till/managarten
1
0
Fork 0
mirror of https://github.com/Memo-2023/mana-monorepo.git synced 2026-05-23 04:46:42 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

feat(ai): workbench agent filter + proposal agent chip + docs (Phase 6+7)

Browse source 
Phase 6 — Multi-Agent observability:
- AI Workbench timeline gets a per-agent filter (dropdown with avatars)
  alongside module + mission. TimelineBucket gains agentId +
  agentDisplayName, projected off the bucket's first AI actor.
- Bucket header now leads with the agent's avatar + name (lookup via
  the live useAgents query so renamed agents reflect instantly) and
  falls back to Actor.displayName for deleted agents.
- AiProposalInbox card header replaces the generic Sparkle + "KI
  schlägt vor" with an agent chip "🤖 Cashflow Watcher schlägt vor"
  using the cached Actor.displayName. Ghost-agent label preserved
  via the cached displayName even when the agent record is gone.

Phase 7 — Docs:
- docs/architecture/COMPANION_BRAIN_ARCHITECTURE.md §22 added:
  data model, identity flow, tick gate order, Scene-Agent binding
  semantics, non-goals.
- services/mana-ai/CLAUDE.md status bumped to v0.5 (Multi-Agent
  Workbench) with the per-agent runner features + metrics listed.
- apps/mana/CLAUDE.md AI Workbench section rewritten to cover the
  Agent primitive, per-agent policy, scene lens, and the updated
  timeline header.

Multi-Agent rollout is code-complete end-to-end:
  Phase 0 Plan ✓  Phase 4 Policy-per-agent ✓
  Phase 1 Actor identity ✓  Phase 5 Agent UI + Scene lens ✓
  Phase 2 Agent CRUD ✓  Phase 6 Observability ✓
  Phase 3 Tick agent-aware ✓  Phase 7 Docs ✓

Tests: webapp svelte-check 0 errors, 0 warnings.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Till JS 2026-04-15 22:08:42 +02:00
parent 98668b69a2
commit 7c89eb625e
6 changed files with 162 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

23
services/mana-ai/CLAUDE.md
View file

@ -52,12 +52,23 @@ Was steht (Phase 0-2, Backend):
Was offen ist (Phase 3, Frontend):
- [ ] Webapp `MissionGrantDialog` + Consent-Flow im `/companion/missions`-Editor.
- [ ] Revoke-Button + "Mission → Datenzugriff" Audit-Tab in `/companion/workbench`.
- [ ] Scope-Change-UX: neue Records → Re-Consent-Prompt.
- [ ] `GET /internal/audit?missionId=` Endpoint (read-only) fuer die UI.
- [ ] Feature-Flag `PUBLIC_AI_MISSION_GRANTS=false` default + Rollout (till → beta → alpha).
- [ ] Produktions-Keypair generieren + in Mac-Mini Secrets ablegen.
- [x] Webapp `MissionGrantDialog` + Consent-Flow im Mission-Detail.
- [x] Revoke-Button + "Datenzugriff" Audit-Tab im Workbench.
- [x] `GET /api/v1/me/ai-audit` JWT-gated Endpoint live.
- [x] Feature-Flag `PUBLIC_AI_MISSION_GRANTS` + Cloudflare-Tunnel.
- [x] Produktions-Keypair auf Mac-Mini unter `secrets/mana-ai/`.
## Status: v0.5 (Multi-Agent Workbench)
Der Runner wird agent-bewusst — Missionen gehoeren einem benannten Agent, Policy und Memory leben auf dem Agent, Concurrency + Budget werden pro Agent respektiert.
- [x] `mana_ai.agent_snapshots` Tabelle (LWW-Projektion von `agents` aus `sync_changes`).
- [x] `refreshAgentSnapshots` + `loadActiveAgents` parallel zum Mission-Snapshot-Refresh.
- [x] `ServerMission.agentId` + `ServerAgent.policy` durchgereicht.
- [x] Tick resolvt pro Mission den Agent, gated `archived`/`paused`/`concurrency`, schreibt iteration unter `makeAgentActor(agent)` Identitaet.
- [x] `<agent_context>` Prompt-Block mit plaintext `role` + `systemPrompt` + `memory` (ciphertext wird uebersprungen).
- [x] `filterToolsByAgentPolicy` schneidet `deny`-Tools raus bevor der Planner sie sieht.
- [x] Metrik `mana_ai_agent_decisions_total{decision}`.
## Port: 3067