4 Commits

Author SHA1 Message Date
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
Nico
a2bc6347fc v0.13.0: Graph engine, versioned nodes, S3* audit, DB tools, Cytoscape
Architecture:
- Graph engine (engine.py) loads graph definitions, instantiates nodes
- Versioned nodes: input_v1, thinker_v1, output_v1, memorizer_v1, director_v1
- NODE_REGISTRY for dynamic node lookup by name
- Graph API: /api/graph/active, /api/graph/list, /api/graph/switch
- Graph definition: graphs/v1_current.py (7 nodes, 13 edges, 3 edge types)

S3* Audit system:
- Workspace mismatch detection (server vs browser controls)
- Code-without-tools retry (Thinker wrote code but no tool calls)
- Intent-without-action retry (request intent but Thinker only produced text)
- Dashboard feedback: browser sends workspace state on every message
- Sensor continuous comparison on 5s tick

State machines:
- create_machine / add_state / reset_machine / destroy_machine via function calling
- Local transitions (go:) resolve without LLM round-trip
- Button persistence across turns

Database tools:
- query_db tool via pymysql to MariaDB K3s pod (eras2_production)
- Table rendering in workspace (tab-separated parsing)
- Director pre-planning with Opus for complex data requests
- Error retry with corrected SQL

Frontend:
- Cytoscape.js pipeline graph with real-time node animations
- Overlay scrollbars (CSS-only, no reflow)
- Tool call/result trace events
- S3* audit events in trace

Testing:
- 167 integration tests (11 test suites)
- 22 node-level unit tests (test_nodes/)
- Three test levels: node unit, graph integration, scenario

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 00:18:45 +01:00
Nico
b6ca02f864 v0.9.2: dedicated UI node, strict node roles, markdown rendering
6-node pipeline: Input -> Thinker -> Output (voice) + UI (screen) in parallel

- Output: text only (markdown, emoji). Never emits HTML or controls.
- UI: dedicated node for labels, buttons, tables. Tracks workspace state.
  Replaces entire workspace on each update. Runs parallel with Output.
- Input: strict one-sentence perception. No more hallucinating responses.
- Thinker: controls removed from prompt, focuses on reasoning + tools.
- Frontend: markdown rendered in chat (bold, italic, code blocks, lists).
  Label control type added. UI node meter in top bar.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-28 14:12:15 +01:00
Nico
7458b2ea35 v0.8.0: refactor agent.py into modular package
Split 1161-line monolith into agent/ package:
auth, llm, types, process, runtime, api, and
nodes/ (base, sensor, input, output, thinker, memorizer).
No logic changes — pure structural split.
uvicorn agent:app entrypoint unchanged.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-28 01:36:41 +01:00