Six P2 items from the AI Workbench audit:
#7 Prompt ↔ loop budget sync:
System prompt now says "1 bis 5 Schritte pro Planungsrunde, bis zu 5
Planungsrunden" — matches MAX_REASONING_LOOP_ITERATIONS. Cross-ref
comment added to runner.ts.
#9 SceneHeader: useAgents() → useAgent(id):
Only loads the single bound agent instead of the full agent list.
Eliminates unnecessary Dexie churn on every scene header render.
#10 Unified scope filter:
New scope-filter.ts with filterByScopeTagMap() (batch, sync) and
filterByScopeAsync() (per-record). Both scope-context.ts (AI) and
scene-scope.svelte.ts (UI) now import from the shared module —
zero duplicated filter logic.
#11 Research dedup:
Research input ID changed from `news-research-${Date.now()}` to
`news-research-${mission.id}` — re-runs overwrite instead of
appending duplicates.
#12 Kontext injection policy clarified:
loadAgentKontextAsResolvedInput no longer falls back to the global
singleton. Comment + code aligned: kontext injection is explicit
(via input picker), not auto. Dead loadKontextAsResolvedInput
kept for potential future opt-in auto-inject feature.
Audit doc updated with all items marked DONE.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Four P1 fixes from the AI Workbench audit:
#3 N+1 junction queries → batch lookups:
- TagLinkOps gains getTagIdsForMany(entityIds) — single
where(field).anyOf(ids).toArray() instead of N calls.
- filterBySceneScopeBatch() uses a pre-fetched Map<id, tagId[]>.
- All 4 module queries (notes, todo, contacts, calendar) migrated.
- 500 notes now = 2 Dexie queries (records + junctions) instead of 501.
#4 Vault-locked detection in readLocalNote:
- Catches VaultLockedError from decryptRecords.
- Throws descriptive "Vault ist gesperrt" instead of returning null.
- Tools surface it as a clear error to the planner ("bitte Vault
entsperren") instead of "Notiz nicht gefunden".
#5 Debug log hardening:
- Resolved-input content truncated to 500 chars before storage.
- Time-based purge: entries older than 7 days auto-deleted.
- Reduces privacy exposure if device is stolen/profile synced.
#6 Timeout 90s → 180s:
- 5 LLM calls on slow models (Ollama/GPU) regularly hit 90s.
- 180s gives comfortable headroom for the reasoning loop.
Audit doc updated with status markers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two critical fixes from the AI Workbench audit:
1. Tool exceptions in the reasoning loop:
stage(ps, aiActor) is now wrapped in try-catch. If a tool throws
(Dexie error, vault locked, network timeout), the step is recorded
as failed with the error message in the summary, and the loop
continues with the next step. Previously, one broken tool crashed
the entire iteration.
2. Concurrent mission scope interleaving:
runMission() now serializes through a promise-based mutex. Two
concurrent calls (double-click, cadence overlap) queue instead of
interleaving — prevents the ambient withAgentScope() from stomping
a running mission's scope with a different agent's tags.
scope-context.ts also gains filterByScopeExplicit(records, scopeTagIds,
getTagIds) — the explicit, race-safe variant that doesn't read
ambient state. Callers that already have the scope should prefer it.
Also adds docs/optimizable/ai-workbench-audit-2026-04-16.md with the
full audit (P0–P2, 12 items).
Runner tests: 8/8.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three toast.success('\1') calls broke Vite's strict-mode parser on
startup. Replaced with proper German messages: purchase success,
cancel confirmation, reactivation confirmation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The SceneHeader (left side of the workbench homepage) now shows a
TagSelector directly above the template-gallery button. Users can
assign scope tags to the active scene — filtering notes/tasks/contacts/
calendar to only records tagged with those scopes (+ untagged globally
visible).
Auto-inference: when a scene is bound to an agent via viewingAsAgentId
and the scene has no explicit scopeTagIds, the agent's scopeTagIds
are used instead. A small "via Agent" hint appears so the user knows
the scope comes from the binding. Explicitly setting scope tags on the
scene overrides the agent's.
New store methods: setSceneScopeTags + updateScene (both sync the
reactive scene-scope store when the active scene is affected).
patchScene accepts scopeTagIds in its type union.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fix 2 broken showToast() calls in SyncSection (function was removed
but two call sites survived — runtime error on deactivate/interval).
Migrate inline toasts to central toast store in:
- gifts/+page.svelte (11 refs)
- gifts/redeem/[code]/+page.svelte (9 refs)
Delete routes/(app)/subscription/+page.svelte — dead standalone route
from before the credits merge. Update Stripe redirect URLs in
subscriptions API to use /?app=credits&success/canceled=true.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add leisure section (media, sports, pets) + social.livingSetup to userContext
- Fix interview questions: each maps to its own field, no more bio overwrites
(leisure.favoriteMedia → leisure.media, leisure.sports → leisure.sports,
social.living → social.livingSetup, social.pets → leisure.pets)
- Add merge flag for array fields (goals.learn merges into goals, not replaces)
- Store.setField() supports merge=true for deduped array merging
- All ContextOverview sections now always visible with empty-state hints
- All tag-based sections (languages, goals, allergies) are inline-editable
- Routine/nutrition/social link to interview for editing
- EditProfileModal: restore email change UI (Ändern button + verification flow)
- Update AI resolver with leisure + livingSetup fields
- Add leisure to crypto registry encryption fields
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Four UX improvements that make agents more discoverable and their
behavior more transparent. All svelte-check clean (0 errors in
changed files).
=== UX 3: Reverse-Mission-Lookup ===
Agent detail view now shows a "Missions (N)" section listing all
missions owned by this agent with status dots + state labels. Includes
a "+ Neue Mission für [agent]" button that navigates to the template
gallery. Users no longer have to mentally cross-reference between the
agents and missions modules.
=== UX 4: Simple-Mode Policy ===
The Policy section defaults to three radio-card presets:
- Standard (Vorschlag für alles)
- Vorsichtig (alles Vorschlag, keine Auto-Writes)
- Aggressiv (gleichartige Schreibvorgänge automatisch)
The full per-module matrix is now hidden behind "▸ Erweitert
anzeigen". This covers 90% of users who just want a quick
conservative/aggressive toggle. Power-users still get the full
matrix.
=== UX 5: Policy Natural Language Summary ===
Above the preset radios, a preformatted block summarizes the current
policy in plain German: "Gesperrt: X, Y · calendar: automatisch ·
Alles andere: Vorschlag". Generated from the policy object. Updates
live when the user switches presets or changes module overrides.
=== UX 6: Agent Fingerprint on List-Views ===
New <AgentDot record={item} /> component: reads __lastActor from
any Dexie record, resolves the agent's avatar via the live useAgents
query, and renders a tiny inline emoji dot next to the item title.
When no AI actor wrote the record, renders nothing (zero-width).
Wired into:
- /todo — task title row, after the title span
- /notes — note title row, after the title span
Each module import is a single line (`import AgentDot from ...`);
the component is self-contained (owns its own query + styles).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The four modules with tag junctions now filter their main useAll*
queries through filterBySceneScope: when a scene has scopeTagIds set,
only records tagged with at least one matching tag (+ untagged records)
appear in the UI. Modules without tag junctions (drink, food, habits,
journal, dreams, places) are unaffected — their records are always
globally visible.
- useAllNotes → noteTagOps.getTagIds
- useAllTasks → taskTagTable junction lookup
- useAllContacts → contactTagOps.getTagIds
- useAllCalendarItems → eventTagOps.getTagIds (calendar-sourced blocks
only; task/habit blocks pass through unfiltered)
When no scene scope is active (scopeTagIds undefined), filterBySceneScope
is a no-op identity pass — zero overhead for unscoped scenes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add ToastContainer.svelte to (app) layout — renders toasts from the
central toast.svelte store (stacked, auto-dismiss, color-coded by
type). Previously the store existed but had no renderer.
Migrate inline toast implementations to the central store:
- SyncSection: showToast() → toast.success/error(), strip DOM + CSS
- Credits ListView: same migration, remove showToast + inline toast
- Profile ListView: same migration, remove showToast + inline toast
Delete apps/mana/apps/web/SETUP.md — completely outdated (references
Supabase, teams, organizations — all removed long ago). Real docs
live in CLAUDE.md and docs/LOCAL_DEVELOPMENT.md.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
WorkbenchScene grows an optional scopeTagIds field so scenes can act
as data-scope lenses: when set, module queries filter records to those
tagged with at least one of the scene's tags (+ untagged = global).
New reactive store scene-scope.svelte.ts:
- setSceneScopeTagIds(ids) — called by scene store on switch/init
- getSceneScopeTagIds() — read by module queries
- filterBySceneScope() — reusable filter (same semantics as
AI scope-context's filterByScope)
Wired into workbench-scenes.svelte.ts:
- setActiveScene() syncs scope on manual switch
- liveQuery subscription syncs scope on init/sync/tab-focus
Module queries can now opt into scene scoping by calling
filterBySceneScope in their useAll* hooks — not wired yet (each
module opts in as needed). The foundation is in place.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add a guardrail system that runs alongside the Mission Runner pipeline
to catch obvious issues before they waste tokens or corrupt data.
Architecture (packages/shared-ai/src/guardrails/):
- types.ts: Guardrail, GuardrailResult, 4 phase interfaces
- builtin.ts: 4 built-in guardrails (always active):
- input-size-limit: blocks >100K chars of resolved input
- plan-step-limit: blocks plans with >25 steps (runaway planner)
- duplicate-destructive-tool: warns if undo_drink called 2x
- empty-required-params: blocks create_task without title
- runner.ts: runPrePlanGuardrails/runPostPlanGuardrails/runPreExecuteGuardrails
Wired into runner.ts at 3 checkpoints:
- Before deps.plan() — pre-plan check
- After plan received — post-plan check
- Before each stage() call — pre-execute check
Guardrails are synchronous, never hit the network, and produce
clear error messages when they block.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All major list-returning auto-tools now filter by the ambient agent
scope: list_notes (already done), list_tasks (via taskTagTable),
get_contacts (via contactTagOps), get_todays_events (via eventTagOps).
Untagged records pass through (globally visible); tagged records are
only returned when at least one tag matches the agent's scopeTagIds.
Notes detail view (/notes/[id]) grows a TagSelector widget between
the content textarea and the color picker, powered by the new
noteTagOps junction. Users can manually tag notes to scope them to
specific agents — complements the AI's add_tag_to_note tool.
Also: todo/stores/tags.svelte.ts created (taskLabelOps wrapper around
the existing taskLabels junction for the scope filter).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
GeneralSection: replace the GlobalSettingsSection wrapper (which
rendered its own SettingsSection pill + SettingsCard, requiring
title="" to suppress the inner header) with inline settings rows.
Each setting is a label+control row with scoped CSS — no double-card,
no wrapper hack.
Delete packages/subscriptions/ — the package is dead after merging
its SubscriptionPage into the Credits & Abo workbench app.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Complete tool handler coverage for the MCP server:
Todo: complete_tasks_by_title
Calendar: create_event (with timeBlock)
Notes: update_note, append_to_note, add_tag_to_note
Places: create_place, visit_place, get_places
Drink: log_drink, get_drink_progress, undo_drink
Food: log_meal, nutrition_summary
Journal: create_journal_entry
Habits: create_habit, log_habit (get_habits improved)
News: save_news_article
27 of 29 tools now have real implementations. Remaining 2
(research_news, get_current_location) need external service
calls that aren't available in the API server context.
Also updates architecture comparison report to mark MCP as done.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Connects the existing global tag system (@mana/shared-tags, 15+ module
junctions, TagSelector UI) to the AI agent model so different agents
can operate on different slices of the user's data.
Core additions:
1. Agent.scopeTagIds — optional array of global tag IDs. When set,
the agent sees only records tagged with at least one of those tags
(plus untagged records, which stay globally visible). Empty/undefined
= General-Agent, sees everything. Agent-editor grows a <TagSelector>
under "Bereiche (Tag-Scope)".
2. Per-agent kontext documents — new Dexie table `agentKontextDocs`
(v22, encrypted, synced). Each agent can have its own markdown
context doc, replacing the global singleton auto-inject. Runner
tries agent kontext first, falls back to global singleton when
the agent has no dedicated doc.
3. Ambient scope context — `withAgentScope(tagIds, fn)` sets a
module-level scope during the reasoning loop. Auto-tools read it
via `getAgentScopeTagIds()` and filter their result sets.
`filterByScope(records, getTagIds)` is the reusable filter
primitive (keeps untagged records, drops mismatched tagged ones).
4. Notes tag junction — `noteTags` table (v22) + `noteTagOps` via
`createTagLinkOps`. Notes was the only major module without
structured tag support. `list_notes` now calls `filterByScope`
so a scoped agent only sees notes tagged with its scope.
Flow: mission starts → runner resolves owning agent → reads
agent.scopeTagIds → wraps entire reasoning loop in withAgentScope →
list_notes (and future list_tasks etc.) auto-filter → planner sees
only scope-relevant records → proposes scoped edits.
Runner tests: 8/8. shared-ai type-check: clean.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Mount an MCP (Model Context Protocol) server at /api/v1/mcp in the
unified Hono API. External clients like Claude Desktop, Cursor, and
VS Code Copilot can discover and call all 29 Mana tools via the
standard MCP protocol.
Architecture:
- WebStandardStreamableHTTPServerTransport for Bun/Hono compatibility
- AI_TOOL_CATALOG → MCP tool definitions with JSON Schema (via Zod)
- Stateful sessions with Mcp-Session-Id header
- Auth via existing authMiddleware (JWT or API key)
Phase 1 scope: tools/list returns all 29 tools with schemas,
tools/call acknowledges with descriptive messages. Phase 2 will add
actual DB reads/writes via sync_changes.
Usage:
Claude Desktop config:
{"mcpServers": {"mana": {"url": "http://localhost:3060/api/v1/mcp"}}}
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The three Settings sub-routes (/settings/sync, /settings/security,
/settings/my-data) were standalone pages with their own PageHeaders
that felt disconnected from the workbench settings app. Inline them
as section components so everything lives in one scrollable view:
- SyncSection.svelte (from /settings/sync) → embedded in Data tab
- MyDataSection.svelte (from /settings/my-data) → embedded in Data tab
- VaultSection.svelte (from /settings/security) → embedded in Security tab
Each component is the route content minus PageHeader/Breadcrumbs/
svelte:head. Toasts stay self-contained in each section.
- Delete all three route files + empty /settings/ directory tree
- Add 'vault' anchor to searchIndex (search "Verschlüsselung")
- Update external links: sync-status dropdown, sync billing banner,
EncryptionIntroBanner → /?app=settings#cloud-sync / #vault
The routes/(app)/settings/ directory is now completely gone.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove empty dirs: modules/mana/, modules/subscription/, and 7
empty route dirs (spiral, profile, themes, help, apps, mana, credits)
- Remove @mana/subscriptions from web app dependencies (never imported)
- PillNavigation: drop settingsHref, manaHref, allAppsHref/allAppsLabel
props + their link-builder blocks (none are passed anymore; all system
pages route via /?app=<id> deep-links now)
- Update layout comment to reflect current architecture
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Introduce AI_TOOL_CATALOG in @mana/shared-ai as the single source of truth
for all 29 tool schemas (17 propose + 12 auto). Both the webapp policy and
the server-side mana-ai planner now derive their tool lists from the catalog
instead of maintaining independent hardcoded copies.
- New: packages/shared-ai/src/tools/schemas.ts — catalog with ToolSchema type
- Rewrite: proposable-tools.ts — derived from catalog instead of hardcoded array
- Rewrite: services/mana-ai/src/planner/tools.ts — 277→30 lines (imports from catalog)
- Simplify: webapp policy.ts — derives AUTO/PROPOSE from catalog defaultPolicy
Adding a new tool now requires 2 files instead of 3-5:
1. Add schema to AI_TOOL_CATALOG (shared-ai)
2. Add execute function in the module's tools.ts (webapp)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The standalone "Abonnement" workbench app (lib/modules/subscription/)
duplicated billing functionality that should live alongside credits.
Users saw two separate apps for the same domain.
Replace the placeholder SubscriptionPage in the Abo tab with the real
subscription management from the subscription module:
- Current plan status with cancel/reactivate
- Plan selection with billing interval toggle (monatlich/jährlich)
- Stripe checkout integration
- Invoice history (collapsed <details>)
- Stripe billing portal link
Delete:
- lib/modules/subscription/ (merged into credits)
- app-registry 'subscription' registration
- CreditCard icon import (no longer used)
The Credits & Abo app now has 5 tabs:
1. Übersicht — balance + recent transactions + quick-buy
2. Abo — current subscription + plan picker + invoices
3. Verlauf — full transaction table
4. Kaufen — one-time credit packages (Stripe)
5. Kosten — per-operation pricing breakdown
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
google-genai >=1.70 changed Part.from_text() from positional to
keyword-only argument. The production container installed v1.73.1
and crashed on startup with "Part.from_text() takes 1 positional
argument but 2 were given".
Fix: Part.from_text(msg.content) → Part.from_text(text=msg.content)
Tested live: curl https://llm.mana.how/v1/chat/completions with
model=google/gemini-2.5-flash returns correct response.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After merging /mana into the credits workbench app, both manaHref and
creditsHref pointed to /?app=credits, rendering two identical dropdown
entries ("Mana" + "Credits"). Drop manaHref so only the "Credits"
entry remains.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Catches up all docs with the current state of the AI tool system.
services/mana-ai/CLAUDE.md:
- New v0.6 status section documenting NewsResearchClient,
pre-planning research injection, config.manaApiUrl, and the full
28-tool / 11-module inventory (17 propose + 11 auto).
apps/mana/CLAUDE.md:
- New "Tool Coverage" table in the AI Workbench section listing all
tools per module with their policy (propose vs auto).
- New "Templates" subsection documenting the two-section gallery
(agent vs workbench templates), the seed-handler registry, and
the current handlers (meditate, habits, goals).
- Architecture cross-reference updated to include §23.
docs/architecture/COMPANION_BRAIN_ARCHITECTURE.md:
- §23.2 gains a "Server-Side Research (mana-ai, ab v0.6)" subsection
explaining how NewsResearchClient mirrors the client-side research
pre-step: same endpoints, same trigger regex, but HTTP-direct from
the Docker network instead of SvelteKit-internal.
docs/plans/README.md:
- workbench-templates.md added to the roadmap table (T1 shipped).
- Multi-agent description updated to mention 28 tools + server-side
web-research.
- Architecture cross-reference includes §23.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Enable real-time token streaming during the planner "calling-llm" phase
so the user sees live progress ("empfange Plan… 128 tokens") instead of
a static spinner. The parser still receives the full text once complete —
no partial-JSON risk.
Changes:
- Extract shared SSE parser from playground into @mana/shared-llm/sse-parser
- remote.ts: use stream:true when onToken callback is provided
- AiPlanInput: add optional onToken field (shared-ai)
- ai-plan task: pass onToken through to backend.generate()
- runner.ts: throttled (500ms) phaseDetail updates during streaming
- Playground: refactored to use shared SSE parser
Also includes: AI agent architecture comparison report (docs/reports/)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The standalone /apps page (AppsPage from shared-ui) is redundant in the
workbench model — apps are discoverable via the app picker and scene
management directly on the home screen.
- Delete routes/(app)/apps/+page.svelte
- Remove command menu "Alle Apps" entry
- Drop allAppsHref prop from PillNavigation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The former /credits (balance, transactions, Stripe checkout, cost
breakdown) and /mana (subscription plans placeholder) were separate
pages covering the same billing domain. Merge into a single workbench
app "Credits & Abo" with 5 tabs:
1. Übersicht — balance cards + recent transactions + quick-buy
2. Abonnements — SubscriptionPage from @mana/subscriptions
3. Transaktionen — full transaction history table
4. Kaufen — Stripe-integrated package cards
5. Kosten — per-operation cost breakdown with category filter
Stripe redirect handling: Stripe returns to /?app=credits&success=true.
The deep-link handler opens the app and strips ?app; the ListView reads
?success / ?canceled from window.location.search on mount, shows the
appropriate toast, and cleans the URL via history.replaceState.
- Delete /credits/+page.svelte and lib/modules/mana/ (placeholder)
- Register workbench app id='credits' (Crown icon, amber)
- Replace mana app registration (no longer needed)
- Update all links: command menu, PillNavigation (manaHref + creditsHref
both → /?app=credits), CreditsSection, CreditsWidget,
TransactionsWidget, CompleteStep, sync-status, sync billing page,
gift redeem page
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two major tool expansions — the Recherche-Agent and Today-Agent can
now research the web autonomously (no browser needed), and a future
Meeting-Prep agent can read + create contacts.
=== research_news (server-side execution) ===
The biggest addition: mana-ai can now call mana-api's news-research
endpoints (POST /discover + /search) directly, without a browser.
Infrastructure:
- services/mana-ai/src/planner/news-research-client.ts — full HTTP
client with discover→search pipeline. 15s/30s timeouts. Graceful
null on any failure (network, mana-api down, bad response) so the
tick never crashes from research errors.
- config.manaApiUrl added (default http://localhost:3060); wired in
docker-compose.macmini.yml as http://mana-api:3060 + depends_on
mana-api with service_healthy condition.
Pre-planning research step (cron/tick.ts):
- Before the planner prompt is built, the tick checks if the
mission's objective or conceptMarkdown matches research keywords
(same RESEARCH_TRIGGER regex the webapp uses). When it matches:
* NewsResearchClient.research(objective) runs discovery + search
* Results are injected as a synthetic ResolvedInput with id
'__web-research__' and a formatted markdown context block
* The Planner then sees real article URLs/titles/excerpts and can
reference them in create_note / save_news_article steps
* Log line: "pre-research: N feeds, M articles"
Tool registration:
- research_news added to AI_PROPOSABLE_TOOL_NAMES + mana-ai tools.ts
with params (query, language?, limit?). This lets the planner also
explicitly propose a research step as a PlanStep (in addition to
the pre-planning auto-injection).
=== create_contact ===
- Added to AI_PROPOSABLE_TOOL_NAMES + mana-ai tools.ts with params
(firstName required, lastName/email/phone/company/notes optional).
- Contacts are encrypted at rest; server planner can plan the step
but execution stays on the webapp (same as all propose tools).
Full server-side contact resolution via Key-Grant is a future
enhancement.
- get_contacts added to webapp AUTO_TOOLS so agents can inspect
existing contacts without nagging (read-only, auto-policy).
Module coverage now:
✅ todo (5) ✅ calendar (2) ✅ notes (5) ✅ places (4)
✅ drink (3) ✅ food (2) ✅ news (1) ✅ journal (1)
✅ habits (3) ✅ news-research (1) ✅ contacts (1)
11 modules, 28 tools total (17 propose, 11 auto).
Tests: mana-ai 41/41 (drift-guard passes), shared-ai type-check
clean, webapp svelte-check 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extract /mana route into lib/modules/mana/ListView.svelte. Register as
workbench app id='mana' with Crown icon (amber). The page shows the
SubscriptionPage component from @mana/subscriptions.
- Delete routes/(app)/mana/+page.svelte
- Update PillNavigation manaHref to /?app=mana
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The help workbench module (lib/modules/help/ListView.svelte) already
renders the same HelpPage component with identical props. The
standalone route was redundant.
- Delete routes/(app)/help/+page.svelte
- Update PillNavigation helpHref to /?app=help
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Closes the three biggest tool-coverage gaps so the shipped agent
templates can actually do their job end-to-end. Before this, the
Recherche-Agent couldn't create notes (only edit), the Today-Agent
couldn't create journal entries, and no habit-related tool was
server-proposable at all.
shared-ai (proposable-tools.ts):
- create_note (notes) — key unlock: Recherche-Agent now creates
per-source notes and the summary report.
- create_journal_entry (journal) — key unlock: Today-Agent proposes
a poem as a journal entry with optional mood.
- create_habit (habits) — agent can suggest new habits.
- log_habit (habits) — agent can log a habit completion for today.
Organized the list with per-module section comments for readability
now that we're at 15 proposable tools.
mana-ai (planner/tools.ts):
- 5 new tool definitions with full parameter schemas:
* create_note (title, content?)
* create_journal_entry (content, title?, mood? enum)
* create_habit (title, icon, color)
* log_habit (habitId, note?)
- Drift-guard contract test passes (41/41) — confirms the mana-ai
tool list is in sync with the shared-ai canonical set.
Webapp (policy.ts):
- get_habits added to AUTO_TOOLS (read-only; agent can inspect
which habits exist without nagging the user for approval).
- list_notes added to AUTO_TOOLS (was already used in the reasoning
loop but missing from the explicit auto-list; the planner default
fell through to 'propose' which was wasteful for a read op).
Module coverage after this change:
✅ todo (5 tools) ✅ calendar (2) ✅ notes (5 incl. create)
✅ places (4) ✅ drink (3) ✅ food (2)
✅ news (1) ✅ journal (1) ✅ habits (3)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extract the /spiral route into lib/modules/spiral/ListView.svelte
(same content minus the standalone PageHeader — the workbench card
provides its own chrome). Register as workbench app id='spiral' with
the Phosphor Spiral icon.
- Delete routes/(app)/spiral/+page.svelte
- Update command menu + PillNavigation spiralHref to /?app=spiral
- deep-link scheme works out of the box (/?app=spiral)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Section deep-links: /?app=settings#ai-options now switches the Settings
ListView to the KI tab and scrolls to the ai-options anchor. ListView
reads the URL hash on mount and maps it to a category via the existing
searchIndex anchors. The AI-tier dropdown "KI-Einstellungen" link now
targets /?app=settings#ai-options instead of just /?app=settings.
Profile & Themes workbench consolidation — same pattern as Settings:
- Delete standalone /profile and /themes routes (redundant with the
workbench apps registered in app-registry)
- Migrate all links: PillNavigation profileHref/themesHref, dashboard
QuickActionsWidget, +layout theme-switcher "Alle Themes", and the
scene context-menu "Hintergrund ändern"
Credits stays as a standalone route — no workbench app registered for it.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Closes out T1 with three templates per category as discussed. The
gallery now renders agent-templates and workbench-templates as two
distinct labeled sections — the earlier implicit "everything's a
template for an agent" framing is gone.
Seed handlers (new):
- apps/mana/apps/web/src/lib/modules/habits/seed.ts — title-based
idempotency (there's no description column on LocalHabit). If a
non-deleted habit with the same title exists, the seed is skipped.
- apps/mana/apps/web/src/lib/companion/goals/seed.ts — title-based
idempotency on companionGoals where status !== 'abandoned'.
- Both pulled in via side-effect imports in missions/setup.ts so the
handler registry is populated before any apply.
New templates:
- 🏋️ Fitness (wellness) — scene body/habits/stretch/sleep + 3 habit
seeds (Täglich 30min Bewegung, 3× Woche Training, 2L Wasser) + 1
goal seed (3 Workouts pro Woche). No agent.
- 💻 Deep Work (work) — scene todo/calendar/notes/times + 2 habit
seeds (1 wichtigste Aufgabe pro Tag, 4h Deep Work pro Tag) + 1
goal seed (20h Deep Work pro Woche). No agent.
Gallery two-section layout:
- Title "Templates" (not "Agent-Templates") — broader framing.
- Section 1: "🤖 Agent-Templates" — filters ALL_TEMPLATES where
category ∈ {'ai','delight'}: Recherche-Agent, Kontext-Agent,
Today-Agent.
- Section 2: "🎨 Workbench-Templates" — filters to the rest:
Calmness, Fitness, Deep Work.
- Each section gets a short intro paragraph so users understand the
distinction before scanning the cards.
- Cards themselves unchanged; rendering extracted into a
{#snippet templateCard(t)} shared between both sections.
- Per-category arrays computed once at module-load time (const in
<script>); no per-render filter cost.
Result: each section has 3 templates, categorised by "does this
create an AI agent" rather than by use-case. Keeps the separation
honest — Agent-Templates set up autonomous work; Workbench-Templates
set up the user's own workspace.
Tests: shared-ai 26/26, webapp svelte-check 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After consolidating Settings into a workbench app, links from the
command menu, pill-nav, AI-tier dropdown, onboarding CTAs, and the
sub-route back-buttons had nowhere specific to go — they pointed at
`/` and dumped users at their home scene with no way to auto-open the
settings app.
- Home (+page.svelte) reads ?app=<id> on mount. If the id is a
registered workbench app and not already in the active scene,
addApp() it. Then scroll the carousel to that page. Strip the
query out of history.replaceState so refresh doesn't re-open.
- Update all settings redirects (command menu, onboarding,
AI-settings dropdown, settings/sync + settings/my-data back-links
and breadcrumbs) to `/?app=settings`.
Unlocks: future deep-links to any app (profile, themes, spiral,
credits, …) without needing a standalone route. `?app=X§ion=Y`
is the natural next step — left for when an app needs it.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
First pass of the workbench-templates plan (docs/plans/workbench-
templates.md) — templates are no longer agent-centric but a general
"starter kit" bundle: optional agent + optional scene + optional
missions + optional per-module seeds. Pilot non-AI template "Calmness"
ships alongside.
Shape generalisation (packages/shared-ai/src/agents/templates/types.ts):
- AgentTemplate renamed to WorkbenchTemplate; all fields now optional
(agent, scene, missions, seeds). Back-compat AgentTemplate alias
kept so research/context/today keep compiling.
- Added `category: 'ai'|'wellness'|'work'|'lifeEvent'|'delight'` +
`icon` (for non-agent templates that have no avatar) + `version`
field (for future update-detection).
- New WorkbenchTemplateSeedItem shape: `{stableId?, data: unknown}`.
Module-specific seed payloads are typed at the handler side.
- Existing three AI templates nachgezogen: category='ai' (or
'delight' for today-agent), icon, version='1'.
Seed infrastructure:
- apps/mana/apps/web/src/lib/data/ai/agents/seed-registry.ts — in-
memory handler map keyed by module name; module-local seed.ts files
register themselves at import time.
- apps/mana/apps/web/src/lib/modules/meditate/seed.ts — first handler:
createPreset-based, idempotent via stableId embedded as HTML
comment in the preset description (T1 pragmatism; T2 adds a proper
column on the preset schema).
- data/ai/missions/setup.ts pulls `import '$lib/modules/meditate/seed'`
so the handler is registered before any template is applied.
Applicator upgrades (data/ai/agents/apply-template.ts):
- Agent step now optional — skipped cleanly when template has no
agent part.
- New step 4: seeds. Walks template.seeds, looks up the handler for
each module, aggregates per-item outcomes (created/skipped-exists/
failed) into result.seedOutcomes. Missing handler = warning, not
fatal. Crypto/encryption unchanged — seeds go through the same
module stores that module code already uses.
- Result shape gains `seedOutcomes: Record<string, SeedOutcome[]>`
so the gallery can show "3 new, 1 already there".
Calmness pilot (packages/shared-ai/src/agents/templates/calmness.ts):
- category='wellness', NO agent, scene with meditate/mood/journal/
sleep apps, two meditate preset seeds:
* 4-7-8 Atmung (breathing preset)
* Body-Scan 10min (bodyscan preset with 9 scan steps)
- Each seed has a stableId so re-apply is idempotent.
Gallery updates (routes/(app)/agents/templates/+page.svelte):
- Card avatar falls back to t.icon when no agent. "Agent" chip shows
only for agent-templates; "N Seeds" chip shows for templates with
seeds.
- Detail header shows "Workbench-Setup ohne AI-Agent" when no agent.
- New "Seeds" preview section: lists per-module counts + item names.
- Options section gains a "Seed-Daten in Module einpflegen" checkbox.
- Success panel shows seed summary: "3 Seeds neu, 1 bereits
vorhanden".
Tests: shared-ai 26/26, webapp svelte-check 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Each consuming app was duplicating eight @source directives with hand-
counted relative paths (../../../../../packages/…). The mana web app's
were off-by-one for months before anyone noticed, silently disabling the
scan for every shared-ui file.
Tailwind v4 resolves @source paths relative to the CSS file that declares
them, so we can drop the list once into packages/shared-tailwind/src/
sources.css. Consumer apps now just add one more @import next to themes.css:
@import "tailwindcss";
@import "@mana/shared-tailwind/themes.css";
@import "@mana/shared-tailwind/sources.css";
New package.json export: "./sources.css". Drop the local paths from the
mana web app's app.css.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Debug log from a "tag 4 notes" mission showed the planner's second-round
response truncated mid-step: it was proposing one add_tag_to_note per
listed note but ran out of tokens halfway through note #2. Parser
rejected the malformed JSON → loop exited with 0 staged, user saw
nothing to approve.
Raising maxTokens to 4096 fits ~15-20 step objects, which covers the
batch-tagging / batch-save pattern the reasoning loop is designed for.
Also updating the system prompt so the planner actually knows about
the loop it's running inside: read-only tools are announced as
auto-executing with outputs visible next turn, and a new rule makes
explicit that batch jobs must emit all write-steps in one plan (because
staging a propose-tool ends the turn). Step count raised 1-5 → 1-10.
Prompt snapshot tests still pass (they check structure, not text).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The runner was one-shot: one planner call per iteration, no feedback
from tool outputs. "Lies alle Notizen und tagge sie" needed two manual
runs (list_notes, then tagging) because the planner never saw the
list_tasks output.
Now runMission loops up to MAX_REASONING_LOOP_ITERATIONS (5):
loop: plan → classify steps by policy
│
├─ auto → execute inline, capture {message, data}, feed back
│ as a synthetic ResolvedInput for the next planner call
│
├─ propose → stage proposal, mark humanInLoop, EXIT after this round
│ (human has to approve before we plan further — we don't
│ know what they'll accept yet)
│
└─ none/0-steps → agent considers the task done, EXIT
Tool outputs become a ResolvedInput titled "Zwischenergebnisse (Runde N)"
so the planner sees them structured and labelled. StageOutcome gains
`autoData` + `autoMessage` so the loop can thread the executor's
payload back through without a second call.
AiDebugEntry now holds `plannerCalls[]` and `loopSteps[]` instead of a
single planner snapshot — so Debug-Panel shows every LLM round + every
auto-tool output, each collapsible. Summary chip shows "3× LLM · 4200ms
· 2× Auto-Tool" when a loop ran.
Side-effects for existing use cases:
- One-shot missions (single propose tool) behave identically (loop
exits after round 1 with humanInLoop=true).
- "Tag all notes" missions now finish in a single run: loop iter 1
runs list_notes auto, iter 2 stages N add_tag_to_note proposals,
exits.
- Server-side mana-ai runner NOT touched — this is foreground-only
for now; the server still runs one plan/tick.
All 8 runner.test.ts tests pass unchanged (the existing test suite
only exercises the single-step path, which is a subset of the loop).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When the seeded default scene ("Home") has no description yet, the
empty contenteditable placeholder shows "Willkommen Zuhause im Mana
Hub" instead of the generic "Beschreibung hinzufügen…". Rename the
scene → generic prompt returns.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
shared-auth-ui components (PasskeyManager, SessionManager, TwoFactorSetup,
AuditLog, ChangePassword, SecurityOnboarding) take a primaryColor prop
that gets written as inline --primary-color on the component root. The
mana app was passing a literal "#6366f1" (indigo) everywhere, so the
Security tab and auth pages used a fixed indigo accent that ignored the
user's theme. Pass "hsl(var(--color-primary))" instead — the nested var
resolves live, so theme switches carry through.
tailwind.config.js in apps/mana/apps/web was fully vestigial:
- no @config directive in app.css, no reference from vite/svelte configs
- imported @mana/shared-tailwind/preset, which the package doesn't export
- only themes.css is exported, and it's loaded directly from app.css
Tailwind v4 with CSS-first config is the real setup. Delete the file
and remove its entry from SETUP.md.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
