤ last(V), with iterated forecasts; φ̂ ≈ 0.84 at every origin, see `out/supplementary.json`).\n- **My model** (`model_name`, `model_description`): a base-effect random walk with drift in the log level. The forecast is ln L̂_T = ln L_last + h·g_last/1200, and the YoY forecast is 100·(ln L̂_T − ln L_{T−12}), with L_{T−12} taken from the same vintage. In words, it is the naive forecast corrected for the known change in the year-earlier comparison level (base effects) plus a drift. The model has no estimated parameters. I fixed the specification before seeing any evaluation result and tried no alternatives on the evaluation sample, so there is no specification search to correct for.\n- **Evaluation:** RMSE and MAE over the 10 origins for each horizon; 1 − RMSE_model/RMSE_naive; and a Diebold–Mariano test on d_t = e²_naive − e²_model. The DM test uses a Bartlett (Newey–West) long-run variance with truncation lag h−1, no HLN correction, and a two-sided normal p-value.\n- **Supplementary uncertainty measure:** a moving-block bootstrap (block length max(h,2), B = 5000, seed `random_seed`) of RMSE_naive − RMSE_model.\n- **Revision estimand:** the mean over the 10 h=1 targets of |g_current − yoy_first_release|.\n\n## Results\nTable 1 (`out/table1.csv`; RMSE / MAE in percentage points; n = 10 per cell):\n\n| model | h=1 RMSE | h=1 MAE | h=3 RMSE | h=3 MAE |\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| BE-RWD (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:** my model lowers RMSE by 44.8% relative to naive (`rel_improvement_rmse_h1` = 0.448). The DM statistic is 2.43 (`dm_stat_h1`), with p = 0.015 (`dm_pvalue_h1`), giving `conclusion_code_h1` = model_better_significant.\n- **h = 3:** the improvement is 19.6% (`rel_improvement_rmse_h3` = 0.196). The DM statistic is 1.55 (`dm_stat_h3`), with p = 0.122 (`dm_pvalue_h3`), giving `conclusion_code_h3` = model_better_not_significant.\n- At h = 3 every alternative has a lower RMSE than naive, but my model's edge over AR(1) is small: 1.142 against 1.187.\n- **Revisions:** first-release YoY of the h=1 targets differs from today's published YoY by 0.548 pp on average (`mean_abs_revision_h1_targets`). That is the same order as the model's h=1 RMSE. All 10 revisions are negative (`out/supplementary.json`), consistent with the large level revision after mid-2026.\n- Figure 1 (`out/figure1.png`) plots the first-release actuals and the naive, AR(1) and model forecasts for each horizon.\n\n## Uncertainty\n- **Small sample.** With only 10 origins, the DM statistic relies on a normal approximation that is unreliable at this sample size. The long-run variance is estimated from 10 loss differentials, and at h=3 from overlapping errors with only two lags. With n = 10 the omitted HLN correction would shrink the statistic and Student-t critical values would be wider. The h=1 p-value of 0.015 (`dm_pvalue_h1`) should therefore be read as suggestive evidence, not a firm rejection.\n- **h = 1 evidence.** Two other measures point the same way. The model has the smaller squared error at 8 of 10 origins (`share_origins_model_smaller_sq_error_h1` = 0.8). The block-bootstrap 95% interval for RMSE_naive − RMSE_model is [0.26, 0.70] pp (`boot_rmse_diff_ci95_lo_h1`, `boot_rmse_diff_ci95_hi_h1`) and excludes zero. Even so, a bootstrap on 10 points is itself fragile.\n- **h = 3 evidence.** The bootstrap interval is [−0.14, 0.63] pp (`boot_rmse_diff_ci95_lo_h3`, `boot_rmse_diff_ci95_hi_h3`) and includes zero. The model wins at 6 of 10 origins (`share_origins_model_smaller_sq_error_h3`). The data cannot distinguish the model from naive at this horizon.\n- **Why the h=1 gain is plausible.** It has a mechanical explanation that should carry over to other periods: the year-earlier comparison level is already known at the origin, and the naive forecast ignores it.\n\n## Limitations and open issues\n- **Short, unusual sample.** There are only 10 origins, the period covers irregular publication timing and a large benchmark revision, and the h=3 errors overlap. Results may not generalise.\n- **Mixed-vintage actuals.** First-release actuals for targets 2026-08 and 2026-09 (h=3, last two origins) come from vintages after a big level revision. Forecasts made from pre-revision vintages are compared with actuals from post-revision vintages; because the comparison is in YoY terms the effect is muted but not removed.\n- **Predictors not used.** PAYEMS and UMCSENT were not used. I made no attempt to show whether they add information, and nothing is claimed about them.\n- **Unresolved conflict with the gate.** The provided gate checks `origin_date < target_date` in `out/forecasts.csv`. TASK.md requires `target_date` to be the first day of the target month (YYYY-MM-01). Because a month-end vintage contains at most the month before V, every h=1 target month begins before its month-end origin date (e.g. origin 2026-05-31, target 2026-05-01), so 40 of 80 rows fail that literal rule. The substantive availability rule — the target month is not yet published in the vintage used — holds for all 80 rows, and this is asserted in `out/analysis.py`. I kept the format TASK.md specifies instead of relabelling dates to pass the gate. Phase P4 is therefore recorded as \"blocked\" by this rule only (see `out/state/checks.md`). All required estimands were produced (`feasibility` = complete).\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect random-walk-with-drift model has a lower RMSE than the naive forecast (0.550 vs 0.997 pp; 44.8% improvement) and the DM test rejects equal accuracy at 5% (DM 2.43, p 0.015).\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"Only 10 origins; the normal approximation for DM is fragile in this sample.\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the model has a lower RMSE than naive (1.142 vs 1.420; 19.6% improvement) but the difference is not statistically significant (DM 1.55, p 0.122; bootstrap interval includes zero).\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\",\"boot_rmse_diff_ci95_lo_h3\",\"boot_rmse_diff_ci95_hi_h3\"],\"status\":\"supported\",\"caveat\":\"Overlapping h=3 errors; two h=3 actuals come after a major level revision.\"},\n {\"id\":\"C3\",\"text\":\"Seasonal naive is the worst baseline at h=1 (RMSE 1.675) and AR(1) is close to naive at h=1 (0.941) but better at h=3 (1.187).\",\"results_keys\":[\"rmse_snaive_h1\",\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_snaive_h3\"],\"status\":\"supported\",\"caveat\":\"Rankings based on 10 origins without formal tests among baselines.\"},\n {\"id\":\"C4\",\"text\":\"The first-release YoY growth of the h=1 target months differs on average by 0.548 pp from today's published YoY growth, the same order as the model's h=1 RMSE.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"rmse_model_h1\"],\"status\":\"supported\",\"caveat\":\"Driven by a large level revision after mid-2026; not representative of typical revision size.\"},\n {\"id\":\"C5\",\"text\":\"Block-bootstrap 95% interval for RMSE_naive minus RMSE_model at h=1 excludes zero, and the model wins at 8 of 10 origins.\",\"results_keys\":[\"boot_rmse_diff_ci95_lo_h1\",\"boot_rmse_diff_ci95_hi_h1\",\"share_origins_model_smaller_sq_error_h1\",\"random_seed\"],\"status\":\"supported\",\"caveat\":\"Bootstrap with 10 observations is itself unreliable.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'))\" && echo 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":664,"cache_read_input_tokens":46937,"output_tokens":4546,"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":664},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsr7MPEYpZ8gHMw5zRx","requestRef":"b24c7be2-67d7-4647-a032-244eaaa65e71","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e5856724-850a-4f08-b445-e4157cdb3004","timestamp":"2026-10-30T05:35:06.599Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}108{"parentUuid":"e5856724-850a-4f08-b445-e4157cdb3004","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01XH2xRdtns971Yfcuah8LmW","type":"tool_result","content":"ok","is_error":false}]},"uuid":"a181e11e-3d4d-4ae8-8401-e3c365732c64","timestamp":"2026-10-30T05:35:06.681Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e5856724-850a-4f08-b445-e4157cdb3004","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}109{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"8b550cbd216fdd88e0ac42550565b80c12f117a091510fbb8e0f15cc206233fd","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01XH2xRdtns971Yfcuah8LmW","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from ALFRED vintages\n\n## Question\nCould the year-over-year growth of US retail and food services sales (RSAFS, g_m = 100·ln(L_m/L_{m−12})) have been forecast in real time, 1 and 3 months beyond the last published month, better than the no-change (naive) forecast, when forecast errors are measured against the first published value of each target month? We evaluate 10 month-end origins from 2025-10-31 (`first_origin`) to 2026-07-31 (`last_origin`), `n_origins` = 10.\n\n## Data and exclusions\n- Inputs (row counts in `n_input_rows`): 10 RSAFS and 10 PAYEMS ALFRED vintages, the current UMCSENT and RSAFS files, and `first_release.csv`. All SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`).\n- **Real-time design.** The forecast made at origin V uses only `RSAFS_vintage_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 in that vintage. Observed publication delays: last(V) = 2025-08 at V = 2025-10-31 and 2026-01 at V = 2026-03-31 (two months before the vintage date); the 2026-04-30 vintage adds two months (2026-02 and 2026-03) at once. For every other origin last(V) is the month before V. As a result, the h=1 targets are 2025-09, 2025-10, 2025-11, 2025-12, 2026-01, 2026-02, 2026-04, 2026-05, 2026-06 and 2026-07, and the h=3 targets run from 2025-11 to 2026-09. 2026-03 is not an h=1 target, and 2026-05 is not an h=3 target.\n- Actuals are `yoy_first_release` from `first_release.csv`. The h=3 actuals for 2026-08 and 2026-09 come after a large level revision of RSAFS (current levels are about 4–5% below the vintage levels). YoY is always computed within a single vintage, so the actuals stay internally consistent.\n- PAYEMS and UMCSENT were audited but are not used by any forecast. `RSAFS_current.csv` is used only for the revision estimand.\n- Exclusions (`out/exclusions.csv`): 80 forecast–actual pairs were planned and 80 were analysed, with 0 removed. `n_analysed` = 20 pairs for my model (10 per horizon).\n- Data problems and how each was handled are listed in `data_issues`.\n\n## Method\n- **Baselines** (computed from the vintage dated V): naive (g_last for both horizons); seasonal naive (g_{T−12} from the vintage); AR(1) (OLS of g_m on a constant and g_{m−1} over 1993-02 ≤ m ≤ last(V), with iterated forecasts; φ̂ ≈ 0.84 at every origin, see `out/supplementary.json`).\n- **My model** (`model_name`, `model_description`): a base-effect random walk with drift in the log level. The forecast is ln L̂_T = ln L_last + h·g_last/1200, and the YoY forecast is 100·(ln L̂_T − ln L_{T−12}), with L_{T−12} taken from the same vintage. In words, it is the naive forecast corrected for the known change in the year-earlier comparison level (base effects) plus a drift. The model has no estimated parameters. I fixed the specification before seeing any evaluation result and tried no alternatives on the evaluation sample, so there is no specification search to correct for.\n- **Evaluation:** RMSE and MAE over the 10 origins for each horizon; 1 − RMSE_model/RMSE_naive; and a Diebold–Mariano test on d_t = e²_naive − e²_model. The DM test uses a Bartlett (Newey–West) long-run variance with truncation lag h−1, no HLN correction, and a two-sided normal p-value.\n- **Supplementary uncertainty measure:** a moving-block bootstrap (block length max(h,2), B = 5000, seed `random_seed`) of RMSE_naive − RMSE_model.\n- **Revision estimand:** the mean over the 10 h=1 targets of |g_current − yoy_first_release|.\n\n## Results\nTable 1 (`out/table1.csv`; RMSE / MAE in percentage points; n = 10 per cell):\n\n| model | h=1 RMSE | h=1 MAE | h=3 RMSE | h=3 MAE |\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| BE-RWD (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:** my model lowers RMSE by 44.8% relative to naive (`rel_improvement_rmse_h1` = 0.448). The DM statistic is 2.43 (`dm_stat_h1`), with p = 0.015 (`dm_pvalue_h1`), giving `conclusion_code_h1` = model_better_significant.\n- **h = 3:** the improvement is 19.6% (`rel_improvement_rmse_h3` = 0.196). The DM statistic is 1.55 (`dm_stat_h3`), with p = 0.122 (`dm_pvalue_h3`), giving `conclusion_code_h3` = model_better_not_significant.\n- At h = 3 every alternative has a lower RMSE than naive, but my model's edge over AR(1) is small: 1.142 against 1.187.\n- **Revisions:** first-release YoY of the h=1 targets differs from today's published YoY by 0.548 pp on average (`mean_abs_revision_h1_targets`). That is the same order as the model's h=1 RMSE. All 10 revisions are negative (`out/supplementary.json`), consistent with the large level revision after mid-2026.\n- Figure 1 (`out/figure1.png`) plots the first-release actuals and the naive, AR(1) and model forecasts for each horizon.\n\n## Uncertainty\n- **Small sample.** With only 10 origins, the DM statistic relies on a normal approximation that is unreliable at this sample size. The long-run variance is estimated from 10 loss differentials, and at h=3 from overlapping errors with only two lags. With n = 10 the omitted HLN correction would shrink the statistic and Student-t critical values would be wider. The h=1 p-value of 0.015 (`dm_pvalue_h1`) should therefore be read as suggestive evidence, not a firm rejection.\n- **h = 1 evidence.** Two other measures point the same way. The model has the smaller squared error at 8 of 10 origins (`share_origins_model_smaller_sq_error_h1` = 0.8). The block-bootstrap 95% interval for RMSE_naive − RMSE_model is [0.26, 0.70] pp (`boot_rmse_diff_ci95_lo_h1`, `boot_rmse_diff_ci95_hi_h1`) and excludes zero. Even so, a bootstrap on 10 points is itself fragile.\n- **h = 3 evidence.** The bootstrap interval is [−0.14, 0.63] pp (`boot_rmse_diff_ci95_lo_h3`, `boot_rmse_diff_ci95_hi_h3`) and includes zero. The model wins at 6 of 10 origins (`share_origins_model_smaller_sq_error_h3`). The data cannot distinguish the model from naive at this horizon.\n- **Why the h=1 gain is plausible.** It has a mechanical explanation that should carry over to other periods: the year-earlier comparison level is already known at the origin, and the naive forecast ignores it.\n\n## Limitations and open issues\n- **Short, unusual sample.** There are only 10 origins, the period covers irregular publication timing and a large benchmark revision, and the h=3 errors overlap. Results may not generalise.\n- **Mixed-vintage actuals.** First-release actuals for targets 2026-08 and 2026-09 (h=3, last two origins) come from vintages after a big level revision. Forecasts made from pre-revision vintages are compared with actuals from post-revision vintages; because the comparison is in YoY terms the effect is muted but not removed.\n- **Predictors not used.** PAYEMS and UMCSENT were not used. I made no attempt to show whether they add information, and nothing is claimed about them.\n- **Unresolved conflict with the gate.** The provided gate checks `origin_date < target_date` in `out/forecasts.csv`. TASK.md requires `target_date` to be the first day of the target month (YYYY-MM-01). Because a month-end vintage contains at most the month before V, every h=1 target month begins before its month-end origin date (e.g. origin 2026-05-31, target 2026-05-01), so 40 of 80 rows fail that literal rule. The substantive availability rule — the target month is not yet published in the vintage used — holds for all 80 rows, and this is asserted in `out/analysis.py`. I kept the format TASK.md specifies instead of relabelling dates to pass the gate. Phase P4 is therefore recorded as \"blocked\" by this rule only (see `out/state/checks.md`). All required estimands were produced (`feasibility` = complete).\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect random-walk-with-drift model has a lower RMSE than the naive forecast (0.550 vs 0.997 pp; 44.8% improvement) and the DM test rejects equal accuracy at 5% (DM 2.43, p 0.015).\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"Only 10 origins; the normal approximation for DM is fragile in this sample.\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the model has a lower RMSE than naive (1.142 vs 1.420; 19.6% improvement) but the difference is not statistically significant (DM 1.55, p 0.122; bootstrap interval includes zero).\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\",\"boot_rmse_diff_ci95_lo_h3\",\"boot_rmse_diff_ci95_hi_h3\"],\"status\":\"supported\",\"caveat\":\"Overlapping h=3 errors; two h=3 actuals come after a major level revision.\"},\n {\"id\":\"C3\",\"text\":\"Seasonal naive is the worst baseline at h=1 (RMSE 1.675) and AR(1) is close to naive at h=1 (0.941) but better at h=3 (1.187).\",\"results_keys\":[\"rmse_snaive_h1\",\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_snaive_h3\"],\"status\":\"supported\",\"caveat\":\"Rankings based on 10 origins without formal tests among baselines.\"},\n {\"id\":\"C4\",\"text\":\"The first-release YoY growth of the h=1 target months differs on average by 0.548 pp from today's published YoY growth, the same order as the model's h=1 RMSE.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"rmse_model_h1\"],\"status\":\"supported\",\"caveat\":\"Driven by a large level revision after mid-2026; not representative of typical revision size.\"},\n {\"id\":\"C5\",\"text\":\"Block-bootstrap 95% interval for RMSE_naive minus RMSE_model at h=1 excludes zero, and the model wins at 8 of 10 origins.\",\"results_keys\":[\"boot_rmse_diff_ci95_lo_h1\",\"boot_rmse_diff_ci95_hi_h1\",\"share_origins_model_smaller_sq_error_h1\",\"random_seed\"],\"status\":\"supported\",\"caveat\":\"Bootstrap with 10 observations is itself unreliable.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'))\" && echo ok","description":"Write report and claims ledger"}}]}}110{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"9327d164-9aeb-4c96-9874-cb5bdda68708","timestamp":"2026-10-30T05:35:06.685Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"b24c7be2-67d7-4647-a032-244eaaa65e71","keep":36,"tail":["8b550cbd216fdd88e0ac42550565b80c12f117a091510fbb8e0f15cc206233fd","eb3e323a0f4fdadb287e14246cd72cc37ba2eaa7e27c1c9d534c3c5a6a92d80d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",37,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9b4a75299d7579041d720ccca4f4ecbfa9dd9aa8bd58391258a9833e80833f55"}111{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a181e11e-3d4d-4ae8-8401-e3c365732c64","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}112{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}113{"type":"tools-used","tools":["Bash","Read"],"sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}114{"parentUuid":"a181e11e-3d4d-4ae8-8401-e3c365732c64","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstqgPbjm3UhbbBCiLx","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":4553,"cache_read_input_tokens":47601,"output_tokens":110,"output_tokens_details":{"thinking_tokens":29},"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":4553},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":333,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXstqS1qVCKwGDbsnezJ","requestRef":"9327d164-9aeb-4c96-9874-cb5bdda68708","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"91b73972-25c1-4cde-b197-c78a27b20a06","timestamp":"2026-10-30T05:35:07.849Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}115{"parentUuid":"91b73972-25c1-4cde-b197-c78a27b20a06","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstqgPbjm3UhbbBCiLx","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013TKga9kB9ysqJkj88S4YNi","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0009/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":4553,"cache_read_input_tokens":47601,"output_tokens":110,"output_tokens_details":{"thinking_tokens":29},"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":4553},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXstqS1qVCKwGDbsnezJ","requestRef":"9327d164-9aeb-4c96-9874-cb5bdda68708","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"65e2345a-640e-4f8a-8c95-49ba049c4894","timestamp":"2026-10-30T05:35:08.012Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}116{"parentUuid":"65e2345a-640e-4f8a-8c95-49ba049c4894","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013TKga9kB9ysqJkj88S4YNi","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"b06cbe61-6add-4d92-8af9-bd5a618f571b","timestamp":"2026-10-30T05:35:08.020Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":121711,"dimensions":{"originalWidth":1440,"originalHeight":540,"displayWidth":1440,"displayHeight":540}}},"sourceToolAssistantUUID":"65e2345a-640e-4f8a-8c95-49ba049c4894","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}117{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"d86b54a95c860ad104024cbd7e97bf74050cb1335e9fa1c064b597ead1afe542","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_013TKga9kB9ysqJkj88S4YNi","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0009/out/figure1.png"}}]}}118{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"f19f1ecd-79a0-4cd9-9241-79c5da6bceab","timestamp":"2026-10-30T05:35:08.026Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"9327d164-9aeb-4c96-9874-cb5bdda68708","keep":38,"tail":["d86b54a95c860ad104024cbd7e97bf74050cb1335e9fa1c064b597ead1afe542","7912e4d60e4d71408b0d62705ab3bb73d480f945384bac53d8eaed949bfcc8cf"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",39,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c954fcb31aa05b9efb28d5850c1d2e8d91a405ab83d5ee58c179cc9400dfb012"}119{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b06cbe61-6add-4d92-8af9-bd5a618f571b","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}120{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}121{"parentUuid":"b06cbe61-6add-4d92-8af9-bd5a618f571b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstwRRTQDEmLkmaKcAS","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":1169,"cache_read_input_tokens":52154,"output_tokens":366,"output_tokens_details":{"thinking_tokens":31},"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":1169},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":487,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXstwBnvDcqzDtvNDGGP","requestRef":"f19f1ecd-79a0-4cd9-9241-79c5da6bceab","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cea6d533-cf5f-4b12-9efb-71750d235d1d","timestamp":"2026-10-30T05:35:09.329Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}122{"parentUuid":"cea6d533-cf5f-4b12-9efb-71750d235d1d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstwRRTQDEmLkmaKcAS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015cf2P6GczmqcgjnqVQrPiG","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; ph=json.load(open(p))\nph['P5']={\"status\":\"passed\",\"checks\":[\"report.md written with 6 required sections, each number cites a results.json key\",\"claims.json: 5 claims, all results_keys exist in results.json\",\"figure1.png inspected visually\",\"final gate run executed (receipt recorded in notes)\"],\"notes\":\"Executed under stopping rule despite P4 blocked by forecasts_chronology rule conflict.\"}\njson.dump(ph,open(p,'w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Update P5 and run final gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1169,"cache_read_input_tokens":52154,"output_tokens":366,"output_tokens_details":{"thinking_tokens":31},"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":1169},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXstwBnvDcqzDtvNDGGP","requestRef":"f19f1ecd-79a0-4cd9-9241-79c5da6bceab","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fc299e56-a487-4402-9bd3-6c9db4e561a6","timestamp":"2026-10-30T05:35:11.351Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}123{"parentUuid":"fc299e56-a487-4402-9bd3-6c9db4e561a6","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015cf2P6GczmqcgjnqVQrPiG","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/RT0009/out/state/gate_receipts/20261030T053512.664445Z.json","is_error":false}]},"uuid":"54fc0835-3ee0-401c-9d27-8304f9dd0b86","timestamp":"2026-10-30T05:35:12.671Z","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/RT0009/out/state/gate_receipts/20261030T053512.664445Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fc299e56-a487-4402-9bd3-6c9db4e561a6","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}124{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"e5f9cd00b589017379dbedcb7cbc2ba14762b6aa28beb6944490df157034b9d6","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSzwYKEAgTGAI4AUIIdGhpbmtpbmcSDAUwtz5WRVSt+qVkjhoMcEXIII94YQKgnEhoIjApWzknWGB6WLNcDnTTHoqfFGu9HLSjNgCiRw+QWDk/n1DeTOCK7F+AszqBPWC4bbEq7AV6KQoMKIEqb1PHzHc3v+uhBVR3E4WSr/oYiZpJcQgybHY1v6Q8i3BsJKMcFr0QVePeHUIYokZrvMm2ZVwKPlWm1rz5vlWqhYP9TamCSV/nCcFDB41oXKZ5rg5q50l0DVGw8WOXm1npNvpBWnpLn7rDVIaeSuLJI0x1HlvlQHwiH6J/HE42GTJZGIYAcdeomcF+Nqc5l9wYjk8dBkeCAehYbXS7q93nJQMxV6kmkZiV3sfoHVAgNBjoM1x126b9Hd0OqArVdlUuKPkPhJjRfdspxAlFbYwx2oYa+PLYCnN77gdYD54MsaxQ2mhLy6rKv9F4874qhkBjJvWer8qtwbcYUaZkIz3vvooYiArwWBp9sViMYNeXagoMq3eXYDCAm7sEgLLcB7sbP1Q+CmyUqndtdbEDmpOEgNfaoWFJIdSsjzy+gEPCwEkdzHf3piArUdmMmXf2hnJWG00imXzgtWmucVTjRuwUOIJ6IpJSZtDfG0koMDoLVWeqoSHA6p2rFYO1LvsWJNg+iqKweyjCDcaNbzABmP8Lxt9M9LJVMVY2sq4HJi4HNQRbKpKMqHPilCE7SxyKjNQSfAw+7pUz4hJJGE8QOAlLLzwKf7cYfRMvx1asKoGTLVNA0lWUvvKLmYb6UCKbL77/SgeeJhQiJ2XG+Rc2RnQFlQF20ttVbeq3hxlV8WPI2f4x3hJJQc2CoRCG0ougH02kHCYAT3sLivhN5DCZ/X6m5tqkIkAsxTaxwkQWUh/J4ynpMp2P7/TtA5uA8n11bXzqxU3h7OnDnf0WKCKWQZNqljiu2xv/V4oOl+qD8cTkgABF6jLJ4JzPta/9/7wGyWb3rK/Fa2L2LY2rshhLD83DiZIKOz/Gb7K8JvdgbkzNMVb4EGZBz0K9f0hpOL1I7qwHHl8dyeBjUmBS5P8zFgtuaC56IFb3qqLX7aTNMvWwG0HiQKPqAbICFdV0luhiOr4s0q4gg0YIJqQhI8JF1b3Fam3ePPFiGAE="},{"type":"tool_use","id":"toolu_015cf2P6GczmqcgjnqVQrPiG","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; ph=json.load(open(p))\nph['P5']={\"status\":\"passed\",\"checks\":[\"report.md written with 6 required sections, each number cites a results.json key\",\"claims.json: 5 claims, all results_keys exist in results.json\",\"figure1.png inspected visually\",\"final gate run executed (receipt recorded in notes)\"],\"notes\":\"Executed under stopping rule despite P4 blocked by forecasts_chronology rule conflict.\"}\njson.dump(ph,open(p,'w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Update P5 and run final gate"}}]}}125{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"74528114-9b21-4e8b-a6ab-224668101d30","timestamp":"2026-10-30T05:35:12.676Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"f19f1ecd-79a0-4cd9-9241-79c5da6bceab","keep":40,"tail":["e5f9cd00b589017379dbedcb7cbc2ba14762b6aa28beb6944490df157034b9d6","7b9f8e64159683e4bb07522f010d62f8bb212f3ef76cb06ebc1dd97c74de0bed"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",41,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"58c93b0773c121fa00b4dd98a0e24178b4ae1b15d26afc929915eb3bda870a88"}126{"parentUuid":"54fc0835-3ee0-401c-9d27-8304f9dd0b86","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsuHLEo5d4TX1HZSCss","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":497,"cache_read_input_tokens":53323,"output_tokens":512,"output_tokens_details":{"thinking_tokens":28},"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":497},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":476,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsuH4NK563hh4TrVu1U","requestRef":"74528114-9b21-4e8b-a6ab-224668101d30","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d274f23f-5331-4259-b244-e964660499a0","timestamp":"2026-10-30T05:35:13.999Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}127{"parentUuid":"d274f23f-5331-4259-b244-e964660499a0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsuHLEo5d4TX1HZSCss","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01E1ktcQuzFm45Lv71sAbF7q","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; ph=json.load(open(p))\nr=\"out/state/gate_receipts/20261030T053512.664445Z.json\"\nph['P5']['checks'][-1]=f\"final gate run receipt {r}: passed=false, 64/65 ok; sole failure forecasts_chronology (40 h=1 rows), a TASK.md-vs-gate rule conflict documented in checks.md and report\"\nph['P4']['checks'].append(f\"gate run 2 receipt {r}: only forecasts_chronology fails\")\njson.dump(ph,open(p,'w'),indent=1)\nEOF\necho \"- 2026-10-30: P5 passed (report, claims). Final gate receipt 20261030T053512.664445Z: 64/65 ok; only forecasts_chronology fails due to the TASK.md target_date convention (kept deliberately, documented).\" >> out/state/log.md\necho \"| 16 | Gate run 2 (20261030T053512.664445Z): 64/65 checks ok; only forecasts_chronology fails (see note) | partial |\" >> out/state/checks.md\nls out out/state","description":"Record final gate receipt and log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":497,"cache_read_input_tokens":53323,"output_tokens":512,"output_tokens_details":{"thinking_tokens":28},"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":497},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsuH4NK563hh4TrVu1U","requestRef":"74528114-9b21-4e8b-a6ab-224668101d30","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d0247a87-f2df-4e06-98bb-691a454366b3","timestamp":"2026-10-30T05:35:17.217Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}128{"parentUuid":"d0247a87-f2df-4e06-98bb-691a454366b3","isSidechain":false,"promptId":"dd4ceed7-0c40-4a6d-92b6-513b6fd48dbc","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01E1ktcQuzFm45Lv71sAbF7q","type":"tool_result","content":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\nstate\nsupplementary.json\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","is_error":false}]},"uuid":"741fa6fd-12e3-4027-93f7-42146f243d16","timestamp":"2026-10-30T05:35:17.297Z","toolUseResult":{"stdout":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\nstate\nsupplementary.json\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d0247a87-f2df-4e06-98bb-691a454366b3","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}129{"type":"api-request-blob","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","hash":"815316bae083b69e7b456a361a3c5315642d019d3a1f6316b4ffca45819a40ea","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01E1ktcQuzFm45Lv71sAbF7q","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; ph=json.load(open(p))\nr=\"out/state/gate_receipts/20261030T053512.664445Z.json\"\nph['P5']['checks'][-1]=f\"final gate run receipt {r}: passed=false, 64/65 ok; sole failure forecasts_chronology (40 h=1 rows), a TASK.md-vs-gate rule conflict documented in checks.md and report\"\nph['P4']['checks'].append(f\"gate run 2 receipt {r}: only forecasts_chronology fails\")\njson.dump(ph,open(p,'w'),indent=1)\nEOF\necho \"- 2026-10-30: P5 passed (report, claims). Final gate receipt 20261030T053512.664445Z: 64/65 ok; only forecasts_chronology fails due to the TASK.md target_date convention (kept deliberately, documented).\" >> out/state/log.md\necho \"| 16 | Gate run 2 (20261030T053512.664445Z): 64/65 checks ok; only forecasts_chronology fails (see note) | partial |\" >> out/state/checks.md\nls out out/state","description":"Record final gate receipt and log"}}]}}130{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"5a377515-c413-4b56-8def-58128bd8b72c","timestamp":"2026-10-30T05:35:17.300Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":"74528114-9b21-4e8b-a6ab-224668101d30","keep":42,"tail":["815316bae083b69e7b456a361a3c5315642d019d3a1f6316b4ffca45819a40ea","8043b9fc5324568217185748d6debc00008bde81f97f4bdc3c6c21419ed18113"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",43,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5330e1275271d7c2c31f4368f1f08175edf4553d60df939c7a8584beb98d4e5c"}131{"parentUuid":"741fa6fd-12e3-4027-93f7-42146f243d16","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsud4QGgtZfnQ96QUfw","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS8gYKEAgTGAI4AUIIdGhpbmtpbmcSDPvaeZDTam1TuEACtBoMdRW2M4S8ZZQgu8i2IjCevrEKis6BSLBwAwDzoRtkT5r03VBI15PdDNa7CDBOot0GAGu0ofBp3QYPC2nCRAAqjwaTWwqGbDfypyOzPW0dU/lBN9z8DOaWsxOeFQcX894ZtmoXSe/knxyDiJEBXQ4VrtXdeJK+umdyvqb31ydpnwOIAQsJWQq7J/40t/KBXIwaLh1YJPbvWXwHr7KRExbrwjji+on2EHsjPbPeB1yWjWIZKFZ5Q+nLBc7jdVuU9l5vumOJGQ/NHQcuZ0jnP7kAVlYwlZK3BJcdTNHDbJG/dWYWUL1FITbzVmSb74KnG06fMg8Ronngm44h+mjKKZpdb4Gz6UFiQfvi32lNLoEMJ7+py/uABvvFsZEXlqRCpD3uvq8lElyZ34tDk1FDBqNrNSMGlYyDLTtS8pcPRjZqyquljh/pFWEun2ebLs2NPJfCUHhWqQV1avCrCn/UnTJCehDfUDAd93fT1fEUhr4MDIsvmPWHms6CQsNc41nPn4qdTrJASLhA48zuudAtGPpN5x6HBDReBSKZnl/HLXjMqroGpPlUSW3Gcq/WJvHwuAmp2QxWoDu1jxbpPg7loLscXXEXX00892OLFyBzLra6DG+dHLASmVcavY+LgaOb5aQI5QewfXujZivGRyVBxEwmRhwycso4X++5++0rd6RinBoGyoA3sA5Iye6T20Df7cJehgH4qFz7VV5uI+VSmqCAe4+9Ye3/87zPTHrC1fJG8+H6aomMUR60WtCiLM4fPVQXFf+0w9eeQYLW3N5MamxiWPFTlUFNjX0w6apHsb9yRSqiWiOiE2VV0sGUdfLYUDPQV0Sef3LEr704Ob8hWt+3Op8+4S0/lGtV+6yaEKEYe2LNQtKiXLTk5bDJ06zULslQWIH+WrJvGRgpB6ttnztqu5qJkc7p5eWoTGCSkTxAPbmnTRMDnVfejTQIRi3Y+X72CBK8F00I93S8bQaNZv2sjaPY5BNIcwcp8Cg70jfTWtig/fxpZlfSLPY8H2z+imGMHZpfBii9Qp5/rbxYh4I1sjQsK20oGcierleaExksYcILzI54lNNnCOGAQdFdJ5x6eRC8kVAbB9Mc+wGP3SE7f7eD022ZOwf8geMI9OS/SnsYAQ=="}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":613,"cache_read_input_tokens":53820,"output_tokens":1090,"output_tokens_details":{"thinking_tokens":37},"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":613},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6853,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsucp1i3Jer1NW9Woax","requestRef":"5a377515-c413-4b56-8def-58128bd8b72c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e29f8061-f6fe-4a24-acbc-841a8655465b","timestamp":"2026-10-30T05:35:25.155Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}132{"parentUuid":"e29f8061-f6fe-4a24-acbc-841a8655465b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsud4QGgtZfnQ96QUfw","type":"message","role":"assistant","content":[{"type":"text","text":"I've produced all the required files and estimands, but the final gate run still fails one of its 65 checks. The failure is a conflict between `TASK.md` and the gate's rules, and I chose not to relabel dates to make it pass. Because of that, phase P4 is recorded as \"blocked\" rather than \"passed\", and the protocol does not let me declare the task complete.\n\n**Results** (10 origins, 2025-10-31 to 2026-07-31; errors in percentage points against first-release values):\n\n| model | 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:** a random walk with drift in the log level, which converts to year-over-year growth using the year-earlier level already published in the same vintage. In effect, it is the naive forecast corrected for the known base effect. It has no estimated parameters, uses only the RSAFS vintage, and I fixed it before looking at any results. PAYEMS and sentiment are not used.\n- **h=1:** it beats naive by 44.8% in RMSE. The Diebold–Mariano statistic is 2.43 (p = 0.015), so the conclusion is \"model better, significant\". With only 10 origins, treat that as suggestive rather than firm. A bootstrap interval for the RMSE gap excludes zero, and the model wins at 8 of 10 origins.\n- **h=3:** it beats naive by 19.6%, but the difference is not significant (DM 1.55, p = 0.12; the bootstrap interval includes zero). It is barely better than AR(1) at this horizon.\n- **Revisions:** first-release growth of the h=1 target months differs from today's published growth by 0.548 points on average. That is about the size of my model's h=1 error, and it is driven by a large downward revision to RSAFS levels after mid-2026.\n\n**Data issues:** some months were published late (for example, the 2025-10-31 and 2026-03-31 data end two months before their dates), so targets follow the last published month as the task requires. The two latest h=3 actual values come from after the large revision. Both points are in the report and `data_issues`.\n\n**The gate failure:** the gate requires each row's target date to be later than its origin date. `TASK.md` requires the target date to be the first day of the target month (YYYY-MM-01). Every h=1 target month starts before its month-end origin (for example, origin 2026-05-31, target 2026-05-01), so all 40 h=1 rows fail that check. The actual rule that matters still holds for all 80 rows: the target month was not yet published in the data used. The script checks this, and the conflict is explained in `checks.md` and in the report's limitations section. All other gate checks pass, including the re-run that confirms `analysis.py` reproduces `results.json` exactly. When the controller re-runs the gate it will fail on this same check.\n\nEverything is in `out/`. Open `report.md` first; `analysis.py` regenerates the results, and the phase ledger, data audit, checks and log are in `out/state/`."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":613,"cache_read_input_tokens":53820,"output_tokens":1090,"output_tokens_details":{"thinking_tokens":37},"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":613},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsucp1i3Jer1NW9Woax","requestRef":"5a377515-c413-4b56-8def-58128bd8b72c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3e5cafc9-50a9-4b6b-a87c-0e149ce362cb","timestamp":"2026-10-30T05:35:28.080Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}133{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"3e5cafc9-50a9-4b6b-a87c-0e149ce362cb","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}134{"type":"cost-state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","totalCostUSD":0.9121184000000001,"totalAPIDuration":225878,"totalAPIDurationWithoutRetries":225866,"totalToolDuration":10811,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":236898,"startTime":1793338291190,"modelUsage":{"claude-opus-5-5":{"inputTokens":46,"outputTokens":25403,"thinkingTokens":4675,"cacheReadInputTokens":696147,"cacheCreationInputTokens":52929,"cacheCreationEphemeral5mInputTokens":52929,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.9121184000000001}},"hasUnknownModelCost":false}135{"type":"tools-used","tools":["Bash","Read"],"sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}136{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:35:29.880Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","content":"The"}137{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:35:29.881Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}138{"parentUuid":"3e5cafc9-50a9-4b6b-a87c-0e149ce362cb","isSidechain":false,"promptId":"a9e4a310-a706-4f15-a8df-098b20ae79fc","type":"user","message":{"role":"user","content":"The"},"uuid":"e2e8bba0-68fe-441e-a895-a7712d2f6ff1","timestamp":"2026-10-30T05:35:29.885Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":2},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}139{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"6347dbc3-a075-467c-986b-3626624120cc","timestamp":"2026-10-30T05:35:29.902Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","f238ba95539a99d3daf0e29621276816d32ea65940ea86c52f086849de9fb1bd","5091368c144595d34bc36632414133968c75ec8967ff421e2ebf06e79bfef535","8438fef5f84a18989cbb29a4c0351c587c98e428116f1cb53db60c9d7bf63bd7","68f6a1ccfdc2ff86124a0f0cbaae87b0b300068d8994026f8ffa58c900e2045a","f4e6ea532300daaa548e9cd54a20c45b9bd077a902cb307487eb9cced8455bd2","01c213379bdc93c1932320871e39662b9a500d29e92bc1a0d67b63231433f9db","36a9c257e015c440bb90392946dcc1e6b69a27df202196edc20a39c1ddb4d47a","aea356b8590f5a6069f7be2f38458783a7d2f9a529b03c3a1a516e295dd19657","7c72da023afce629b656536d5387503899a0eadce866e4545dc07b079e6a47dc","92f239d200a5ea5911719c2dbd9d54b47fe6af2c6caf2c21511ca749ff805780","1e1ef5a29991faab8d6a521d20f7c999155d986a9c2cd15476ee12e33bbc201d","47b5e144e20c734de67d86193414fd86eacc43db2e4c3cfa6a872e4524aa304e","e4380dae6e5f08e15aab0a154a427e6ef4f84cc46c2357861daf6ac40354ca91","14da83b08e106624de757637c9473b33a914972516fb20ba41b1389333b58ae0","948ce94b8e2a0fa9a1528901c4a0b29257a06e7960df93b8e6f53a23207c53a9","8c84a42f432fcd4eff1c0f43f1bcb00702eb4970398e74531bb6463f6fad62e0","5d8dd5af61be70b26897e365048f26653491a7ffd53ba8d8f89333b0f0f36e89","cef84bd49238289238976b7037065b8f46f02225299c8ef1b9428378c9b05304","d321fa92f4080957e2ceb1b81a8334167c6b08c2d793cc45bbc55ea51defa113","3c6de7af70c37c7076ca4cbe59eb8994e4412bb3e2833d30136a73521149633a","845812d5e831599b3f84f6d402c5bdaeb946b342af8433627467cb6e9a674439","a8ab1160734602524e306dfb776f3d4adac31792a6fbca416676b509f6c43bd2","b082dbe6bcd02e8bdfb73389ad2be4588e50bf98797fe9d1b8909cd57efd18d1","3df3d5a37e0e66f003e45dc16b0d1ca17eaed2d3b2fac20b340997d2e9541b3b","390a79f878bb3d6ce42f1884e1fa457076bb6951a7c0b787cbf98f1dfe8a3d7f","9d7f0913e488103e35d4e91dc58662820d15c01082d6dea85c9b2fd24533f4fd","1284e0edeb9bd29ecf74a82631ae88a617c495f967a1bc3e1624e2efab669af0","6cd2edb0a7a3a4f7b814ed35d3cdaa957cf5072fdce8fdba11c38087836a5d7a","e8db9af22c852b3d6a0749b94b21e887da566a9e0f3da56fe6cddd4ad519c6fa","ed04d6386a8ea75e07267855d67231864e2d43246b885a4ab2d414276c350ee6","436f75ba33ed879bc68e9c46a2db99d7c7ba9e94ab290d41e6b668317d7a027d","596141c29617965557573c38d820b1a706da09d213c9963eb7c353789620740c","327998b0a8535c4f3ef6ef4886e78cada63a7f359683e10a091afb060ca78ded","754b3fce2ca416258ab82984e79e3d862c6dcc1385f4c8d9e8319389a43e3b02","8b550cbd216fdd88e0ac42550565b80c12f117a091510fbb8e0f15cc206233fd","eb3e323a0f4fdadb287e14246cd72cc37ba2eaa7e27c1c9d534c3c5a6a92d80d","d86b54a95c860ad104024cbd7e97bf74050cb1335e9fa1c064b597ead1afe542","7912e4d60e4d71408b0d62705ab3bb73d480f945384bac53d8eaed949bfcc8cf","e5f9cd00b589017379dbedcb7cbc2ba14762b6aa28beb6944490df157034b9d6","7b9f8e64159683e4bb07522f010d62f8bb212f3ef76cb06ebc1dd97c74de0bed","815316bae083b69e7b456a361a3c5315642d019d3a1f6316b4ffca45819a40ea","8043b9fc5324568217185748d6debc00008bde81f97f4bdc3c6c21419ed18113","92f2995b314bb377d262bf2bd6362fa13382e0c11b731075d1cc9266ed330f83","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",45,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"fddb374d089da644d9f3c65b5f6b3639aa7b10634883cf4d34fff930aeeb11d4"}140{"parentUuid":"e2e8bba0-68fe-441e-a895-a7712d2f6ff1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvcLWhrLQDJb63qLR8","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":1093,"cache_read_input_tokens":54433,"output_tokens":334,"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":1093},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":285,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsvc9rSbDGcpeRCwQN2","requestRef":"6347dbc3-a075-467c-986b-3626624120cc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"acad3082-11af-48dc-9987-8d0fe09afa88","timestamp":"2026-10-30T05:35:31.530Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}141{"parentUuid":"acad3082-11af-48dc-9987-8d0fe09afa88","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvcLWhrLQDJb63qLR8","type":"message","role":"assistant","content":[{"type":"text","text":"Your message seems to have been cut off after \"The\". What would you like me to do?\n\nThe work is in the state I described. All outputs are written and reproducible, and the final gate run passes 64 of 65 checks. The one failure is the target-date check, which can't pass for any h=1 row while `target_date` uses the YYYY-MM-01 format `TASK.md` requires.\n\nIf you'd like the gate to pass, you'll have to choose; I won't change the format on my own:\n\n1. **Keep it as is (my recommendation).** It follows `TASK.md`, and the report explains the conflict.\n2. **Write `target_date` as the last day of the target month** (e.g. 2026-05-31 instead of 2026-05-01). The gate would then pass, but the file would break `TASK.md`'s format rule and no longer join directly to `first_release.csv` on the target month.\n3. **Something else**, such as rerunning a step, revising the model, or expanding a section of the report."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":1093,"cache_read_input_tokens":54433,"output_tokens":334,"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":1093},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsvc9rSbDGcpeRCwQN2","requestRef":"6347dbc3-a075-467c-986b-3626624120cc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5c677385-be00-4956-93f3-eb513f851bc7","timestamp":"2026-10-30T05:35:34.716Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}142{"type":"last-prompt","lastPrompt":"The","leafUuid":"5c677385-be00-4956-93f3-eb513f851bc7","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}143{"type":"mode","mode":"normal","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}144{"type":"atis-latch","atis":"","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}145{"type":"cost-state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","totalCostUSD":0.9351660000000002,"totalAPIDuration":230698,"totalAPIDurationWithoutRetries":230685,"totalToolDuration":10811,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":241752,"startTime":1793338291190,"modelUsage":{"claude-opus-5-5":{"inputTokens":50,"outputTokens":25737,"thinkingTokens":4698,"cacheReadInputTokens":750580,"cacheCreationInputTokens":54022,"cacheCreationEphemeral5mInputTokens":54022,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.9351660000000002}},"hasUnknownModelCost":false}146{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:35:36.326Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","content":"The"}147{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:35:36.327Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}148{"parentUuid":"5c677385-be00-4956-93f3-eb513f851bc7","isSidechain":false,"promptId":"2e014d5d-cda6-4ae3-acb3-1b8ea2ffbcea","type":"user","message":{"role":"user","content":"The"},"uuid":"42a7501e-11f5-43a7-9d40-321cf38dd408","timestamp":"2026-10-30T05:35:36.331Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":3},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}149{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"f09985bd-93ec-4a5a-89a7-cb5184fad6b8","timestamp":"2026-10-30T05:35:36.346Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","f238ba95539a99d3daf0e29621276816d32ea65940ea86c52f086849de9fb1bd","5091368c144595d34bc36632414133968c75ec8967ff421e2ebf06e79bfef535","8438fef5f84a18989cbb29a4c0351c587c98e428116f1cb53db60c9d7bf63bd7","68f6a1ccfdc2ff86124a0f0cbaae87b0b300068d8994026f8ffa58c900e2045a","f4e6ea532300daaa548e9cd54a20c45b9bd077a902cb307487eb9cced8455bd2","01c213379bdc93c1932320871e39662b9a500d29e92bc1a0d67b63231433f9db","36a9c257e015c440bb90392946dcc1e6b69a27df202196edc20a39c1ddb4d47a","aea356b8590f5a6069f7be2f38458783a7d2f9a529b03c3a1a516e295dd19657","7c72da023afce629b656536d5387503899a0eadce866e4545dc07b079e6a47dc","92f239d200a5ea5911719c2dbd9d54b47fe6af2c6caf2c21511ca749ff805780","1e1ef5a29991faab8d6a521d20f7c999155d986a9c2cd15476ee12e33bbc201d","47b5e144e20c734de67d86193414fd86eacc43db2e4c3cfa6a872e4524aa304e","e4380dae6e5f08e15aab0a154a427e6ef4f84cc46c2357861daf6ac40354ca91","14da83b08e106624de757637c9473b33a914972516fb20ba41b1389333b58ae0","948ce94b8e2a0fa9a1528901c4a0b29257a06e7960df93b8e6f53a23207c53a9","8c84a42f432fcd4eff1c0f43f1bcb00702eb4970398e74531bb6463f6fad62e0","5d8dd5af61be70b26897e365048f26653491a7ffd53ba8d8f89333b0f0f36e89","cef84bd49238289238976b7037065b8f46f02225299c8ef1b9428378c9b05304","d321fa92f4080957e2ceb1b81a8334167c6b08c2d793cc45bbc55ea51defa113","3c6de7af70c37c7076ca4cbe59eb8994e4412bb3e2833d30136a73521149633a","845812d5e831599b3f84f6d402c5bdaeb946b342af8433627467cb6e9a674439","a8ab1160734602524e306dfb776f3d4adac31792a6fbca416676b509f6c43bd2","b082dbe6bcd02e8bdfb73389ad2be4588e50bf98797fe9d1b8909cd57efd18d1","3df3d5a37e0e66f003e45dc16b0d1ca17eaed2d3b2fac20b340997d2e9541b3b","390a79f878bb3d6ce42f1884e1fa457076bb6951a7c0b787cbf98f1dfe8a3d7f","9d7f0913e488103e35d4e91dc58662820d15c01082d6dea85c9b2fd24533f4fd","1284e0edeb9bd29ecf74a82631ae88a617c495f967a1bc3e1624e2efab669af0","6cd2edb0a7a3a4f7b814ed35d3cdaa957cf5072fdce8fdba11c38087836a5d7a","e8db9af22c852b3d6a0749b94b21e887da566a9e0f3da56fe6cddd4ad519c6fa","ed04d6386a8ea75e07267855d67231864e2d43246b885a4ab2d414276c350ee6","436f75ba33ed879bc68e9c46a2db99d7c7ba9e94ab290d41e6b668317d7a027d","596141c29617965557573c38d820b1a706da09d213c9963eb7c353789620740c","327998b0a8535c4f3ef6ef4886e78cada63a7f359683e10a091afb060ca78ded","754b3fce2ca416258ab82984e79e3d862c6dcc1385f4c8d9e8319389a43e3b02","8b550cbd216fdd88e0ac42550565b80c12f117a091510fbb8e0f15cc206233fd","eb3e323a0f4fdadb287e14246cd72cc37ba2eaa7e27c1c9d534c3c5a6a92d80d","d86b54a95c860ad104024cbd7e97bf74050cb1335e9fa1c064b597ead1afe542","7912e4d60e4d71408b0d62705ab3bb73d480f945384bac53d8eaed949bfcc8cf","e5f9cd00b589017379dbedcb7cbc2ba14762b6aa28beb6944490df157034b9d6","7b9f8e64159683e4bb07522f010d62f8bb212f3ef76cb06ebc1dd97c74de0bed","815316bae083b69e7b456a361a3c5315642d019d3a1f6316b4ffca45819a40ea","8043b9fc5324568217185748d6debc00008bde81f97f4bdc3c6c21419ed18113","92f2995b314bb377d262bf2bd6362fa13382e0c11b731075d1cc9266ed330f83","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c","040575f800eea6056817cd61fa3462ae5af11f6553587b261b826dacd998edb3","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",47,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"aec6a2635bf2bcce5cd069c3e11a4c2e5c60c85ad8119d5abf3f9c4f3ba2101c"}150{"parentUuid":"42a7501e-11f5-43a7-9d40-321cf38dd408","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsw639YfYxT3n7nujfv","type":"message","role":"assistant","content":[{"type":"text","text":"Your message came through as just \"The\" again, so it looks like it's being cut off before it sends. Could you resend it in full?\n\nUntil then nothing has changed. All outputs are in `out/`, the final gate run passes 64 of 65 checks, and the one failure is the target-date check. I've kept `target_date` in the YYYY-MM-01 format `TASK.md` requires. If you want me to change that format, rerun something, or revise the model or report, just say which."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":339,"cache_read_input_tokens":55526,"output_tokens":148,"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":339},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsw5i4KTQ9YTEfLoSJX","requestRef":"f09985bd-93ec-4a5a-89a7-cb5184fad6b8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e235927c-22e6-454a-bc98-c6c12106dcf4","timestamp":"2026-10-30T05:35:39.351Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}151{"type":"last-prompt","lastPrompt":"The","leafUuid":"e235927c-22e6-454a-bc98-c6c12106dcf4","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}152{"type":"cost-state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","totalCostUSD":0.9509422000000002,"totalAPIDuration":233709,"totalAPIDurationWithoutRetries":233695,"totalToolDuration":10811,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":244793,"startTime":1793338291190,"modelUsage":{"claude-opus-5-5":{"inputTokens":54,"outputTokens":25885,"thinkingTokens":4698,"cacheReadInputTokens":806106,"cacheCreationInputTokens":54361,"cacheCreationEphemeral5mInputTokens":54361,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.9509422000000002}},"hasUnknownModelCost":false}153{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:35:40.949Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","content":"The"}154{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:35:40.950Z","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}155{"parentUuid":"e235927c-22e6-454a-bc98-c6c12106dcf4","isSidechain":false,"promptId":"464ada56-f5ce-44dc-a218-020b163396e8","type":"user","message":{"role":"user","content":"The"},"uuid":"91478db9-5e0f-488b-9ad0-aeb4c1342d9a","timestamp":"2026-10-30T05:35:40.954Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":4},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}156{"type":"api-request","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","id":"acabe97a-8a8c-4871-b194-46fc2126e59a","timestamp":"2026-10-30T05:35:40.970Z","version":"2.1.314","querySource":"sdk","shapeHash":"db39d13e5a7303458b548db37546d008f8ffb80b3ffcf3d9e74ea849977dfe72","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":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","f238ba95539a99d3daf0e29621276816d32ea65940ea86c52f086849de9fb1bd","5091368c144595d34bc36632414133968c75ec8967ff421e2ebf06e79bfef535","8438fef5f84a18989cbb29a4c0351c587c98e428116f1cb53db60c9d7bf63bd7","68f6a1ccfdc2ff86124a0f0cbaae87b0b300068d8994026f8ffa58c900e2045a","f4e6ea532300daaa548e9cd54a20c45b9bd077a902cb307487eb9cced8455bd2","01c213379bdc93c1932320871e39662b9a500d29e92bc1a0d67b63231433f9db","36a9c257e015c440bb90392946dcc1e6b69a27df202196edc20a39c1ddb4d47a","aea356b8590f5a6069f7be2f38458783a7d2f9a529b03c3a1a516e295dd19657","7c72da023afce629b656536d5387503899a0eadce866e4545dc07b079e6a47dc","92f239d200a5ea5911719c2dbd9d54b47fe6af2c6caf2c21511ca749ff805780","1e1ef5a29991faab8d6a521d20f7c999155d986a9c2cd15476ee12e33bbc201d","47b5e144e20c734de67d86193414fd86eacc43db2e4c3cfa6a872e4524aa304e","e4380dae6e5f08e15aab0a154a427e6ef4f84cc46c2357861daf6ac40354ca91","14da83b08e106624de757637c9473b33a914972516fb20ba41b1389333b58ae0","948ce94b8e2a0fa9a1528901c4a0b29257a06e7960df93b8e6f53a23207c53a9","8c84a42f432fcd4eff1c0f43f1bcb00702eb4970398e74531bb6463f6fad62e0","5d8dd5af61be70b26897e365048f26653491a7ffd53ba8d8f89333b0f0f36e89","cef84bd49238289238976b7037065b8f46f02225299c8ef1b9428378c9b05304","d321fa92f4080957e2ceb1b81a8334167c6b08c2d793cc45bbc55ea51defa113","3c6de7af70c37c7076ca4cbe59eb8994e4412bb3e2833d30136a73521149633a","845812d5e831599b3f84f6d402c5bdaeb946b342af8433627467cb6e9a674439","a8ab1160734602524e306dfb776f3d4adac31792a6fbca416676b509f6c43bd2","b082dbe6bcd02e8bdfb73389ad2be4588e50bf98797fe9d1b8909cd57efd18d1","3df3d5a37e0e66f003e45dc16b0d1ca17eaed2d3b2fac20b340997d2e9541b3b","390a79f878bb3d6ce42f1884e1fa457076bb6951a7c0b787cbf98f1dfe8a3d7f","9d7f0913e488103e35d4e91dc58662820d15c01082d6dea85c9b2fd24533f4fd","1284e0edeb9bd29ecf74a82631ae88a617c495f967a1bc3e1624e2efab669af0","6cd2edb0a7a3a4f7b814ed35d3cdaa957cf5072fdce8fdba11c38087836a5d7a","e8db9af22c852b3d6a0749b94b21e887da566a9e0f3da56fe6cddd4ad519c6fa","ed04d6386a8ea75e07267855d67231864e2d43246b885a4ab2d414276c350ee6","436f75ba33ed879bc68e9c46a2db99d7c7ba9e94ab290d41e6b668317d7a027d","596141c29617965557573c38d820b1a706da09d213c9963eb7c353789620740c","327998b0a8535c4f3ef6ef4886e78cada63a7f359683e10a091afb060ca78ded","754b3fce2ca416258ab82984e79e3d862c6dcc1385f4c8d9e8319389a43e3b02","8b550cbd216fdd88e0ac42550565b80c12f117a091510fbb8e0f15cc206233fd","eb3e323a0f4fdadb287e14246cd72cc37ba2eaa7e27c1c9d534c3c5a6a92d80d","d86b54a95c860ad104024cbd7e97bf74050cb1335e9fa1c064b597ead1afe542","7912e4d60e4d71408b0d62705ab3bb73d480f945384bac53d8eaed949bfcc8cf","e5f9cd00b589017379dbedcb7cbc2ba14762b6aa28beb6944490df157034b9d6","7b9f8e64159683e4bb07522f010d62f8bb212f3ef76cb06ebc1dd97c74de0bed","815316bae083b69e7b456a361a3c5315642d019d3a1f6316b4ffca45819a40ea","8043b9fc5324568217185748d6debc00008bde81f97f4bdc3c6c21419ed18113","92f2995b314bb377d262bf2bd6362fa13382e0c11b731075d1cc9266ed330f83","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c","040575f800eea6056817cd61fa3462ae5af11f6553587b261b826dacd998edb3","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c","9d7c848330e9fc97b83370db1de843c95d45f3906945676cfc39ff804c1d9c6a","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",49,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"db0d1eef9a984aed6d666a5e114e49ff91bfa32c680d72876ce6ea9f9a695b2d"}157{"parentUuid":"91478db9-5e0f-488b-9ad0-aeb4c1342d9a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswPJyVU5VtVvwiTnEW","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS5gYKEAgTGAI4AUIIdGhpbmtpbmcSDFsuci8BOaJIgotOZBoMObtcv9M9Bwbhhtg6IjCtxx8Ju9nxlcHvnUQj3AMVFYd0euxrVMsSLsBX9DXEZiawPk8Vh4x6s7/GyYnFGQgqgwaNGod0M24b/fWsbqr/5eQt0ySXUU7f3anmCezKYV6LMaE2lp3E1i7RU2hhb7AOIS75xfjUa2O92c4JJRuZ4l+xbHcuKaYlmEjgqTMC3vMwqUt8k4lJc8JNl0kDh/YeomuzNubxKKEsZGayYWCb34zDsfJGW+tA65UU6+IA4NaqVe8qAi8XlJj4YgxoRKQqCG+jx01xCUxXSh7Zs3BMsFQRrgiUJHf1ujpjHoMaDX2SeDDa/Yx+KA3oAjaQ18qAQ8bYIxQ+L9g6hzr1VgFjRMWEJ3WHishXhJ7/KlDobIB+Q4x/FcrWmmc3kXA+BUbc+AXxv375L2WMws4g359P9kF57n1SbIh1fqVfux2YLdV+QFjspwBs7iApRr9r6DFgZp7FW6vWl0zdHUmqAW/uSSW2HCZ59m/Y6F3f8JkpwMMLrIHyZeOsKVsJeOY5AnFJ6nye85ISztV65QL3CSkvWd+L/EX4gsWZkUNjvLonuGICspUtjbV9u8X4Gc5nXCuxjyEZ1R59uaZMFv+CXUG0i2qPG+x36PNtdOpFXnTk9FuH0/H8F2RI3Y24gfmyVashj926rfPgNit5BquXlUQaQjz6CRL7lNcfyACDTjC4XcI2p+eX0pkK0o0wQ7nMr0KlLUWavN+ySWx9VQ4jJXHbp8SYaotdJyeLTIhl7O09S3wIVZBBU2JAQ6ll8UJ6Ylr2jnhannJD8bsmEj9k3WvWSxXhJ7uHZRgZ2EtEAL0jXh1gqWCP8OCazYZrrEdgUyTKZja+krY2ioLE1bLmbQEYl8B5Jf3lGO85jrAdH5T8GVgwutUkndDp/yA/aKlJXzLxfdk13DbZP3+Zu5wEdDFppnbMhO73kbycsLu5HAa4mR0d905BP0HQgK8o2DfjSA3wm07szbm89rtWZ/cB1/MlyyX7zBKss718QncgYvwFknRo3BwWEMp/CkcLP0qQerdlSNl6Rah0ipmDMF3lZG7On/6voR9Uq8NGUTIgMBg8U4TJVrnuJ0+OVrt22s0iuQXqhwiiTXEYAQ=="}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":153,"cache_read_input_tokens":55865,"output_tokens":128,"output_tokens_details":{"thinking_tokens":29},"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":153},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":410,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXswP36QQa9nosvWqzjH","requestRef":"acabe97a-8a8c-4871-b194-46fc2126e59a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"543c364d-c4ac-471a-b141-8f02badff900","timestamp":"2026-10-30T05:35:42.134Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}158{"parentUuid":"543c364d-c4ac-471a-b141-8f02badff900","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswPJyVU5VtVvwiTnEW","type":"message","role":"assistant","content":[{"type":"text","text":"I've received only \"The\" for the third time, so your messages are probably being cut off before they send. Try sending it again, or put the request in a single short sentence.\n\nUntil I hear from you I'm leaving everything as it is: all outputs in `out/` are final, and the only gate failure is the target-date format conflict I described."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":153,"cache_read_input_tokens":55865,"output_tokens":128,"output_tokens_details":{"thinking_tokens":29},"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":153},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXswP36QQa9nosvWqzjH","requestRef":"acabe97a-8a8c-4871-b194-46fc2126e59a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cab241c2-e4fc-439f-9370-5d4ba2631158","timestamp":"2026-10-30T05:35:43.428Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0009","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","version":"2.1.314","gitBranch":"HEAD"}159{"type":"last-prompt","lastPrompt":"The","leafUuid":"cab241c2-e4fc-439f-9370-5d4ba2631158","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30"}160{"type":"cost-state","sessionId":"ef392a95-df5d-456f-ace3-bc495418df30","totalCostUSD":0.9654562000000002,"totalAPIDuration":236172,"totalAPIDurationWithoutRetries":236157,"totalToolDuration":10811,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":247287,"startTime":1793338291190,"modelUsage":{"claude-opus-5-5":{"inputTokens":58,"outputTokens":26013,"thinkingTokens":4727,"cacheReadInputTokens":861971,"cacheCreationInputTokens":54514,"cacheCreationEphemeral5mInputTokens":54514,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.9654562000000002}},"hasUnknownModelCost":false}161