phase3: gate passed — live POC vs claude-sonnet-5 (deny path + happy path), checkpoint in PLAN.md
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Showing 1 changed file with +6 and −4
modified
docs/PLAN.md
+6 −4
@@ -21,10 +21,12 @@ | ||
| 21 | 21 | **Phase 2 checkpoint (2026-07-30):** Build clean, zero warnings. Key names locked: `ProviderClient`, `ChatRequest`/`ChatEvent`, `ToolSpec`/`ToolCall`/`ToolResult`/`ToolChoice`, `StopReason`, `Tool`, `AgentStep`, `PolicyEngine`, `AuditLog`. Message model round-trips tool calls/results for both wire dialects. |
| 22 | 22 | |
| 23 | 23 | ## Phase 3 — Agent Engine (loop, memory, tools+safety) → CLI POC gate |
| 24 | −- [ ] 3.C ExecutionService (actor, streaming Process), full PolicyEngine rule engine + risk classifier, ShellTool, AppleScriptTool, FileTools, ToolRegistry, WorkspaceManager | |
| 25 | −- [ ] 3.A AgentLoop actor + Planner + LoopGuard + Transcript + system prompt | |
| 26 | −- [ ] 3.B MemoryManager (compaction, output offloading, MEMORY.md) | |
| 27 | −- [ ] GATE: CLI POC `ZyquoAgent --run "…"` executes a real multi-tool task end-to-end through the policy gate | |
| 24 | +- [x] 3.C ExecutionService (actor, streaming Process, SIGTERM→SIGKILL timeouts, cancellation), full PolicyEngine deny→ask→allow engine (quote-aware subcommand parsing, $()/backtick extraction, wrapper stripping, always-ask circuit breakers, remembered rules that can't override breakers), bash/osascript/5 file tools, ToolRegistry, WorkspaceManager (tracking+checkpoints) — `--verify-policy` 38/38 PASS | |
| 25 | +- [x] 3.A AgentLoop actor (stop_reason-keyed, retry-once on transient, parallel calls only when all read-only) + Planner (`update_plan` internal tool, .zyquo/plan.json) + LoopGuard (50 steps/500k tok/30min; repetition N=3, stall M=6; pause-not-abort) + Transcript (.zyquo/transcript.json) + sectioned system prompt | |
| 26 | +- [x] 3.B MemoryManager (85% compaction w/ same-model summarization + mechanical fallback, keep plan+MEMORY.md+last-6-steps verbatim, 10-step thrash guard; >8KB outputs offloaded to .zyquo/outputs/ with stubs) | |
| 27 | +- [x] GATE: `--run-mock` proves loop end-to-end offline; LIVE POC vs claude-sonnet-5: `--run "create ~/zqtest + hello.txt …"` → policy correctly auto-DENIED outside-workspace write under --yes, model adapted gracefully; with --allow-destructive: executed, verified, completed in 2 steps / 4.4s. Transcript + audit confirmed on disk. | |
| 28 | + | |
| 29 | +**Phase 3 checkpoint (2026-07-30):** Engine complete and proven live. Build 0 warnings; policy self-check 38/38; safety contract demonstrated against a real model (deny path AND happy path). ~/zqtest cleaned up after verification. | |
| 28 | 30 | |
| 29 | 31 | ## Phase 4 — Design system & UI spec (ZyquoTheme violet) |
| 30 | 32 | |
| 31 | 33 | |