Commit Graph

28 Commits

Author SHA1 Message Date
bc48abd970 feat: standardize llama.cpp backend for sovereign local inference (#1123) 2026-04-15 21:24:01 -04:00
428a9da3bd feat: standardize llama.cpp backend for sovereign local inference (#1123) 2026-04-15 21:24:01 -04:00
Alexander Whitestone
ec2a427a7a feat: implement A2A protocol for fleet-wizard delegation (#1122)
Implements Google Agent2Agent Protocol v1.0 with full fleet integration:

## Phase 1 - Agent Card & Discovery
- Agent Card types with JSON serialization (camelCase, Part discrimination by key)
- Card generation from YAML config (~/.hermes/agent_card.yaml)
- Fleet registry with LocalFileRegistry + GiteaRegistry backends
- Discovery by skill ID or tag

## Phase 2 - Task Delegation
- Async A2A client with JSON-RPC SendMessage/GetTask/ListTasks/CancelTask
- FastAPI server with pluggable task handlers (skill-routed)
- CLI tool (bin/a2a_delegate.py) for fleet delegation
- Broadcast to multiple agents in parallel

## Phase 3 - Security & Reliability
- Bearer token + API key auth (configurable per agent)
- Retry logic (max 3 retries, 30s timeout)
- Audit logging for all inter-agent requests
- Error handling per A2A spec (-32001 to -32009 codes)

## Test Coverage
- 37 tests covering types, card building, registry, server integration
- Auth (required + success), handler routing, error handling

Files:
- nexus/a2a/ (types.py, card.py, client.py, server.py, registry.py)
- bin/a2a_delegate.py (CLI)
- config/ (agent_card.example.yaml, fleet_agents.json)
- docs/A2A_PROTOCOL.md
- tests/test_a2a.py (37 tests, all passing)
2026-04-15 21:24:01 -04:00
Timmy (NEXUSBURN)
4215ef786f feat: fleet audit tool — deduplicate agents, one identity per machine
Closes #1144. Builds a fleet audit pipeline that detects duplicate
agent identities, ghost accounts, and authorship ambiguity across
all machines.

Deliverables:

bin/fleet_audit.py — Full audit tool with four checks:
  - Identity registry validation (one name per machine, unique gitea_user)
  - Git authorship audit (detects ambiguous committers from branch names)
  - Gitea org member audit (finds ghost accounts with zero activity)
  - Cross-reference registry vs fleet-routing.json (orphan/location mismatch)

fleet/identity-registry.yaml — Canonical identity registry:
  - 8 active agents (timmy, allegro, ezra, bezalel, bilbobagginshire,
    fenrir, substratum, claw-code)
  - 7 ghost/deprecated accounts marked inactive
  - Rules: one identity per machine, unique gitea_user, required fields

tests/test_fleet_audit.py — 11 tests covering all validation rules.

Usage:
  python3 bin/fleet_audit.py                  # full audit -> JSON
  python3 bin/fleet_audit.py --identity-check # registry only
  python3 bin/fleet_audit.py --git-authors    # authorship only
  python3 bin/fleet_audit.py --report out.json # write to file
2026-04-15 21:24:01 -04:00
61c24c390b purge: remove Anthropic from the-nexus fleet + deepdive (#1346) 2026-04-15 21:24:01 -04:00
1154460919 Add swarm governor — prevents PR pileup across the org 2026-04-15 21:24:01 -04:00
Alexander Whitestone
6f9b2cd299 fix: closes #865 2026-04-15 21:24:00 -04:00
perplexity
67adf79757 [IaC] Fix .gitignore — recursive __pycache__ exclusion + purge 22 cached .pyc files
Closes #1249

- Replace path-specific __pycache__ entries with recursive **/__pycache__/
- Add *.pyc and *.pyo globs
- Remove 22 tracked .pyc files from bin/, nexus/evennia_mempalace/,
  nexus/mempalace/, and nexus/mnemosyne/
- Reorganize .gitignore with section comments for clarity
2026-04-12 03:49:50 +00:00
Alexander Whitestone
6f1264f6c6 WIP: Browser smoke tests (issue #686)
Some checks failed
CI / test (pull_request) Failing after 9s
CI / validate (pull_request) Failing after 12s
Review Approval Gate / verify-review (pull_request) Failing after 4s
2026-04-10 21:17:44 -04:00
7a2a48f4f1 fix: [MONITORING] Integrate Kimi Heartbeat status into Nexus Watchdog (#1192)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Staging Verification Gate / verify-staging (push) Has been cancelled
2026-04-11 00:21:12 +00:00
Alexander Whitestone
ef74536e33 feat: add edge-tts as zero-cost voice output provider
Some checks failed
CI / test (pull_request) Failing after 33s
CI / validate (pull_request) Failing after 26s
Review Approval Gate / verify-review (pull_request) Failing after 5s
- Add EdgeTTSAdapter to bin/deepdive_tts.py (provider key: "edge-tts")
  default voice: en-US-GuyNeural, no API key required
- Add EdgeTTS class to intelligence/deepdive/tts_engine.py
- Update HybridTTS to try edge-tts as fallback between piper and elevenlabs
- Add --voice-memo flag to bin/night_watch.py for spoken nightly reports
- Add edge-tts>=6.1.9 to requirements.txt
- Create docs/voice-output.md documenting all providers and fallback chain
- Add tests/test_edge_tts.py with 17 unit tests (all mocked, no network)

Fixes #1126

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-08 06:29:26 -04:00
34ec13bc29 [claude] Poka-yoke cron heartbeats: write, check, and report (#1096) (#1107)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-07 14:44:05 +00:00
ea3cc6b393 [claude] Poka-yoke cron heartbeats — make silent failures impossible (#1096) (#1102)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-07 14:38:55 +00:00
Groq Agent
9fd59a64f0 [groq] [QA][POLICY] Branch Protection + Mandatory Review Policy for All Repos (#918) (#971)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
CI / test (pull_request) Failing after 8s
CI / validate (pull_request) Failing after 3s
2026-04-07 08:18:18 +00:00
Groq Agent
7fe92958dd [groq] [QA][POLICY] Branch Protection + Mandatory Review Policy for All Repos (#918) (#948)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-07 07:07:58 +00:00
Groq Agent
907c021940 [groq] [QA][POLICY] Branch Protection + Mandatory Review Policy for All Repos (#918) (#935)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-07 06:47:03 +00:00
3b4c5e7207 [claude] Add /help page for Nexus web frontend (#833) (#887)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-06 17:52:10 +00:00
0b57145dde [timmy] Add webhook health dashboard (#855) (#885)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-06 15:51:22 +00:00
Allegro (Burn Mode)
6df57dcec0 fix(watchdog): repair malformed Gitea URL after domain migration
Some checks failed
CI / validate (pull_request) Failing after 11s
2026-04-06 15:23:35 +00:00
Ezra (Archivist)
00600a7e67 [BURN] Deep Dive proof-of-life, fleet context fix, dry-run repair
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
- Fix fleet_context.py env-var substitution for 0c16baadaebaaabc2c8390f35ef5e9aa2f4db671
- Remove non-existent wizard-checkpoints from config.yaml
- Fix bin/deepdive_orchestrator.py dry-run mock items
- Add PROOF_OF_LIFE.md with live execution output including fleet context

Progresses #830
2026-04-05 18:42:18 +00:00
cbf05e1fc8 [ezra] Phase 2: Relevance scoring for Deep Dive (#830)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-05 05:16:33 +00:00
Ezra (Archivist)
2b06e179d1 [deep-dive] Complete #830 implementation scaffold
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Phase 3 (Synthesis):
- deepdive_synthesis.py: LLM-powered briefing generation
- Supports OpenAI (gpt-4o-mini) and Anthropic (claude-3-haiku)
- Fallback to keyword summary if LLM unavailable
- Intelligence briefing format: Headlines, Deep Dive, Bottom Line

Phase 4 (TTS):
- TTS integration in orchestrator
- Converts markdown to speech-friendly text
- Configurable provider (openai/elevenlabs/piper)

Phase 5 (Delivery):
- Enhanced delivery.py with --text and --chat-id/--bot-token overrides
- Supports text-only and audio+text delivery
- Full Telegram Bot API integration

Orchestrator:
- Complete 5-phase pipeline
- --dry-run mode for testing
- State management in ~/the-nexus/deepdive_state/
- Error handling with fallbacks

Progresses #830 to implementation-ready status
2026-04-05 04:43:22 +00:00
a0d9a79c7d [ezra] Add Phase 5 Telegram voice delivery pipeline #830
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-05 03:45:07 +00:00
dde9c74fa7 [ezra] Add Phase 4 TTS pipeline with multi-adapter support #830
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-05 03:45:06 +00:00
75fa66344d [ezra] Deep Dive scaffold #830: deepdive_orchestrator.py
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-05 01:51:03 +00:00
9ba00b7ea8 [ezra] Deep Dive scaffold #830: deepdive_aggregator.py
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
2026-04-05 01:51:02 +00:00
8645798ed4 feat: Evennia-Nexus Bridge v2 — Live Event Streaming (#804) (#807)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Co-authored-by: Allegro <allegro@hermes.local>
Co-committed-by: Allegro <allegro@hermes.local>
2026-04-04 01:39:38 +00:00
d32baa696b [watchdog] The Eye That Never Sleeps — Nexus Health Monitor (#794)
Some checks failed
Deploy Nexus / deploy (push) Has been cancelled
Co-authored-by: Google AI Agent <gemini@hermes.local>
Co-committed-by: Google AI Agent <gemini@hermes.local>
2026-04-04 01:36:56 +00:00