2 Commits

Author	SHA1	Message	Date
Nico	4c412d3c4b	v0.14.4: Interpreter wired in v2, tool_call convention, Haiku models, UI fix ... - Wire Interpreter into v2 pipeline (after Thinker tool_output, before Output) - Rename tool_exec -> tool_call everywhere (consistent convention across v1/v2) - Switch Director v1+v2 to anthropic/claude-haiku-4.5 (was opus, reserved) - Fix UI apply_machine_ops crash when states are strings instead of dicts - Fix runtime_test.py async poll to match on message ID (prevent stale results) - Add traceback to pipeline error logging Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-03-29 06:06:13 +02:00
Nico	5f447dfd53	v0.14.0: v2 Director-drives architecture + 3-pod K8s split ... Architecture: - director_v2: always-on brain, produces DirectorPlan with tool_sequence - thinker_v2: pure executor, runs tools from DirectorPlan - interpreter_v1: factual result summarizer, no hallucination - v2_director_drives graph: Input -> Director -> Thinker -> Output Infrastructure: - Split into 3 pods: cog-frontend (nginx), cog-runtime (FastAPI), cog-mcp (SSE proxy) - MCP survives runtime restarts (separate pod, proxies via HTTP) - Async send pipeline: /api/send/check -> /api/send -> /api/result with progress - Zero-downtime rolling updates (maxUnavailable: 0) - Dynamic graph visualization (fetched from API, not hardcoded) Tests: 22 new mocked unit tests (director_v2: 7, thinker_v2: 8, interpreter_v1: 7) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-03-29 04:17:44 +02:00