Second phase of the Multi-Agent Workbench rollout (docs/plans/
multi-agent-workbench.md). Builds on Phase 1's identity-aware Actor.
Adds the Agent primitive — a named AI persona that owns Missions,
carries its own policy + memory, and (from Phase 3 on) drives the
Workbench lens. Everything is wired; a single user currently has one
"Mana" default agent until the UI (Phase 5) lets them create more.
Shared types (@mana/shared-ai):
- agents/types.ts: Agent, AgentState, DEFAULT_AGENT_ID/NAME constants
- policy/types.ts: AiPolicy + PolicyDecision (moved from webapp so
Agent.policy can reference it without a runtime dep on the web app)
- missions/types.ts: new optional Mission.agentId field
Webapp data layer:
- data/ai/agents/{types,store,queries,bootstrap}.ts
- Dexie schema v19 adds `agents` table (indexes on state, name,
[state+name]); sync registered under the existing ai app-id
- Encryption registry: agents.systemPrompt + agents.memory encrypted;
name/role/avatar/policy stay plaintext for search + UI rendering
- DuplicateAgentNameError thrown at write time (not a Dexie unique
index — bootstrap races between tabs would otherwise hit
ConstraintError; store now resolves via getOrCreateAgent)
- bootstrap.ts: ensureDefaultAgent + backfillMissionsAgentId. The
backfill runs once per device (localStorage sentinel) so missions
that pre-date the rollout get stamped with the default agent's id.
Called fire-and-forget from startMissionTick() during layout init.
Runner threading (already merged into d5c351d63 via Till's debug-log
commit that picked up my uncommitted edits):
- runner.ts + server-iteration-staging.ts now resolve mission.agentId
to the real Agent and build makeAgentActor with agent.name as
displayName. Missing-agent fallback keeps using LEGACY_AI_PRINCIPAL
so historical writes still attribute cleanly.
Tests: shared-ai 26/26, mana-ai 35/35, svelte-check 0 errors.
Agent store vitest suite is present but blocked by a pre-existing
\$lib alias resolution issue in the webapp vitest config that
predates this phase (proposals/store.test.ts is broken the same way
on HEAD). Will address separately.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Foundation for the Multi-Agent Workbench roadmap
(docs/plans/multi-agent-workbench.md). Every event, record, and
sync_changes row now carries a principal identity + cached display
name in addition to the three-kind discriminator.
Shape change (source of truth in @mana/shared-ai):
Before: { kind: 'user' | 'ai' | 'system', ...kind-specific fields }
After: discriminated union on kind, with
- common: principalId, displayName
- 'user': principalId = userId
- 'ai': principalId = agentId + missionId/iterationId/rationale
- 'system': principalId = one of SYSTEM_* sentinel strings
('system:projection', 'system:mission-runner', etc.)
Key design calls (from the plan's Q&A):
- System sub-sources get distinct principalIds (not a shared 'system'
bucket) — lets Workbench filter + revert distinguish projection
writes from migration writes from server-iteration writes
- displayName cached on the record so renaming an agent doesn't
rewrite history
- normalizeActor() compat shim fills principalId/displayName on
legacy rows with 'legacy:*' sentinels so historical events never
crash the timeline
New exports:
- BaseActor / UserActor / AiActor / SystemActor (narrowed types)
- makeUserActor, makeAgentActor, makeSystemActor (factories with
typed return)
- SYSTEM_PROJECTION, SYSTEM_RULE, SYSTEM_MIGRATION, SYSTEM_STREAM,
SYSTEM_MISSION_RUNNER (principalId constants)
- LEGACY_USER_PRINCIPAL, LEGACY_AI_PRINCIPAL, LEGACY_SYSTEM_PRINCIPAL
- isUserActor / isFromMissionRunner predicates
Webapp:
- data/events/actor.ts now re-exports from shared-ai, keeps runtime
ambient-context (runAs, getCurrentActor) local
- bindDefaultUser(userId, displayName) lets the auth layer replace
the legacy placeholder with the real logged-in user actor at login
- Mission runner + server-iteration-staging stamp LEGACY_AI_PRINCIPAL
as the agentId placeholder — Phase 2 will thread the real agent
- Streaks projection uses makeSystemActor(SYSTEM_PROJECTION)
- All test fixtures migrated to factories
Service:
- mana-ai/db/iteration-writer.ts stamps makeSystemActor(
SYSTEM_MISSION_RUNNER) instead of the old { kind:'system',
source:'mission-runner' } shape. Phase 3 will switch this to an
agent actor per mission.
Tests: 26 shared-ai + 21 webapp vitest + 35 mana-ai — all green.
svelte-check: 0 errors, 0 warnings.
No behavior change; purely a type + shape upgrade. Old sync_changes
rows parse via the normalizeActor compat shim at read time.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Closes the "iteration is running, no feedback" black hole. The user now
sees, per running iteration:
⏳ Frage Planner · frage Planner an ⏱ 23s
[Abbrechen]
Phases (\`IterationPhase\`):
resolving-inputs → calling-llm → parsing-response →
staging-proposals → finalizing
The runner advances through these via \`setIterationPhase\` between each
await, writing currentPhase + phaseDetail + phaseStartedAt onto the
iteration. UI reads them via Dexie liveQuery — no polling.
Cancel:
- \`requestIterationCancel\` writes cancelRequested=true on the iteration
- runner polls \`isCancelRequested\` between every phase + per stage step
- cancellation finalises as \`failed\` with summary \`'cancelled by user'\`
- UI button is disabled + relabelled "Wird abgebrochen…" until the next
poll picks it up
Hard timeout: 90 s wall-clock per iteration via Promise.race against a
CancelledError. Wedged backends (e.g. flaky mana-llm) fail fast with
"timeout after 90s" instead of sitting in \`running\` forever.
Elapsed counter is a \$state variable ticking once a second, scoped to
the ListView component — Dexie isn't touched. Auto-cleaned on
component destroy.
shared-ai re-exports \`IterationPhase\` so server-side mana-ai can
inspect the same phase enum (no consumer there yet, but the type is
ready for the run-status endpoint planned in HEALTH page).
77/77 webapp tests still green; svelte-check clean.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Foundation for Phase 2+ of the Mission Key-Grant flow: lets mana-ai
execute missions that depend on encrypted inputs (notes/tasks/events/
journal/kontext) without needing an open browser tab. Opt-in per
mission, Zero-Knowledge users excluded.
- Canonical HKDF-SHA256 derivation (scope-bound via tables + recordIds
in the HKDF info string → scope changes invalidate the grant
cryptographically, not just via a runtime check)
- Mission.grant field on the shared Mission type
- Golden snapshot + drift-guard test so webapp wrap path and mana-auth
wrap endpoint can't silently diverge
- Ideas backlog at docs/future/AI_AGENTS_IDEAS.md
- Full rollout plan at docs/plans/ai-mission-key-grant.md
- COMPANION_BRAIN_ARCHITECTURE.md §21 captures the flow + privacy
guarantees + non-goals
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Makes the webapp's AI policy and the server's tool allow-list physically
impossible to drift. Adds the missing entries the guard caught on first
run: `complete_tasks_by_title`, `visit_place`, `undo_drink` now have
parameter schemas server-side too.
- `packages/shared-ai/src/policy/proposable-tools.ts`
- `AI_PROPOSABLE_TOOL_NAMES` as `const` array + literal union type
- `AI_PROPOSABLE_TOOL_SET` for set-membership checks
- Webapp `DEFAULT_AI_POLICY` derives its `propose` entries from the
shared list via `Object.fromEntries(...)` — adding a tool there is now
a one-line change in `@mana/shared-ai`
- mana-ai `AI_AVAILABLE_TOOLS`: module-load assertion compares its
hardcoded names against `AI_PROPOSABLE_TOOL_SET` and throws with a
pointed error on drift (extras in one direction, missing in the
other). Service refuses to start on mismatch — better than silent
degradation.
- Bun test (`tools.test.ts`) runs the same contract plus sanity checks
(non-empty description, required params carry docs). Vitest policy
test adds the symmetric check on the webapp side.
All three runtimes now green: webapp 66/66, shared-ai 2/2,
mana-ai 9/9 Bun tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Single source of truth for AI Workbench types shared between the webapp
(Vite/SvelteKit) and the server-side mana-ai Bun service. Prevents the
two runtimes from drifting on prompt shape or mission structure.
- `@mana/shared-ai` package:
- `actor.ts` — Actor union (user | ai | system) + helpers, mirrors the
webapp's runtime type so server-side consumers parse incoming actors
without re-declaring
- `missions/types.ts` — Mission, MissionCadence, MissionInputRef,
MissionIteration, PlanStep, MissionState. Adds optional
`iteration.source: 'browser' | 'server'` to distinguish foreground
vs server-produced iterations (groundwork for proposal write-back)
- `planner/prompt.ts` — `buildPlannerPrompt` pure function
- `planner/parser.ts` — `parsePlannerResponse` strict JSON validator
- Vitest smoke tests (2) cover prompt → parse round-trip + unknown-
tool rejection
- Webapp:
- `missions/types.ts` re-exports from shared-ai, keeps webapp-local
`MISSIONS_TABLE` constant + `planStepStatusFromProposal` bridge
- `missions/planner/{types,prompt,parser}.ts` become re-export stubs
so existing imports keep working unchanged
- Existing webapp tests (60) continue to pass — the wire code didn't
move, just its home
Next: mana-ai service imports buildPlannerPrompt/parsePlannerResponse
from shared-ai + wires mana-llm + writes iteration back as a
'source=server' row (tracked in services/mana-ai/CLAUDE.md).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
