Spaces:
Runtime error
Runtime error
Commit History
-
docs(plan): errand_runner redesign implementation plan (6 phases, TDD tasks)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>81302ae
-
docs(plan): errand_runner Plans 2-4 (scenario, discovery+memory director, web)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>2a07439 -
docs(plan): errand_runner foundations (Plan 1/4) — additive engine/runtime/memory primitives
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>4d567cb -
docs(plan): take_a_seat implementation plan (TDD, 5 tasks)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>a750970
-
docs: implementation plan for multi-agent memory + predator visuals (+ spec resource_race turn-order fix)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>2e262ce -
docs(plan): proteus game/web restructure implementation plan
Phased plan: parallel preservation docs (0), serial atomic move+codemod (1), gate+commit (2), cli split (3), parallel doc updates + cleanup (4), optional test mirroring (5). Honest parallelism map: mutation is serial, docs+verify are parallel. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>8979c5f -
docs: implementation plan for memory replay + pack_evade walls
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>d8b4331 -
docs(plan): web LLM spectating — 7-task TDD implementation plan
6dafaf5 -
docs(plan): pack_evade scenario — 7-task TDD implementation plan
c4fd26d -
docs(cp8): agentness-eval plan (5 passes + auto-GIF) + HANDOFF Next
Three-layer eval (survival / distance / persona-maintenance) per the user's predator-agentness spec. Six staged handoff units: Stage0 auto-GIF + Stage1 metric-only + Stage2 persona-ref + Stage4 hidden-weight memory are TDD-ready (full code/tests, additive, 152-safe); Stage3 simultaneous-resolver and Stage5 multi-feature personas are design-gated (need their own brainstorm+sub-spec). Implementation deferred to next session(s). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>9a23797 -
docs(cp7): TDD plan — memory pre-roll (4 stages, 11 tasks)
Stage1 memory.py models+persistence+renderer; Stage2 memory_gen self-play + scenario memory_brief; Stage3 SessionTrace.memory_ref + hybrid SessionRunner injection; Stage4 CLI `memory` + `run --memory` + Ollama smoke. Each stage is a clean handoff boundary; full code in every TDD step; 127 baseline guarded by None/"" defaults throughout. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>64ce939 -
docs(web): interactive color-grid web play — implementation plan (10 tasks, TDD)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>ddd1836
-
docs(cp6): implementation plan — 9 TDD tasks (layouts + category eval + compare)
e45f4f7 -
docs(cp5): implementation plan — HumanAgent + viz (11 TDD tasks)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>2dae457 -
docs: CP4 implementation plan (real-provider CLI)
b93aa9b -
docs: CP0-CP3 implementation plan (deterministic end-to-end core)
17 TDD tasks: package skeleton + arc_grid vendoring (CP0), grid port + determinism/handover invariant (CP1), slim Agent + FakeProvider (CP2), SessionRunner + trace + metrics + golden integration (CP3), handoff record. Runs fully offline (FakeProvider). CP4-CP6 get follow-up plans. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>26c6421