gitea/agent-runtime
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
19 Commits 1 Branch 0 Tags
Commit Graph

10 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
3d71c651fc v0.10.0: test framework with markdown testcases and web UI 
- testcases/*.md: declarative test definitions (send, expect_response,
  expect_state, expect_actions, action)
- runtime_test.py: standalone runner + pytest integration via conftest.py
- /tests route: web UI showing last run results from results.json
- /api/tests: serves results JSON
- Two initial testcases: counter_state (UI actions) and pub_conversation
  (multi-turn, language switch, tool use, memorizer state)
- pub_conversation: 19/20 passed on first run
- Fix nm-text vertical overflow in node metrics bar

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 15:36:19 +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
f6939d47f5 v0.8.5: smart Output renderer + awareness panel 
Output node upgraded from dumb echo to device-aware renderer:
- Knows it's rendering to HTML/browser, uses markdown formatting
- Receives full ThoughtResult (response + tool output + controls)
- Always in pipeline: Input perceives, Thinker reasons, Output renders
- Keeps user's language, weaves tool results into natural responses

Awareness panel (3-column layout):
- State: mood, topic, language, facts from Memorizer
- Sensors: clock, idle, memo deltas from Sensor ticks
- Processes: live cards with cancel during tool execution
- Workspace: docked controls (tables/buttons) persist across messages

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 02:02:41 +01:00
Nico
231f81bc52 v0.8.2: fix pipeline — skip Output for tools, process HUD, inline controls, structured actions 
- Thinker tool results stream directly to user, skipping Output node (halves latency)
- ProcessManager process_start/process_done events render as live cards in chat
- UI controls sent before response text, not after
- Button clicks route to handle_action(), skip Input, go straight to Thinker
- Fix Thinker model: gemini-2.5-flash-preview -> gemini-2.5-flash (old ID expired)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 01:43:07 +01:00
Nico
20363a1f2f v0.7.2: UI controls + ProcessManager + Thinker upgrade (WIP) 
- ProcessManager: observable tool execution with start/stop/status
- UI controls protocol: buttons, tables, process cards
- Frontend renders controls in chat, clicks route back as actions
- Thinker upgraded to gemini-2.5-flash-preview
- Auto-detect SQL/python/tool_code blocks for execution
- SQL blocks auto-wrapped in Python sqlite3 script
- WIP: tool execution path needs tuning, controls not yet triggered

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 01:16:26 +01:00
Nico
8b69e6dd0d v0.6.2: Thinker node with python tool execution (S3 Control) 
- ThinkerNode: reasons about perception, decides tool use vs direct answer
- Python tool: subprocess execution with 10s timeout
- Auto-detects python code blocks in LLM output and executes them
- Tool call/result visible in trace + HUD
- Thinker meter in frontend (token budget: 4K)
- Flow: Input (perceive) -> Thinker (reason + tools) -> Output (speak)
- Tested: math (42*137=5754), SQLite (create+query), time, greetings

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 01:04:22 +01:00
Nico
5c7aece397 v0.5.5: node token meters in frontend 
- Per-node context fill bars (input/output/memorizer/sensor)
- Color-coded: green <50%, amber 50-80%, red >80%
- Sensor meter shows tick count + latest deltas
- Token info in trace context events

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 00:51:43 +01:00
Nico
569a6022fe cognitive agent runtime v0.4.6: 3-node graph + Zitadel auth + K3s deploy 
- Input/Output/Memorizer nodes with OpenRouter (Gemini Flash)
- Zitadel OIDC auth with PKCE flow, service token for Titan
- SSE event stream + poll endpoint for external observers
- Identity from Zitadel userinfo, listener context in Input prompt
- Trace logging to file + SSE broadcast
- K3s deployment on IONOS with Let's Encrypt TLS
- Frontend: chat + trace view, OIDC login

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-27 23:21:51 +01:00