# Roadmap — Chat Switchboard

**See also:**
- [ARCHITECTURE.md](ARCHITECTURE.md) — Core services design, store layer, scope model
- [EXTENSIONS.md](EXTENSIONS.md) — Extension system spec (Browser/Starlark/Sidecar tiers,
  manifests, browser tool bridge, surfaces/modes, model roles)

**Versioning (pre-1.0):** `0.<major>.<minor>` — hotfixes use quad: `0.x.y.z`
No compatibility guarantees before 1.0.

---

## Dependency Graph

Features have real dependencies. This ordering respects them.

```
v0.9.x  Stability + Quick UX Wins
          │
v0.9.3  Content Visibility & Block Controls
          │
v0.9.4  API Key Encryption + Vault
          │
v0.10.0 Model Roles (utility + embedding) + Usage Tracking
          │
v0.10.2 Summarize & Continue (first utility role consumer)
          │
v0.10.3 Frontend Refactor (no features, code health)
          │
v0.10.4 Model Type Pipeline + Role Fixes
          │
v0.10.5 UI Primitives + Extension Surfaces
          │
  ┌───────┴──────────────┐
  │                      │
v0.11.0 Extension      v0.12.0 File Handling
  Foundation              + Vision
  (browser tier)          │
  │                       │
  ├── Custom renderers    ├── Doc gen outputs
  ├── Image gen tool      ├── KB documents
  ├── STT/TTS             │
  │                       │
  ├───────────────────────┤
  │                       │
v0.13.0 Web Search + Tools Expansion
          │
v0.14.0 Knowledge Bases (embedding role + file storage + pgvector)
          │
v0.15.0 Compaction (utility role + background job)
          │
v0.16.0 @mention Routing + Multi-model
          │
v0.17.0 Extension Surfaces + Modes
          │
v0.18.0 Smart Routing (policy on model roles)
          │
v0.19.0 Multi-Participant Channels + Presence
          │
v0.20.0 Auth Strategy (mTLS/OIDC) + Full RBAC
          │
  ┌───────┴──────────────┐
  │                      │
v0.21.0 Workflow       v0.22.0 Tasks /
  Engine                 Autonomous Agents
  (team-owned,           (service channels,
   staged processes,      scheduler, unattended
   human + AI collab)     execution)
```

---

## ✅ v0.9.0 — Schema Consolidation + BYOK

The "rewrite" release: 21 migrations collapsed to 1, store layer abstraction,
and the model pipeline made real for end users.

**Schema & Architecture**
- [x] Consolidated schema (21 migrations → single 001_initial.sql)
- [x] Store layer abstraction (all DB via typed interfaces, no raw SQL in handlers)
- [x] Persona-as-trust-boundary model (replaces old presets concept)
- [x] Scope model (global/team/personal) for configs, personas, models
- [x] Backward-compatible API routes (v0.8 → v0.9 field aliases)

**Capabilities System**
- [x] Two-tier resolution: catalog (provider API, per-provider) → heuristic inference
- [x] Venice provider: full capability mapping incl. `optimizedForCode`
- [x] `ResolveIntrinsic` with gap-fill merging (catalog authoritative, heuristic fills gaps)
- [x] Preset capability inheritance via `GetByModelIDAny` fallback

**BYOK (Bring Your Own Key)**
- [x] Auto-fetch models on provider creation
- [x] User-facing refresh endpoint + "Refresh Models" button
- [x] Personal models in selector with `scope=personal` badge
- [x] Composite model IDs (`configId:modelId`) prevent cross-provider collisions

**Bug Fixes (0.9.0.x)**
- [x] API key storage (`json:"-"` tag silently dropped keys)
- [x] NULL model_default scan crash (sql.NullString)
- [x] Nil slice → JSON null (make([]T, 0))
- [x] Frontend error swallowing

**Testing**
- [x] Journey-based integration tests (API-only, 4-actor × 3-provider matrix)
- [x] Live Venice API integration test
- [x] Frontend JS test suite (107 tests, 27 suites)

---

## ✅ v0.9.1 — Capability Architecture + Docs

- [x] Removed static known model table (same model ≠ same capabilities across providers)
- [x] Resolution chain: catalog → heuristic only, no hardcoded table
- [x] Frontend KNOWN_MODELS removed — backend is sole source of truth
- [x] Heuristic patterns expanded (qwen3, gpt-5, grok, kimi, minimax, glm-5, gemma-3)
- [x] All providers updated to use `InferCapabilities()` directly
- [x] EXTENSIONS.md recovered and updated with Appendix A (Custom Renderers)
  and Appendix B (Model Roles)
- [x] ROADMAP.md, CHANGELOG.md, README.md comprehensive rewrite

---

## ✅ v0.9.2 — Quick UX Wins + Hardening

Polish that doesn't need new infrastructure. Ship fast, stabilize.

**UX**
- [x] Collapsible code blocks (long outputs get `<details>` wrapper)
- [x] HTML preview for generated content (sandboxed iframe toggle)
- [x] Token count estimate in input area (before send)
- [x] "Conversation is getting long" warning (context % thresholds)
- [x] New switchboard panel favicon (animated SVG + PNG + ICO)

**Hardening**
- [x] Proxy interception detection (Content-Type checks, actionable error messages)
- [x] Environment injection to frontend (`window.__ENV__`)
- [x] Enhanced debug diagnostics (NET:PROXY log type, Content-Type capture, env info)
- [x] Team admin audit scoping (see only their team's audit entries)

---

## ✅ v0.9.3 — Content Visibility & Block Controls

User control over what's expanded/collapsed in the message flow. Thinking
blocks, tool calls, and code blocks all get consistent collapse controls
instead of being hidden or auto-formatted without user agency.

**Code Blocks**
- [x] Collapse/expand toggle button on code block header (alongside Copy/Preview)
- [x] Auto-collapse at threshold (>15 lines), user can always toggle
- [x] Smooth max-height transition instead of `<details>` wrapping

**Thinking Blocks**
- [x] Always render thinking blocks (never hide from DOM)
- [x] `showThinking` setting controls default open/closed (default: false), not visibility
- [x] User can always click to expand regardless of setting
- [x] `reasoning_content` delta field support for models that stream thinking separately (Grok, etc.)
- [x] Reasoning accumulated during streaming, wrapped in `<think>` tags before persistence

**Tool Calls**
- [x] Persist tool call metadata in stored messages (`tool_calls` JSONB column)
- [x] Render tool calls on history load (not just during streaming)
- [x] Collapsed by default: "🔧 tool_name → done" with toggle for full I/O
- [x] Notes tool: "📝 View note" link that navigates to Notes panel
- [x] Tool result rendering fix (operator precedence bug showing "undefined results")

**Notes Panel → Side Panel**
- [x] Copy button on note cards (same pattern as code block copy)
- [x] Unified side panel replaces inline HTML preview and notes modal
- [x] Tabbed interface: Preview and Notes tabs
- [x] Desktop: slides in from right (480px), chat area shrinks via flexbox
- [x] Mobile: full-width overlay at z-index 200
- [x] Escape key integration (generation → command palette → side panel → modals)

**Streaming Refactor**
- [x] Extracted `streamWithToolLoop()` into `stream_loop.go` as single canonical streaming implementation
- [x] Both `streamCompletion` (normal chat) and `Regenerate` call shared function — only persistence differs
- [x] Regenerate handler now has full feature parity: tools, reasoning, tool_calls persistence
- [x] Fixed nil `json.RawMessage` causing PostgreSQL JSONB rejection on regen persistence

**Regenerate Fix**
- [x] Regen streams in-place (truncates display to parent before streaming)
- [x] No more "collapse to original branch" after completion

**Favicon**
- [x] Animated SVG favicon during generation (cascading opacity pulse on 4 dots)

**Admin Scope**
- [x] Admin models endpoint returns only global-scope models (not user BYOK or team models)
- [x] Bulk visibility toggle scoped to global providers only

---

## ✅ v0.9.4 — API Key Encryption + Vault

Two-tier encryption with a trust boundary between organizational keys (admin-
accessible) and personal BYOK keys (user-only). Personal keys are protected
by a per-user encryption key (UEK) that the platform admin cannot recover
without the user's passphrase.

### Threat Model

| Threat | Global/Team keys | Personal BYOK keys |
|--------|-----------------|---------------------|
| DB backup theft | ✅ Protected (env-var AES) | ✅ Protected (UEK AES) |
| SQL injection exfil | ✅ Protected | ✅ Protected |
| Admin reads DB directly | ⚠️ Admin can decrypt (owns env var) | ✅ Admin cannot decrypt (lacks user passphrase) |
| Admin modifies server code | ⚠️ Out of scope (runtime access) | ⚠️ Out of scope (runtime access) |

### Crypto Design

**Two encryption paths, one mechanism (AES-256-GCM):**

1. **Global/Team keys** — encrypted with a key derived from `ENCRYPTION_KEY`
   env var. Admin-owned, admin-recoverable. Simple.

2. **Personal keys** — encrypted with a per-user **User Encryption Key (UEK)**.
   The UEK is a random 256-bit key generated at account creation, itself
   encrypted with a key derived from the user's password via Argon2id.

```
Password → Argon2id(salt) → Password-Derived Key (PDK)
PDK → AES-256-GCM-Decrypt(encrypted_uek) → UEK (plaintext, session-only)
UEK → AES-256-GCM-Decrypt(api_key_enc) → API key (plaintext, per-request)
```

The UEK lives in server memory for the duration of the session (alongside the
JWT). It is never written to disk, logs, or the database in plaintext.

### Schema Changes (migration)

```sql
-- Users: vault support
ALTER TABLE users ADD COLUMN encrypted_uek  BYTEA;
ALTER TABLE users ADD COLUMN uek_salt       BYTEA;    -- Argon2id salt
ALTER TABLE users ADD COLUMN uek_nonce      BYTEA;    -- GCM nonce for UEK wrap
ALTER TABLE users ADD COLUMN vault_set      BOOLEAN NOT NULL DEFAULT false;

-- API configs: encrypted key storage
ALTER TABLE api_configs ADD COLUMN api_key_enc  BYTEA;
ALTER TABLE api_configs ADD COLUMN key_nonce    BYTEA;
ALTER TABLE api_configs ADD COLUMN key_scope    TEXT NOT NULL DEFAULT 'global';
-- key_scope: 'global' | 'team' | 'personal'
-- global/team: decrypt with env-var-derived key
-- personal:    decrypt with user's UEK

-- Team providers: same pattern
ALTER TABLE team_providers ADD COLUMN api_key_enc  BYTEA;
ALTER TABLE team_providers ADD COLUMN key_nonce    BYTEA;
```

Migration backfills: encrypt existing plaintext keys using the env var key
(all existing keys are global/team scope). Drop plaintext `api_key` column
after backfill. If `ENCRYPTION_KEY` is not set, migration refuses to run
(fail-safe).

### Auth Mode Integration

**Builtin auth** — password serves double duty: authentication + UEK
derivation. No additional UX. On login, derive PDK → unwrap UEK → cache
in session. User never knows the vault exists.

**mTLS / OIDC** (v0.20.0) — authentication is external (cert/token).
Vault passphrase is conditionally required:

```
External auth → auto-authenticated
  ├── Personal providers DISABLED → straight to app, no prompt
  └── Personal providers ENABLED
        ├── First visit  → "Set a vault passphrase to protect your API keys"
        └── Returning    → "Unlock your vault" (passphrase field, pre-filled username)
```

Terminology: **"vault passphrase"** for mTLS/OIDC users (distinct from their
non-existent account password). Builtin auth users never see this term.

### Backend Implementation

**`server/crypto/vault.go`** — pure encryption/decryption, no DB awareness:
- `DeriveKey(password, salt) → key` (Argon2id, 64MB memory, 3 iterations)
- `GenerateUEK() → (uek, error)` (crypto/rand, 32 bytes)
- `WrapUEK(uek, pdk) → (ciphertext, nonce, error)`
- `UnwrapUEK(ciphertext, nonce, pdk) → (uek, error)`
- `Encrypt(plaintext, key) → (ciphertext, nonce, error)`
- `Decrypt(ciphertext, nonce, key) → (plaintext, error)`
- `DeriveEnvKey(envVar) → key` (HKDF-SHA256 with domain separation context)

**Session UEK caching** — UEK stored in a sync.Map keyed by user ID, evicted
on logout / token expiry. Completion handler retrieves UEK from cache to
decrypt personal provider keys at request time.

**Provider resolution** — `key_scope` determines decryption path:
```go
func (s *Store) DecryptAPIKey(config ApiConfig, uekCache *sync.Map) (string, error) {
    switch config.KeyScope {
    case "global", "team":
        return crypto.Decrypt(config.APIKeyEnc, config.KeyNonce, envDerivedKey)
    case "personal":
        uek, ok := uekCache.Load(config.UserID)
        if !ok { return "", ErrVaultLocked }
        return crypto.Decrypt(config.APIKeyEnc, config.KeyNonce, uek.([]byte))
    }
}
```

### Edge Cases

| Scenario | Behavior |
|----------|----------|
| **User changes password** (builtin) | Re-derive PDK, re-encrypt UEK with new PDK. Personal API keys unchanged (keyed to UEK, not password). |
| **Admin resets user password** | Old UEK unrecoverable. Personal keys destroyed. Admin UI warns before confirming. |
| **mTLS user forgets passphrase** | Self-service reset: destroys encrypted personal keys. UX: "This will erase your stored API keys." |
| **Admin disables personal providers** | Keys stay encrypted in DB (inert). Re-enable later → keys accessible if user remembers passphrase. |
| **`ENCRYPTION_KEY` not set** | Startup refuses to run if encrypted keys exist in DB. Fresh install: keys stored plaintext with deprecation warning in logs + admin panel. |
| **`ENCRYPTION_KEY` rotated** | Admin CLI tool: `switchboard vault rekey` — re-encrypts all global/team keys with new env key. Personal keys unaffected (keyed to UEK). |

### Frontend Changes

- Provider management (Settings → Providers): no change to UX for builtin auth
- mTLS/OIDC splash: conditional vault passphrase prompt (new component)
- Admin → Users → Reset Password: warning dialog about personal key destruction
- Admin → Settings: indicator for `ENCRYPTION_KEY` status (set / not set)

### Checklist

**Crypto core**
- [x] `server/crypto/vault.go` — Argon2id derivation, AES-256-GCM wrap/unwrap
- [x] `server/crypto/vault_test.go` — round-trip, wrong-password, corruption (11 tests)
- [x] Env-var key derivation + validation on startup (HKDF-SHA256 with domain separation)
- [x] `server/crypto/cache.go` — UEK cache with copy-on-read/write, memory zeroing
- [x] `server/crypto/resolver.go` — KeyResolver routes decrypt/encrypt by key_scope
- [x] `server/crypto/backfill.go` — startup migration for plaintext → encrypted keys

**Schema + migration**
- [x] Migration 003_vault.sql: encrypted columns, key_scope backfill
- [x] `ENCRYPTION_KEY` enforcement (refuse to start if keys exist but no env var)
- [x] Unencrypted fallback when `ENCRYPTION_KEY` not set (raw bytes, graceful degradation)

**Auth integration**
- [x] UEK generation on user creation (builtin auth)
- [x] UEK unwrap on login, cache in session
- [x] UEK eviction on logout (memory zeroing)
- [ ] UEK re-wrap on password change _(deferred — Settings handler)_
- [ ] UEK destruction on admin password reset with confirmation _(deferred)_
- [ ] Vault passphrase prompt for mTLS/OIDC _(deferred — v0.20.0 dependency)_

**Provider key lifecycle**
- [x] Encrypt on provider create/update (all 6 write paths: admin global, personal, team)
- [x] Decrypt on completion request (all 4 read paths: completion, admin fetch, personal fetch, team fetch)
- [x] `ErrVaultLocked` handling (prompt user to unlock)

**Admin tooling**
- [ ] `switchboard vault rekey` CLI command _(deferred)_
- [ ] Admin UI: encryption status indicator _(deferred)_
- [x] Admin UI: password reset warning (v0.10.0 — vault destruction dialog)

**CI/CD**
- [x] `ENCRYPTION_KEY` Gitea secret → k8s `switchboard-encryption` secret sync
- [x] Backend k8s manifest: optional `secretKeyRef` for `ENCRYPTION_KEY`
- [x] Pipeline version bump to v0.9.4

**Security fix (bonus)**
- [x] DOMPurify: strict `ALLOWED_TAGS` allowlist (was permissive `ADD_TAGS` default)
- [x] Think-block placeholder `\n\n` padding (prevents fence fusion with `</think>`)
- [x] Unclosed code fence auto-close before `marked.parse` (streaming protection)

---

## ✅ v0.10.0 — Model Roles + Usage Tracking + Vault Debt

Three tracks of infrastructure that everything downstream depends on.

**Vault Debt (Security Fixes)**
- [x] UEK re-wrap on user password change (prevents permanent key loss)
- [x] UEK destruction on admin password reset (vault + personal BYOK keys deleted)
- [x] Admin UI: password reset confirmation with vault destruction warning
- [x] Audit logging for vault destruction events

**Model Roles** (see [EXTENSIONS.md Appendix B](EXTENSIONS.md#appendix-b-model-roles))
- [x] `model_roles` in global_settings: named slots (utility, embedding, generation)
- [x] Each role: primary provider+model, optional fallback provider+model
- [x] Team-level role overrides (team.settings JSONB)
- [x] `Provider.Embed()` interface — OpenAI/Venice/OpenRouter implement, Anthropic returns `ErrNotSupported`
- [x] `roles.Resolver` package: `Complete()` + `Embed()` with automatic fallback
- [x] Admin API: `GET/PUT /admin/roles/:role`, `POST /admin/roles/:role/test`
- [x] Team API: `GET/PUT/DELETE /teams/:id/roles/:role`
- [x] Admin UI: role configuration tab (select provider + model per role, test fire)

**Usage Tracking**
- [x] Streaming token capture fix — OpenAI: `stream_options.include_usage` + parse usage chunk;
      Anthropic: parse `message_start`/`message_delta` usage events
- [x] Cache token fields across all types (`CompletionResponse`, `StreamEvent`, `streamResult`)
- [x] `usage_log` table: channel_id, user_id, model_id, provider_config_id,
      role, token counts (prompt, completion, cache_creation, cache_read), cost, timestamp
- [x] `model_pricing` table: provider+model, input/output/cache per-M, source (catalog/manual)
- [x] Cost calculated at insert time (baked, not query-time)
- [x] BYOK exclusion: admin views filter `provider_scope != 'personal'`, BYOK gets separate endpoint
- [x] Model pricing from catalog sync (won't overwrite manual overrides)
- [x] Admin API: `GET /admin/usage`, `GET /admin/usage/users/:id`, `GET /admin/usage/teams/:id`
- [x] Admin API: `GET/PUT/DELETE /admin/pricing`
- [x] User API: `GET /usage` (personal usage summary)
- [x] Admin UI: usage dashboard (period selector, group-by, totals cards, breakdown table, pricing table)
- [x] Team admin UI: usage dashboard for team-owned providers (`GET /teams/:teamId/usage`)
- [x] Token accumulation across multi-tool-call iterations in `stream_loop.go`

**Schema (migration 004)**
- [x] `usage_log` with indexes on user, created_at, provider, model, scope
- [x] `model_pricing` with unique constraint on (provider_config_id, model_id)
- [x] `model_roles` seed in global_settings

---

## ✅ v0.10.1 — Polish + UX

Spit and polish release: admin system prompt injection, team management modal
extraction, persona tab, side panel enhancements, code download, and critical
OpenAI streaming usage race fix.

- [x] Admin system prompt (global, injected before user/preset prompts)
- [x] Personas tab (moved from Models, policy-gated)
- [x] Team Management modal (extracted from Settings, tabbed, multi-team picker)
- [x] Preview pane: clear button, fullscreen toggle, resizable
- [x] Code block: download button (infers extension from language tag)
- [x] Personal Usage scoped to BYOK only
- [x] OpenAI streaming usage race fix (deferred Done event until usage chunk)
- [x] Usage logging zero-token guard removal

---

## v0.10.2 — Summarize & Continue + Role Cleanup

First consumer of the utility model role. User-triggered conversation
compaction — not automatic (that's v0.15.0).

Depends on: utility model role (v0.10.0).

**Summarize & Continue**
- [x] "Summarize and continue" button in context warning bar (≥75% context)
- [x] `POST /channels/:id/summarize` — calls utility role with conversation history
- [x] Summary inserted as tree node with `metadata.type = "summary"` + boundary metadata
- [x] `loadConversation` recognizes summary boundaries: replaces pre-summary messages with summary system message
- [x] Multiple summaries stack (re-summarize after context fills again)
- [x] Fork-aware: summary is a tree node, branches have independent boundaries
- [x] Original messages preserved: "show full history" toggle reveals collapsed messages
- [x] Usage logged against utility role with cost tracking

**BYOK Role Overrides**
- [x] Personal role resolution chain: personal → team → global
- [x] User Settings → Model Roles tab (BYOK providers only)
- [x] Stored in `user.settings` JSONB (`model_roles` key, same shape as team overrides)
- [x] Only utility and embedding roles (generation removed)

**Generation Role Removal**
- [x] `RoleGeneration` removed from `ValidRoles` (was "generation" for image/media)
- [x] Removed from admin Roles tab UI
- [x] Image gen will be extension-managed (v0.11.0), not a role slot

**Utility Rate Limiting**
- [x] `utility_rate_limit` global setting (default: 20 calls/hour/user, 0 = unlimited)
- [x] Check against `usage_log` before executing org-funded utility calls
- [x] BYOK calls exempt (user's own key, user's own cost)
- [x] 429 response with clear message when exceeded

---

## v0.10.3 — Frontend Refactor ✅

Zero features. Split the two monolith frontend files (app.js 2,940 lines,
ui.js 2,582 lines) into 13 domain-scoped files averaging ~544 lines each.
Vanilla JS, no modules, no build step, no function renaming.

See [REFACTOR-0.10.3.md](REFACTOR-0.10.3.md) for full plan.

- [x] Extract `ui-format.js` — markdown, code blocks, `esc()`, helpers
- [x] Extract `ui-settings.js` — settings tabs, teams, providers, user prefs
- [x] Extract `ui-admin.js` — admin modal tabs, all admin rendering
- [x] Extract `tokens.js` — context tracking, token estimation
- [x] Extract `notes.js` — notes panel, editor, multi-select
- [x] Extract `chat.js` — chat ops, send, regen, edit, branch, summarize
- [x] Extract `settings-handlers.js` — settings save, provider CRUD, cmd palette
- [x] Extract `admin-handlers.js` — admin actions, presets, team management
- [x] Slim `app.js` to orchestrator — state, init, boot, auth, listener dispatch
- [x] Update `sw.js` SHELL_FILES, `index.html` script tags
- [x] All 159+ frontend tests pass, `node --check` on all files

---

## v0.10.4 — Model Type Pipeline + Role Fixes ✅

Provider APIs report model types (chat, embedding, image) — now captured
end-to-end through sync → catalog → resolver → frontend. Role dropdowns
filter models by type instead of showing everything.

- [x] Migration `005_model_type.sql` — `model_catalog.model_type` column
- [x] `providers.Model.Type` — captured from provider wire response
- [x] Venice: reads `type` field, normalizes (`text`→`chat`, `embedding`→`embedding`)
- [x] OpenAI: wire struct extended with optional `type` for compatible APIs
- [x] `CatalogSyncEntry.ModelType` → `CatalogEntry.ModelType` → `UserModel.ModelType`
- [x] Frontend `model_type` mapped through `fetchModels()`
- [x] Admin role dropdowns: filter by `model_type` matching role
- [x] User role dropdowns: filter by `model_type` matching role
- [x] `adminSaveRole()` reloads UI after save (was showing "Saved" without refresh)

---

## v0.10.5 — UI Primitives + Extension Surfaces ✅

Consolidate duplicated UI patterns into shared primitives with extension-ready
interfaces. Pre-extension infrastructure: the primitives we build now become
the `ctx.*` extension API surface in v0.11.0 with no rewrite needed.

- [x] `Providers` registry — single source of truth for types, labels, endpoints
- [x] `Roles` registry — names, type filters, hints
- [x] `renderCapBadges()` — consolidates 3 badge builders (compact + detailed modes)
- [x] `renderProviderForm()` — replaces 3 form implementations, dual-mode create/edit
- [x] `renderProviderList()` — replaces 3 list renderers, event delegation
- [x] `renderRoleConfig()` — replaces 2 role UIs + 4 handlers
- [x] `renderUsageDashboard()` — replaces 3 usage renderers (compact + full)
- [x] Admin provider form gets endpoint auto-fill (was missing)
- [x] Team provider form consolidated from 2 separate forms to 1 dual-mode
- [x] Removed ~360 lines of duplicated code + ~40 lines of static HTML
- [x] `showConfirm()` — styled confirm dialog replacing all 16 native `confirm()` calls
- [x] `.popup-menu` shared CSS + `createPopupMenu()` primitive for consistent menus
- [x] Sidebar collapse icon always visible (dimmed), brightens on hover

---

## v0.11.0 — Extension Foundation (Browser Tier)

The platform play. See [EXTENSIONS.md](EXTENSIONS.md) for full spec.

**Core Loader** (EXTENSIONS.md §4, §7)
- [ ] `extensions.js` — loader, registry, scoped context (~200 lines)
- [ ] `Extensions.register()` API with permission enforcement
- [ ] Manifest format parser and validator
- [ ] `extensions` + `extension_user_settings` tables
- [ ] Admin endpoints: install, uninstall, enable/disable
- [ ] Asset serving: `/api/v1/extensions/:id/assets/*path`
- [ ] Extension settings UI in Settings modal

**Browser Tool Bridge** (EXTENSIONS.md §5)
- [ ] `ctx.tools.handle()` API for browser tool registration
- [ ] Tool schema collection: merge built-in + extension tools
- [ ] `tool.call.*` / `tool.result.*` WebSocket routing
- [ ] 30-second timeout with LLM error recovery
- [ ] Tool execution via EventBus `WaitFor` pattern

**Custom Renderer API** (EXTENSIONS.md Appendix A)
- [ ] `ctx.renderers.register()` — pattern + render function
- [ ] Renderer pipeline in message display (after markdown, before DOM insert)
- [ ] First-party renderers: collapsible code, HTML preview, mermaid, LaTeX
      (migrate core v0.9.2 implementations to extension format)

**First Extensions**
- [ ] Image generation tool (browser or sidecar, uses generation model role)
- [ ] STT/TTS (browser extension, Web Speech API — personal use case)

---

## v0.12.0 — File Handling + Vision

File input into chat — table stakes for serious use.

**Storage Backend**
- [ ] S3-compatible API (MinIO, Ceph RGW, AWS — anything with S3 API)
- [ ] Local PVC fallback (single-node / dev)
- [ ] Admin config: backend selection, endpoint, credentials, size limits
- [ ] Reused by KBs (v0.14.0) and compaction snapshots (v0.15.0)

**Chat Integration**
- [ ] `attachments` table (metadata in PG, blobs in object store)
- [ ] Image/file upload in chat messages
- [ ] Multimodal message assembly for vision-capable models
- [ ] Text extraction on upload (PDF, DOCX, TXT → tsvector)
- [ ] Paste-to-upload (clipboard image support)
- [ ] Document generation output storage (extension → attachment → download)

---

## v0.13.0 — Web Search + Tools Expansion

Built-in tools that use the tool framework shipped in v0.7.x.

- [ ] `web_search` tool: search provider abstraction (SearXNG, Brave, DuckDuckGo)
- [ ] `url_fetch` tool: retrieve and extract content from URLs
- [ ] Sidecar or direct HTTP from backend (configurable)
- [ ] Results injected into context
- [ ] "Research X and save to my notes" workflow

---

## v0.14.0 — Knowledge Bases

Depends on: embedding model role (v0.10.0), file storage (v0.12.0).

- [ ] Embedding pipeline: chunking (recursive, semantic), generation via embedding role
- [ ] `pgvector` storage and similarity search
- [ ] `knowledge_bases` table with team scoping
- [ ] KB document storage via v0.12.0 storage backend
- [ ] `kb_search` tool (uses existing tool framework)
- [ ] Context injection in completion flow
- [ ] Notes embedded too (once pipeline exists)
- [ ] Per-channel KB toggle

---

## v0.15.0 — Compaction

Depends on: utility model role (v0.10.0).

- [ ] Auto-compaction service: background job that calls utility model to summarize
- [ ] Channel-scoped: triggers when context exceeds threshold
- [ ] Summaries stored as system messages
- [ ] Configurable: per-channel opt-in/out, summary model override
- [ ] Admin controls for resource limits

---

## v0.16.0 — @mention Routing + Multi-model

The channel schema already supports multiple models. This adds routing.

- [ ] @mention parsing in messages (users and AI models)
- [ ] Resolve mentions against `channel_models`
- [ ] Multi-model channels: fire completions per mentioned model
- [ ] "Add a model" UI per channel
- [ ] Enables: second opinions, cross-model conversations

---

## v0.17.0 — Extension Surfaces + Modes

Depends on: extension foundation (v0.11.0).
See [EXTENSIONS.md §6](EXTENSIONS.md#6-surfaces-modes).

- [ ] Surface registration and activation API
- [ ] Mode selector in sidebar (below brand, above chat history)
- [ ] `ctx.ui.replace()` / `ctx.ui.restore()` for region management
- [ ] `surface.activated` / `surface.deactivated` events
- [ ] Editor mode (extension: file tree + code editor + AI chat split pane)
- [ ] Article mode (extension: outline + rich text + AI assistant panel)

---

## v0.18.0 — Smart Routing

Depends on: model roles (v0.10.0), usage tracking (v0.10.0).
Rules-based routing engine — policy, not ML.

- [ ] Admin routing policies: "cheapest model with required capabilities",
      "prefer private providers, fallback to cloud", "for team X, use Y"
- [ ] Fallback chains: primary provider down → next with same model
- [ ] Cost-aware: factor pricing into routing decisions
- [ ] Latency-aware: track response times per provider, prefer faster

---

## v0.19.0 — Multi-Participant Channels + Presence

The channel foundation for workflows and real-time collaboration. Today
channels are single-user direct chats. This release makes channels a
shared space that multiple actors can inhabit.

Depends on: extension surfaces (v0.17.0), WebSocket infrastructure (already exists).

**Channel Participants**
- [ ] `channel_participants` table: `channel_id`, `participant_type` (user, session, persona), `participant_id`, `role` (owner, member, observer), `joined_at`
- [ ] Channel access queries rewritten: `WHERE user_id = $1` → participant-based lookup
- [ ] Backward compatible: existing single-user channels auto-have one participant (owner)
- [ ] Channel `type` column: `direct` (current), `group` (multi-user), `workflow` (staged)

**Presence + Real-time**
- [ ] Typing indicators and presence (who's online, who's in this channel)
- [ ] Participant join/leave events via WebSocket
- [ ] Co-editing for extension surfaces (editor mode, article mode)
- [ ] Cursor sharing, selection highlighting

**Channel-Scoped Notes**
- [ ] Optional `channel_id` FK on notes (NULL = personal notebook, set = channel-attached)
- [ ] Notes created by tool calls within a channel auto-attach to that channel
- [ ] Channel notes visible to all participants (not just creator)

---

## v0.20.0 — Auth Strategy (mTLS/OIDC) + Full RBAC

Enterprise auth modes on top of the teams foundation.
Depends on: vault passphrase support from v0.9.3 (conditional unlock for
personal providers under external auth).

- [ ] `AUTH_MODE` env var: `builtin` | `mtls` | `oidc`
- [ ] All three resolve to the same internal user model
- [ ] `auth_source` + `external_id` columns on users table
- [ ] mTLS: header trust, auto-provision from cert DN
- [ ] OIDC: Keycloak/Okta token validation, claim extraction, role mapping
- [ ] Per-source auto-activate policy: auto_activate, default_team, default_role
- [ ] Vault passphrase prompt for mTLS/OIDC users (v0.9.3 conditional unlock)
- [ ] Fine-grained permissions: model access, KB write, task create, token budgets

**Anonymous / Session Participants**
- [ ] Session-based identity for unauthenticated visitors (workflow intake)
- [ ] mTLS: cert CN/fingerprint as stable session identity (no `users` row required)
- [ ] Non-mTLS: ephemeral session token (cookie or URL token)
- [ ] Session participants can send messages and trigger tool calls within workflow channels
- [ ] Session identity visible to assigned team members (cert DN, display name, or "Anonymous #N")

---

## v0.21.0 — Workflow Engine

Team-owned, stage-based process execution. The channel is the runtime,
personas drive each stage, and the existing tool/notes infrastructure
handles structured data collection. See [ARCHITECTURE.md — Workflow
Architecture](ARCHITECTURE.md#workflow-architecture-future--v0210) for
the conceptual model.

Depends on: multi-participant channels (v0.19.0), anonymous identity (v0.20.0).

**Workflow Definitions**
- [ ] `workflows` table: `team_id` (owner), `name`, `description`, `is_active`, `entry_mode` (public_link, team_internal, api)
- [ ] `workflow_stages` table: `workflow_id`, `ordinal`, `persona_id`, `assignment_team_id`, `form_template` (JSONB, structured note schema), `transition_rules` (JSONB)
- [ ] Team-admin CRUD: create/edit/delete workflows and stages
- [ ] Workflow versioning: edits create new version, active instances continue on their version

**Workflow Instances (Channels)**
- [ ] Workflow-typed channels: `type='workflow'`, `workflow_id`, `current_stage`, `stage_version`
- [ ] Entry point: public link generates workflow channel, adds anonymous participant, binds stage 1 persona
- [ ] Stage transitions: triggered by AI (tool call), team member (button), or rule (form complete)
- [ ] On transition: swap active persona, notify assignment team, update channel metadata

**AI Intake**
- [ ] Stage persona drives structured collection via system prompt
- [ ] Form template → persona system prompt injection ("collect these fields: ...")
- [ ] Tool calls create channel-scoped notes as form responses
- [ ] AI determines readiness: "I have everything needed" → trigger transition

**Assignment + Queue**
- [ ] Assignment queue: unassigned workflow channels visible to team members
- [ ] Claim model: team member claims channel (becomes participant with `member` role)
- [ ] Round-robin / rule-based auto-assignment (optional, per-stage config)
- [ ] Assignment notifications via WebSocket + optional webhook

**Team Member Collaboration**
- [ ] Assigned member sees full history (AI intake + artifacts + notes)
- [ ] Persona remains active — assists both visitor and team member
- [ ] Member can trigger stage transitions, add notes, invoke tools
- [ ] Member can reassign to different team member or escalate to different team

**Frontend**
- [ ] Workflow builder UI in team admin panel (stage list, persona picker, form template editor)
- [ ] Queue view: sidebar section showing unassigned workflow channels for user's teams
- [ ] Channel header: workflow stage indicator, transition controls
- [ ] Anonymous visitor view: minimal UI, persona-driven conversation (public link entry)

---

## v0.22.0 — Tasks / Autonomous Agents

Unattended execution — workflows without a human in the loop.
Depends on: workflow engine (v0.21.0).

- [ ] Scheduler + task runner (cron-like triggers for workflow instantiation)
- [ ] `task_create` tool (AI can spawn sub-workflows)
- [ ] `type: 'service'` channels: workflow instances with no human participants
- [ ] Execution budgets: max tokens, max tool calls, max wall-clock per stage
- [ ] Admin controls for resource limits and kill switches
- [ ] Completion webhooks (notify external systems when workflow completes)

---

## TBD (unscheduled — real features, no immediate need)

Items that are real but don't yet have a version assignment. Pull left
based on need.

**Extension System — Server Tiers**
- Starlark runtime integration (Tier 1 — server sandbox)
- Sidecar HTTP tool protocol (Tier 2 — container isolation)
- Server-side tool execution in completion handler

**Desktop + Mobile**
- Desktop app (Tauri)
- Full PWA with offline capability
- Mobile-optimized layouts (beyond current responsive)

**Data + Portability**
- Bulk export/import (account data, conversations, settings)
- ChatGPT/other tool import
- GDPR-style "download my data"
- Backup/restore CronJob manifests

**UX / Multi-Seat**
- Per-chat model/preset persistence (server-side). Currently a localStorage
  bandaid (v0.10.2) that doesn't roam across devices. Proper fix: store
  `last_selector_id` in `channels.settings` JSONB on each send. On chat
  selection, resolve from `channel.settings.last_selector_id` → match against
  available models/presets → fall back to `channel.model` → global default.
  Eliminates device-local state entirely. Needs `updateChannel` PATCH on
  completion success (single extra column merge, no migration).

**Platform**
- Rate limiting per user/team/tier (token budgets)
- Provider health monitoring + key rotation
- Multi-tenant SaaS mode
- Plugin/extension marketplace
- Virtual scroll for long conversations
- SQLite backend option (single-user / dev)