Archived

This repository has been archived on 2026-04-03. You can view files and clone it. You cannot open issues or pull requests or push a commit.

Files

xcaliber b6cc4df6e7 Changeset 0.24.1 (#157 )

2026-03-07 17:11:32 +00:00

87 KiB

Raw Blame History

Roadmap — Chat Switchboard

See also:

ARCHITECTURE.md — Core services design, store layer, scope model
EXTENSIONS.md — Extension system spec (Browser/Starlark/Sidecar tiers, manifests, browser tool bridge, surfaces/modes, model roles)
CHANGELOG.md — Detailed release notes for all completed versions

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                    ✅
          │
v0.10.3 Frontend Refactor                       ✅
          │
v0.10.4 Model Type Pipeline + Role Fixes        ✅
          │
v0.10.5 UI Primitives + Extension Surfaces      ✅
          │
v0.11.0 Extension Foundation (browser tier)     ✅
          │
  ┌───────┴──────────────┐
  │                      │
v0.12.0 File Handling  v0.13.0 Admin Panel
  + Vision ✅            Refactor (fullscreen) ✅
  │                      │
  │                    v0.13.1 Web Search
  │                      + url_fetch ✅
  │                      │
  └───────┬──────────────┘
          │
v0.14.0 Knowledge Bases ✅ (embedding role + file storage + pgvector)
          │
v0.15.0 Compaction ✅ (utility role + background job)
          │
v0.15.1 Context Recall Tools ✅ (attachment_recall, conversation_search)
          │
  ┌───────┴──────────────┐
  │                      │
v0.16.0 User Groups    v0.17.0 Persona-KB Binding
  + Resource Grants ✅   + Enterprise KB Mode
  │                      + QOL / UX Wins
  └───────┬──────────────┘
          │
  ┌───────┴──────────────┐
  │                      │
v0.17.1 SQLite Backend ✅ v0.17.2 CodeMirror 6 ✅
v0.17.3 Notes Graph + Wikilinks ✅
  (dual DB)              (editor bundle, chat
  │                       input, ext editor)
  └───────┬──────────────┘
          │
v0.18.0 Memory ✅ (user + persona scopes, review pipeline)
          │
v0.18.1 Side Panel Architecture ✅ (single-slot, ctx.ui primitives, mermaid refactor)
          │
v0.19.0 Projects / Workspaces ✅ (project groups, KB resolution, drag-drop sidebar)
          │
v0.19.1 Active Project + System Prompt + Detail Panel ✅
          │
v0.19.2 Project Persona Default + Archive + Reorder ✅
          │
v0.20.0 Notifications + @mention Routing + Multi-model   ✅
          │
v0.21.0 Workspace Storage Primitive                      ✅
          │
  ┌───────┴──────────────┐
  │                      │
v0.21.1 Workspace ✅   v0.21.3 Surface Infra ✅
  Tools + Bindings       + REPL (parallel)
  │                      │
v0.21.2 Workspace ✅   v0.21.5 Editor Surface ✅
  Indexing + Search      (Development Mode)
  │                      │
v0.21.4 Git ✅         v0.21.6 Editor Surface ✅
  Integration            + Document Output
  └───────┬──────────────┘
          │
v0.21.7 Bugfix: scanJSON driver buffer aliasing   ✅
          │
v0.22.0 Provider Health + Capability Overrides     ✅
  + Workspace Pane Refactor (FE)
          │
v0.22.1 Provider Extensions (declarative config)   ✅
          │
v0.22.2 Routing Policies + Fallback Chains          ✅
          │
v0.22.3 Provider Admin UI + Deferred Polish          ✅
          │
v0.22.4 Provider Health UX + Project Files + Export   ✅
          │
v0.22.5 Surfaces + Go Templates + Admin Bug Fixes     ✅
          │
v0.22.6 Split Deployment Fix + CI Timeout + Code Pruning  ✅
          │
v0.22.7 Surface Prototypes (Theme + ChatPane + Splash)     ✅
          │
v0.22.8 Surface Integration (Wire into existing JS)        ✅
          │
v0.23.0 @mention Routing + Persona Handles + Proxy         ✅
          │
v0.23.1 Multi-User Navigation + Conversation Taxonomy      ✅
          │
v0.23.2 Multi-User Polish + Channel Lifecycle              ✅
          │
v0.24.0 Auth Abstraction + User Identity                   ← active
          │
          ├── v0.24.1 mTLS + OIDC Providers (parallel)
          │       │
          │       └── v0.24.3 Anonymous Sessions
          │
          └── v0.24.2 Fine-Grained Permissions (parallel)
          │
  ┌───────┴──────────────┐
  │                      │
v0.25.0 Workflow       v0.26.0 Tasks /
  Engine                 Autonomous Agents
  (team-owned,           (service channels,
   staged processes,      scheduler, unattended
   human + AI collab)     execution)

Completed Releases

Full details for all completed versions are in CHANGELOG.md.

✅ v0.9.0 — Schema Consolidation + BYOK

21 migrations → single schema, store layer abstraction, persona-as-trust-boundary, BYOK with auto-fetch, composite model IDs, journey integration tests.

✅ v0.9.1 — Capability Architecture + Docs

Removed static known model table. Resolution chain: catalog → heuristic only. Frontend relies solely on backend for capabilities. Docs rewrite.

✅ v0.9.2 — Quick UX Wins + Hardening

Collapsible code blocks, HTML preview, token counter, context warning, proxy interception detection, environment injection, team admin audit scoping.

✅ v0.9.3 — Content Visibility & Block Controls

Button-driven code collapse, always-rendered thinking blocks, tool call persistence in history, Notes panel → unified side panel, streaming refactor (streamWithToolLoop), regenerate fix.

✅ v0.9.4 — API Key Encryption + Vault

Two-tier AES-256-GCM: env-var key for global/team, per-user UEK (Argon2id) for personal BYOK. server/crypto/ package. Migration 003. Startup backfill. DOMPurify strict allowlist (XSS fix).

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

Named role slots (utility, embedding) with fallback. Provider.Embed() interface. usage_log + model_pricing tables. Streaming token capture. Vault debt: UEK re-wrap on password change, destruction on admin reset.

✅ v0.10.1 — Polish + UX

Admin system prompt injection, Personas tab, Team Management modal extraction, preview pane enhancements, code download, personal usage scoped to BYOK.

✅ v0.10.2 — Summarize & Continue + Role Cleanup

User-triggered conversation compaction via utility role. Summary as tree node with boundary metadata. BYOK role overrides (personal → team → global). Utility rate limiting. Generation role removed.

✅ v0.10.3 — Frontend Refactor

2 monolith files → 13 domain-scoped files (~544 lines avg). Zero features, no function renames. Vanilla JS, no build step. See REFACTOR-0.10.3.md.

✅ v0.10.4 — Model Type Pipeline + Role Fixes

model_type (chat/embedding/image) captured end-to-end from provider API through catalog to frontend. Role dropdowns filter by type.

✅ v0.10.5 — UI Primitives + Extension Surfaces

Shared Providers/Roles registries, 6 consolidated render primitives, showConfirm() replacing native dialogs, .popup-menu CSS primitive. Removed ~400 lines of duplication.

✅ v0.11.0 — Extension Foundation (Browser Tier)

Full extension lifecycle: manifest, loader, scoped ctx.* API, browser tool bridge via WebSocket. Custom renderer pipeline. 2 server tools (calculator, datetime), 6 built-in browser extensions (Mermaid, KaTeX, CSV, Diff, JS Sandbox, Regex). See EXTENSIONS.md.

✅ v0.12.0 — File Handling + Vision

S3/PVC storage backend, image/file upload (📎, drag-drop, paste), multimodal message assembly, text extraction pipeline (PDF/DOCX/XLSX/PPTX/ODT/RTF), vault CLI (rekey/status), per-chat model persistence.

✅ v0.13.0 — Admin Panel Refactor

12-tab modal → fullscreen admin panel. 4 categories (People, AI, System, Monitoring) × section sidebar. URL-based routing, responsive, banner-aware. CSS design token cleanup.

✅ v0.13.1 — Web Search + URL Fetch

web_search + url_fetch tools. Search provider abstraction (DuckDuckGo, SearXNG). Tool categories with per-tool toggle UI in chat bar.

✅ v0.14.0 — Knowledge Bases

RAG: upload → chunk → embed (pgvector) → kb_search tool. Channel KB toggle. Team/personal KB scopes. Notes semantic search. Admin panel KB management. See DESIGN-0.14.0.md.

✅ v0.15.0 — Compaction

Background scanner with configurable thresholds. Automatic summarization via utility role. Per-channel opt-in/out. Context budget guard rail (80% ceiling).

✅ v0.15.1 — Context Recall Tools

attachment_recall (list + read, channel-scoped), conversation_search (full-text via plainto_tsquery). Token estimator attachment awareness.

✅ v0.16.0 — User Groups + Resource Grants

Groups (global/team-scoped ACLs) decoupled from team membership. Three-way resource grants (team_only/global/groups) for Personas and KBs. Grant picker UI. Schema consolidation: 9 migrations → single 001_v016_schema.sql.

v0.17.0 — Persona-KB Binding + Enterprise KB Mode + QOL ✅

Personas become gateways to knowledge. In enterprise deployments, users don't interact with KBs directly — they talk to Personas that have KBs attached. Plus quality-of-life improvements: chat rename, token display, state persistence, utility model auto-naming.

Depends on: knowledge bases (v0.14.0), user groups (v0.16.0).

Persona-KB Binding

persona_knowledge_bases table: persona_id, kb_id, auto_search (bool — always search vs tool-only)
When a channel uses a Persona with bound KBs, kb_search is auto-scoped to those KBs
No user toggle needed — Persona carries its own KB context
Channel KB toggle becomes "additional KBs" on top of Persona-provided ones
Persona system prompt auto-includes KB listing hint (reuses BuildKBHint pattern)
Admin/team admin UI: KB picker on Persona create/edit form

Enterprise KB Mode

discoverable flag on knowledge_bases: true (default — appears in user's KB popup) or false (hidden, only accessible through Persona binding)
Hidden KBs don't appear in GET /api/v1/knowledge-bases-discoverable for non-admins
Hidden KBs still searchable by kb_search tool when accessed through a Persona
Admin panel: toggle discoverability per KB
Platform policy: kb_direct_access — when false, disables channel KB popup entirely (strict enterprise mode)

Access Control Integration

Persona grants (v0.16.0 groups) control who can use a Persona
KB grants control who can manage a KB (upload/delete docs)
Persona-KB binding grants implicit search access through the Persona
Users who can use a Persona can search its KBs, even if they can't see those KBs directly

Team Admin Workflow

Team admin creates KB → uploads documents → marks non-discoverable
Team admin creates Persona → binds KBs → sets access to Team Only or specific Groups
Team members see the Persona in their preset list, use it, get KB-powered answers
Team members never see or manage the underlying KBs

Technical Debt (carried forward)

Security: KB create handler authorization — team/global scope verified
Test hygiene: stripped DIAG diagnostics from TestGroupBasedPersonaAccess
Architecture: KnowledgeBaseStore.UpdateDocumentStorageKey() — moved to store layer
UX: Embedding dropdown fix — tolerant type filter, manual model ID fallback, auto-switch on empty (already implemented in ui-primitives.js)
Minor: Paste-to-file character threshold — synced from backend PublicSettings (storage.paste_to_file_chars), admin-configurable, default 2000

Role Fallback Alerts (#69)

Audit log entry on fallback fire: action = "role.fallback" with primary/fallback model IDs and error string
role.fallback WebSocket event via EventBus (PublishAsync, zero latency impact on completion path)
In-memory cooldown on Resolver (per-role, 5-minute TTL) to deduplicate repeated fallback alerts
Admin UI: persistent alert banner on role.fallback event (persists until dismissed)
Wire *events.Bus into roles.NewResolver via .WithBus() builder

QOL / UX Wins

Chat rename: inline edit on sidebar item — dblclick title → input → blur/Enter saves via API.updateChannel(id, { title })
Chat token count: display Tokens.estimateConversation() in model bar, update on selectChat and after each message
State restore on refresh: persist App.currentChatId to sessionStorage on select, restore on load
Utility model auto-naming: after first assistant response, background utility role request → POST /channels/:id/generate-title → re-render sidebar. Fallback to truncation when no utility model configured. Debounced via _autoNamePending set
SW extension cache fix: exclude /extensions/ from service worker fetch handler
Mermaid renderer: promoted enhanced version (v2.0 — pan/zoom, SVG/PNG export, source copy) to extensions/builtin/mermaid-renderer/

v0.17.1 — SQLite Backend ✅

Dual-database support. Every subsequent schema change is developed against both Postgres and SQLite from day one — no retrofit. SQLite enables single-binary deployment for dev, demo, edge, and single-user.

Depends on: v0.17.0 DB debt cleanup (store layer is sole DB interface).

Store Layer

19 SQLite store implementations covering all domain interfaces
DB_DRIVER env var: postgres (default) | sqlite
Separate migration files per driver (migrations/sqlite/)
WAL mode + single-writer connection pooling for SQLite concurrency
CI matrix: full handler integration tests against both Postgres and SQLite

Vector Search

App-level cosine similarity in Go (pure Go, no CGO/sqlite-vec required)
Embeddings stored as JSON text in kb_chunks.embedding column
Full feature parity with pgvector: SimilaritySearch, InsertChunks
Graceful: adequate performance for SQLite-scale deployments (single-user, not millions of chunks)

Schema Compatibility

UUID generation: application-side store.NewID() (Go uuid.New())
JSONB → JSON text columns with ToJSON()/ScanJSON() helpers
UUID[] arrays → JSON arrays with ToJSONArray()/ScanJSONArray()
TIMESTAMPTZ → SQLite TEXT with datetime('now')
ON CONFLICT excluded.* pattern (works in both dialects)
INSERT RETURNING id → separate query pattern for SQLite

Test Infrastructure

dialectSQL() converts $N → ? and strips ::jsonb at runtime
database.PH(n) returns dialect-appropriate placeholder
database.TruncateAll() dialect-aware (DELETE + PRAGMA vs TRUNCATE CASCADE)
Generic provider config: PROVIDER/PROVIDER_KEY/PROVIDER_URL (replaces VENICE_API_KEY)
Model selection prefers non-reasoning models in live tests

What SQLite mode skips (feature-gated, not broken):

LISTEN/NOTIFY — WebSocket event fan-out uses in-process EventBus (already works)
Full-text search tsvector — conversation_search uses LIKE fallback

v0.17.2 — CodeMirror 6 Integration ✅

Rich editor infrastructure for the frontend. CM6 is ESM-native; the build step runs in Docker (esbuild → single IIFE bundle). No change to dev experience for non-editor code — the rest of src/js/ stays vanilla.

Depends on: nothing (frontend-only). Prerequisite for: extension surfaces (v0.21.5 editor surface). See DESIGN-CM6.md for full spec.

Build Pipeline

src/editor/ directory: package.json, build.mjs, index.mjs, language/theme modules
scripts/build-editor.sh: shared build script for both Dockerfiles and local dev
New Docker stage (cm6-build): npm ci + node build.mjs → vendor/codemirror/
Both Dockerfile.frontend and Dockerfile (unified) use the shared build script
Bundle output: codemirror.bundle.js (~295KB min, ~90KB gzip)
Graceful degradation: all integration points check window.CM — falls back to <textarea> if bundle unavailable

Languages (bundled)

Markdown, JavaScript, JSON, SQL, HTML, CSS, YAML, Go, Python, Rust
Additional modes: one-line import + rebuild

Phase 1: Extension Editor (admin panel)

CM.codeEditor() factory: line numbers, bracket matching, auto-indent, search/replace
Replace manifest <textarea> → CM6 JSON mode
Replace script <textarea> → CM6 JavaScript mode
Remove manual Tab-key handler in admin-handlers.js (CM6 handles it)
Update saveAdminExtension() to use .getValue()

Phase 2: Chat Input (markdown mode)

CM.chatInput() factory: markdown highlighting, minimal chrome (no line numbers, no gutter)
Enter=send, Shift+Enter=newline keybindings
Auto-growing height, placeholder text
Wire onChange → updateInputTokens()
Update chat.js, attachments.js, tokens.js to use CM API
WYSIWYG fenced code block decorations (visual container matching claude.ai UX)
Inline code shortcut (Ctrl/Cmd+E)

Phase 3: Polish

Theme integration: CSS variable overrides (--bg, --border, --accent, etc.)
Dark/light/system mode toggle in appearance settings
Vim/Emacs keybinding preference in appearance settings (@replit/codemirror-vim, @replit/codemirror-emacs)
Vim/Emacs applies to code editor + extension editor only (never chat input)
SW cache: exclude vendor/codemirror/ with version bust
Update debug.js snapshot to include CM6 version
Documentation in ARCHITECTURE.md

CI/CD

Path-based change detection gating (FE-only → skip BE tests, docs-only → skip all)

v0.17.3 — Notes Graph + Wikilinks ✅

Knowledge graph and bi-directional linking for the notes system. Transforms notes from flat documents into an interconnected knowledge base with Obsidian-style [[wikilinks]], backlinks, graph visualization, and transclusion.

Depends on: CodeMirror 6 (v0.17.2), Notes CRUD (v0.13.x). See DESIGN-0.17.3.md for full spec.

Backend: Note Links

note_links table (Postgres + SQLite migrations)
NoteLinkStore interface + both implementations
ExtractWikilinks() regex parser + tests
Link extraction on note create/update
Dangling link resolution on note create
notes.source_message_id column for chat-to-note provenance

API Endpoints

GET /notes/:id/backlinks — notes linking to this note
GET /notes/search-titles?q= — lightweight fuzzy search for autocomplete
GET /notes/graph — full graph topology (nodes + edges + unresolved)

CM6 Note Editor

note-editor.mjs factory: markdown live preview (heading sizes, blockquotes, code blocks)
wikilink.mjs CM6 extension: parse, decorate as clickable chips, autocomplete on [[
Textarea → CM6 swap in notes.js with graceful fallback
noteEditorTheme in theme.mjs

Graph Visualization

Canvas-based force-directed graph (~200 lines, no d3 dependency)
O(n²) Coulomb repulsion + Hooke spring + center gravity
Pan, zoom (0.15–4.0x), drag nodes, hover highlight, click to open
Node sizing by link_count, folder-based coloring
Ghost nodes for unresolved [[links]] with toggle
Energy-based pause (stop rAF below KE threshold)
ResizeObserver for responsive canvas

Note-from-Selection + Daily Notes

"Note" button in message action bar
Selection-aware capture (window.getSelection() within message)
Provenance tracking (source_channel_id + source_message_id)
"Today" button → find-or-create daily note in /daily/

Read Mode

[[link]] rendered as clickable wikilink chips
![[embed]] transclusion with async content fetch, recursion guard
Backlinks panel (collapsible, with count badge)

v0.18.0 — Memory (User + Persona Scopes) ✅

Long-term memory across conversations, with scope-aware isolation. Unlike KB (static documents) or compaction (within-conversation), this captures facts and preferences that persist across channels.

Key differentiator: Persona-scoped memory. Each Persona can build its own memory independently of user memory, preventing cross-context contamination and enabling specialized knowledge accumulation.

Depends on: compaction (v0.15.0), knowledge bases (v0.14.0), persona-KB binding (v0.17.0), SQLite backend (v0.17.1).

See DESIGN-0.18.0.md for full spec.

Memory Scopes

user — personal facts/preferences, persists across all conversations (current industry standard)
persona — shared across all users of that Persona, accumulated from conversations (differentiator)
persona+user — per-user within a Persona context (e.g. tutoring progress per student)
Configurable per Persona: which scopes are active, whether user memory is passed through

Data Model

memories table: id, scope (user, persona, persona_user), owner_id (user_id or persona_id), user_id (nullable — for persona+user scope), key, value, source_channel_id, confidence (float), status (active, pending_review, archived), created_at, updated_at
Index on (scope, owner_id, user_id) for fast lookup
Embedding column (vector(3072)) for semantic memory search

Tools

memory_save tool: LLM explicitly stores a fact
- Scope-aware: saves to the active memory scope for the current Persona context
- Structured: key (short label) + value (detail) + confidence
memory_recall tool: LLM queries stored facts relevant to current context
- Merges results from applicable scopes (user + persona + persona+user)
- Semantic search via embeddings + keyword fallback

Automatic Extraction

Background job: post-conversation analysis identifies memorable facts (opt-in)
Configurable extraction prompt per Persona (e.g. "extract FAQ-worthy Q&A pairs")
Extracted memories start in pending_review status

Review Pipeline

Admin/team admin review queue: pending memories with approve/reject/edit
Persona memory review: team admins see what Personas are "learning"
User memory review: users see their own memories in Settings

Memory Injection

At completion time: inject relevant memories into system prompt
Context budget aware: limit injected memory tokens
Scope priority: persona+user > persona > user (most specific wins on conflicts)

Use Cases

Helpdesk Persona: builds FAQ from repeated questions, human-reviewable
Roleplay Persona: isolated memory prevents tone/context bleeding from user's other conversations
Tutoring Persona: tracks per-student progress, common misconceptions
Sales Persona: accumulates objection responses from real conversations
Onboarding Persona: learns what new hires commonly struggle with

User Controls

Settings → Memory: view, edit, delete personal memories
Per-Persona memory toggle: "Allow this persona to remember things about me"
Admin: enable/disable, retention policies, per-team scoping
Privacy: user memories never cross team boundaries; persona memories respect group access

v0.18.1 — Side Panel Architecture ✅

Refactored the side panel from a shared-tab layout to independent single-slot panels. Any action fills the slot, replacing whatever was there — no tabs, no association between panel types. Extension UI primitives give browser extensions safe access to host app features.

Depends on: Notes graph + wikilinks (v0.17.3). Prerequisite for: live collaboration (v0.23.0) where multiple panels need simultaneous visibility.

Panel System

Panel registry: named panels with independent open/close state
Single-slot model: action-driven, each open replaces the previous
Dual-view mode: two panels side-by-side (configurable split ratio via drag divider)
Panel-persistent state: each panel remembers scroll position, open note, etc.
Header label shows active panel name (replaces tab bar)
Keyboard shortcut: Ctrl/Cmd+\ cycles panels, Ctrl/Cmd+Shift+\ toggles dual

Preview Panel

Dedicated preview panel (independent of Notes)
HTML/document preview with iframe sandbox
Code output preview (extension-rendered blocks via pop-out)
Live-updating during streaming responses (500ms debounce)

Extension UI Primitives

ctx.ui.toast() — toast notifications
ctx.ui.openPreview() — load HTML into side panel preview
ctx.ui.isDark() — theme detection
ctx.ui.isMobile() — viewport width check
ctx.ui.isPanelOpen() — side panel visibility
ctx.ui.confirm() — modal confirm dialog
Mermaid extension refactored to use primitives exclusively (zero direct globals)
Context-aware expand: single button, fullscreen or side panel pop-out

Mobile

Swipe navigation between panels
Tap-to-close overlay
Graceful collapse to single-panel on narrow viewports
Enlarged touch targets, fullscreen close button (40px desktop, 48px mobile)

✅ v0.19.0 — Projects / Workspaces

Organizational containers that group related conversations, KBs, and notes into a single workspace with shared access controls.

Depends on: user groups (v0.16.0), knowledge bases (v0.14.0).

Data Model

projects table: id, name, description, color, icon, scope (personal/team/global), owner_id, team_id, is_archived, settings (JSONB)
project_channels junction: ordered membership with UNIQUE channel_id, denormalized FK on channels.project_id
project_knowledge_bases junction: with auto_search flag
project_notes junction
resource_grants CHECK extended to include 'project'

Features

Channels can belong to a project (optional project_id FK)
KBs can belong to a project → auto-linked to all channels in the project (BuildKBHint + kbsearch)
Notes can belong to a project → auto-associated when created from project channel
KB resolution chain: Persona → Project → Channel → Personal
Project sidebar section: collapsible groups above time-based Recent section

Sidebar: projects as collapsible groups with color dots, counts, options menu
Right-click context menu: move chat to project / remove / create-and-assign
Drag-and-drop channels between project groups and Recent
New Project button in split dropdown
Channel list project_id filter (?project_id=uuid or ?project_id=none)
Collapse state persisted in localStorage

Deferred to later versions:

Project creation dialog (name, description, default Persona, default KBs) — using prompt() for now
~~Project detail panel (KB + note management within a project)~~ → v0.19.1
~~Project-level Persona default~~ → v0.19.2
Folders within projects
Project templates
Admin-level team/global project management
Project-specific files (full project-level upload — deferred for proper architecture)
Notifications (moved to v0.20.0)

✅ v0.19.1 — Active Project + Project System Prompt + Detail Panel

Quality-of-life improvements making projects usable for daily workflow. No migrations.

Depends on: v0.19.0 Projects/Workspaces.

Active Project

Pin a project as active — new chats auto-assign via addChannelToProject after channel creation
App.activeProjectId persisted in localStorage('cs-active-project')
Visual indicator: .project-group.active accent border + 📌 icon
Toggle from project ⋯ menu ("Pin as active" / "Unpin project")
Cleared on project delete

Project System Prompt

Per-project instructions in projects.settings JSONB (system_prompt key)
Injected in loadConversation between persona/channel prompt and KB hint
Merge semantics on update: reads existing JSONB, overlays patch keys, writes back
Both Postgres and SQLite stores updated

Project Detail Panel

Registered with PanelRegistry (same pattern as Notes, Preview)
System prompt textarea with Save button
KB management: list with names (LEFT JOIN), [+ Add] picker dropdown, [✕] remove
Notes list with titles (LEFT JOIN), [✕] unbind
Accessible from project ⋯ menu → "Project settings"

Bug Fixes

renderChatList early return prevented project groups from rendering when zero chats
Recent section drop target: "Drop chats here to unassign" hint with min-height: 40px

✅ v0.19.2 — Project Persona Default + Archive + Channel Reorder

Completes the project management feature set. No migrations.

Depends on: v0.19.1.

Project Persona Default

Bind a persona to a project via detail panel dropdown
Stored in projects.settings.persona_id
Resolution chain: explicit req.PresetID → project persona → none
Inherits model, provider config, temperature, max tokens, system prompt as defaults

Project Archive Toggle

Checkbox in project detail panel
Archived projects hidden from sidebar by default
"▸ Show archived (N)" toggle button below project list
Chats in hidden-archived projects spill into Recent section (never vanish)
Dimmed + italic visual treatment for archived groups

Channel Reorder

loadProjectChannelPositions() fetches server-persisted positions on startup
_getReorderedProjectChats() sorts project chats by stored position
Right-click context menu: ↑ Move up / ↓ Move down (optimistic swap + API call)
Order maintained across add/remove/move operations

v0.20.0 — Notifications + @mention Routing + Multi-model ✅

Notification infrastructure that makes collaboration real-time, plus multi-model routing for channels. Three-phase delivery: notifications core (in-app), @mention parsing + fan-out completions, email transport

per-user notification preferences.

(Notifications shifted from v0.19.0; @mention routing shifted from v0.17.0)

Depends on: v0.19.2 (Projects complete), EventBus + WebSocket hub (v0.9.x), channel_models table (v0.16.0 schema). See DESIGN-0.20.0.md for full spec.

Phase 1 — Notifications Core (in-app)

notifications table: id, user_id, type, title, body, resource_type, resource_id, is_read, created_at (Postgres + SQLite migrations)
NotificationStore interface + both implementations: Create, ListByUser (paginated), MarkRead, MarkAllRead, Delete, UnreadCount
notifications.Service with Notify() / NotifyMany() — centralized creation + WebSocket dispatch
EventBus routes: notification.new, notification.read (badge sync across tabs)
API endpoints: list, unread-count, mark-read, mark-all-read, delete (5 endpoints, all user-scoped)
Initial sources: role.fallback (EventBus subscription), kb.ready/kb.error, grant.changed
Frontend: bell icon + unread badge (capped 9+), notification dropdown (latest 10, click-to-navigate), full panel via PanelRegistry
WebSocket handler: real-time push + toast for high-priority types
Background cleanup goroutine (configurable retention, default 90 days)

Phase 2 — @mention Parsing + Multi-model Routing

mentions.Parse(): extract @mentions, resolve against channel model roster (case-insensitive, longest-match-first, trailing punctuation tolerant)
Parser tests: no mentions, unresolved, multiple, overlapping names, punctuation edge cases
Channel model CRUD handlers (4 endpoints: list, add, remove, update)
Completion handler: mention extraction → target resolution → sequential fan-out → N assistant messages
SSE streaming: model attribution in delta events (model_display field)
Frontend: model pills in chat header with add/remove UI
Frontend: @mention autocomplete via CM6 mentionCompletion extension (roster-backed)
Frontend: model attribution labels on multi-model assistant messages
Backward compat: channels with no extra channel_models rows work exactly as before

Phase 3 — Email Transport + Notification Preferences

notification_preferences table (Postgres + SQLite): per-user, per-type in_app/email toggles
Preference resolution chain: specific type → user wildcard * → system default (in_app=true, email=false)
EmailTransport: SMTP with implicit TLS (port 465) and STARTTLS (port 587), multipart MIME (HTML + plaintext)
Email templates: branded HTML + plaintext, domain-prefixed subjects, Go html/template
Preference CRUD endpoints (3: list, set with partial patch, delete)
Admin SMTP configuration: enable toggle, host/port/user/password/from/TLS fields, test email button
User notification preferences UI (Settings → Notifications tab, per-type checkboxes)
Notification service: preference check before dispatch, async email delivery (goroutine, 30s timeout)
Tests: preference resolution chain (7 tests), email templates (4 tests)
Deferred: digest mode (batched email), SMTP password vault encryption

Hotfix (carried forward from v0.19.2 investigation)

user_model_settings NULL scan fix: COALESCE on hidden/sort_order in SELECT + INSERT for both dialects
Gin release mode: auto-set gin.ReleaseMode when ENVIRONMENT=production, suppress health check log spam

v0.21.x — Workspace Platform + Extension Surfaces

Seven-release series decomposing workspace storage, tools, indexing, git, surface infrastructure, and editor/article modes. Full specification in DESIGN-0.21.0.md.

Depends on: file storage (v0.12.0), extension foundation (v0.11.0), CodeMirror 6 (v0.17.2), knowledge base embedding pipeline (v0.14.0).

v0.21.0 — Workspace Storage Primitive ✅

Pure backend foundation. Workspaces as a polymorphic platform primitive owned by users, projects, channels, or teams. Dual-layer storage: PVC filesystem (source of truth) + DB metadata index (queryable cache).

workspaces table: polymorphic owner (user/project/channel/team), root_path, max_bytes quota, status
workspace_files table: metadata index (path, MIME type, size, sha256, is_directory)
WorkspaceStore interface: CRUD, file index (upsert/delete/list/prefix), ownership lookup, stats
Postgres + SQLite store implementations with upsert-on-conflict for file index
workspace.FS package: read, write (atomic via temp+rename), delete, mkdir, stat, list, reconcile (FS→DB sync)
workspace.Archive: zip/tar.gz extract + create with archive bomb protection (10K file limit, 100MB single file, quota enforcement), common-prefix stripping
Content type detection: extension-based (40+ source code types) with http.DetectContentType fallback
SHA256 computed during write via tee reader (enables content-addressed skip in v0.21.2)
Path traversal guards: cleanPath + absPath validation, symlink rejection
15 API endpoints: workspace CRUD, file CRUD, archive upload/download, reconcile, stats
Owner-based authorization: user=self, channel=owner, project=member, team=member
Unit tests: path cleaning, traversal detection, MIME detection, unsafe path filtering, write/read round-trip, delete, mkdir

v0.21.1 — Workspace Tools + Channel/Project Binding ✅

Make workspaces useful in chat mode via tool calls.

Workspace tools (category: workspace): workspace_ls, workspace_read (50KB soft limit), workspace_write (auto-mkdir), workspace_rm (recursive guard), workspace_mv, workspace_patch (find/replace)
channels.workspace_id FK, projects.workspace_id FK
Workspace resolution: channel workspace → project workspace (override pattern)
Tool injection in completion handler when workspace bound
Frontend: deferred (channel settings workspace toggle, project Files tab, chat bar workspace indicator)

v0.21.2 — Workspace Indexing + Semantic Search ✅

Embed text files for semantic search. Reuses knowledge.SplitText + knowledge.Embedder.

workspace_chunks table (Postgres + SQLite migrations)
workspace_files additions: index_status, chunk_count columns
workspaces.indexing_enabled boolean (default true)
Store methods: InsertChunks, DeleteChunksByFile, SimilaritySearch, UpdateFileIndexStatus
Indexable types: text MIME types + 40+ code extensions + special filenames (Makefile, Dockerfile, etc.)
Code-aware chunking: 1500-char chunks with function/class/type/sub boundary separators
Content-addressed skip: sha256 comparison before re-chunking/re-embedding
workspace.Indexer: background goroutine with configurable concurrency semaphore
Single-file indexing via FS.WriteFile hook (SetIndexer)
Batch indexing via ExtractArchive (sequential within one semaphore slot)
workspace_search tool: semantic search with optional glob filtering, top-K capped at 20
GET /api/v1/workspaces/:id/index-status endpoint (per-status file counts, total chunks)
Configuration: WORKSPACE_INDEXING_ENABLED, WORKSPACE_INDEX_CONCURRENCY env vars
Graceful degradation when no embedding role configured
Mock store updated for FS unit tests

v0.21.3 — Surface Infrastructure + REPL ✅

Pure UI architecture. No workspace dependency (parallel development).

data-surface-region attributes on index.html containers (surface-header, surface-main, surface-footer, sidebar-content)
surfaces.js — SurfaceRegistry: register, activate, deactivate, getCurrent, list
ctx.ui.replace() / ctx.ui.restore() with DOM preservation (DocumentFragment-based)
ctx.surfaces.register() API for extensions
Mode selector component in sidebar (#modeSelectorWrap, auto-shown when ≥2 surfaces)
Chat as default surface (implicit, always registered)
surface.activated / surface.deactivated / surface.registered / surface.unregistered EventBus events
REPL tab: AsyncFunction wrapper, global injection (API, Events, Extensions, Surfaces, DebugLog, Panels, UI, , $, sleep)
REPL tab: pretty-print results (collapsible JSON, type-colored primitives, DOM element summaries)
REPL tab: command history (sessionStorage, ↑/↓ navigation)
REPL tab: tab-completion on object graphs, event labels, globals
REPL tab: event label hints (Events.on/emit completion)
REPL tab: admin gate (admin role OR ?debug=1 URL param)
REPL tab: toolbar (clear, copy, help)
CSS: mode selector + REPL styles
Documentation in EXTENSIONS.md §6 updated with implementation details
Mobile: mode selector collapses to hamburger/bottom nav — moved to v0.22+
Integration with extension loader (surfaces from manifest — moved to v0.22+)

v0.21.4 — Git Integration ✅

Layer git operations onto workspaces.

workspaces additions: git_remote_url, git_branch, git_credential_id, git_last_sync
git_credentials table: auth_type (https_pat/https_basic/ssh_key), encrypted_data (AES-256-GCM)
Postgres migration (012_v0214_git.sql) + SQLite migration (011_v0214_git.sql)
models.GitCredential, GitCredentialSummary, GitStatus, GitFileStatus, GitLogEntry
GitCredentialStore interface + Postgres/SQLite implementations (Create, GetByID, ListByUser, Delete)
workspace.GitOps with exec-based git operations (9 operations)
Credential injection: temp GIT_ASKPASS (PAT), .git-credentials (basic), GIT_SSH_COMMAND (SSH)
Security: reject file:// URLs, sanitize error output, GIT_TERMINAL_PROMPT=0
Clone, Pull, Push, Status, Diff, Commit, Log, BranchList, Checkout
SetGitLastSync on WorkspaceStore interface + both implementations
Post-operation reconcile + re-index hook (clone, pull, checkout)
5 git tools: git_status, git_diff, git_commit, git_log, git_branch
Git tools filtered out when no workspace bound (completion handler)
9 git API endpoints on /api/v1/workspaces/:id/git/*
3 credential CRUD endpoints on /api/v1/git-credentials
Wired in main.go: GitOps creation, tool registration, route registration
Workspace settings UI: git config section — moved to v0.22+
User Settings: git credentials management UI — moved to v0.22+
Integration tests: clone, commit, push/pull cycle (requires git binary in CI)
.gitignore respect in workspace indexing — moved to v0.22+

v0.21.5 — Editor Surface (Development Mode) ✅

IDE-like experience. Browser-tier surface consuming workspace primitives.

Layout: file tree (sidebar), code editor (CM6, main), AI chat panel (resizable split), status bar
File tree: workspace_ls backed, context menu (open, delete), nested directory expansion, file icons
Code editor: CM6 codeEditor() factory with textarea fallback, language auto-detection (20+ languages), tab bar, Ctrl+S save
AI chat panel: same channel context via Surfaces DOM borrowing, live update via workspace.file.changed event
Keyboard shortcuts: Ctrl+P quick open, Ctrl+S save, Ctrl+W close tab
Split pane layout with draggable resize handle
Status bar: file path, language mode, git branch
Workspace API methods on frontend (8 methods)
Surfaces.getSavedFragment/putSavedFragment for cross-surface DOM sharing
workspace.file.changed event emission from stream_loop.go after tool calls
Event route table: workspace.file. → DirToClient
editor-mode.css: dark theme, mobile responsive (stacked at ≤768px)
Auto-registration: surface registers when channel/project has workspace binding
Workspace management UI: create, list, bind from project settings + chat context menu
GET /workspaces list endpoint, workspace_id in channel API (update, get, list)
Git status indicators in file tree (M/A/U badges + colors) — closed in v0.21.6
Drag-drop file reorder — moved to v0.22+
Ctrl+Shift+F workspace search (maps to quick open) — closed in v0.21.6
Auto-save on tab/mode switch — closed in v0.21.6

v0.21.6 — Article Surface + Document Output Pipeline ✅

Writing-focused surface. Document is artifact, conversation is secondary.

Layout: outline (sidebar top), AI assistant (sidebar bottom), rich text editor (CM6 markdown, main)
Outline: auto-generated from headings, click-to-scroll (navigates CM6 cursor)
Rich text editor: CM6 codeEditor() markdown mode, line wrapping, centered content (720px max), textarea fallback
AI assistant: chat panel embedded in sidebar via Surfaces DOM borrowing
Export dropdown: Download Markdown, Download HTML (via marked.js + DOMPurify), Copy to clipboard
Document picker: lists .md/.mdx/.txt files from workspace, create new document inline
Focus mode: dims non-active lines in editor (CM6 opacity-based, toggle button)
Word count + reading time in status bar (~230 wpm)
Auto-save: debounced (2s) on content change, save on tab switch / surface deactivate
Live update on workspace.file.changed event (reloads if file unmodified)
Surface registration: registers as "Article" with file-text icon when workspace bound
article-mode.css: outline styling, export menu, focus mode, mobile responsive
(from v0.21.5 deferred) Git status indicators in editor file tree (M/A/U badges + colors)
(from v0.21.5 deferred) Auto-save on tab/mode switch in editor surface
(from v0.21.5 deferred) Ctrl+Shift+F workspace search (maps to quick open)
Article-specific AI tools (suggest_outline, expand_section, check_citations) — moved to v0.22+
Drag-to-reorder outline sections — moved to v0.22+
PDF export via pandoc — moved to v0.22+

Bugfixes & DX (added post-initial)

Hash Router (router.js): URL-driven direct-to-surface navigation (#/chat, #/editor, #/article). Bookmarkable, back/forward works. Precursor to Go html/template server-rendered pages (v0.25.0) for public/workflow entry points.
openDirect(wsId) on EditorMode + ArticleMode: bypass check(), register directly with workspace ID
Workspace picker overlay: shown when navigating to surface without workspace, auto-selects if only one
SEED_PROVIDERS env var: auto-creates global providers on startup (dev/test only, idempotent)
Mode selector labels: icon + text, labels hide when sidebar collapsed
chat.switched / chat.created events: wired into selectChat(), newChat(), sendMessage()
workspace_id in channel API responses: added to list/get/create for both SQLite and Postgres
Frontend chat + project objects: now carry workspace_id for Router and surface check() optimization

v0.21.7 — Bugfix: scanJSON Driver Buffer Aliasing ✅

Critical fix for intermittent 500 errors on paginated list endpoints.

scanJSON []byte path: copy driver buffer instead of aliasing (json.RawMessage(v) → make+copy)
CreateChannel Postgres RETURNING path: use scanJSON(&ch.Settings) instead of bare &ch.Settings
UpdateChannel settings write: validate json.Valid() before JSONB merge, reject with 400
New tests: TestScanJSON_ByteSliceNotAliased, TestScanJSON_ByteSliceIsolation_MultiRow

Root cause: json.RawMessage(v) is a type conversion, not a copy — it aliases the []byte buffer owned by database/sql. Per the Scanner interface docs, []byte values are only valid until the next rows.Scan() call. In paginated list endpoints, row N's Settings slice header pointed into memory that row N+1's scan overwrote, producing corrupt JSON that passed json.Valid() at scan time but failed at marshal time when SafeJSON serialized the full response.

v0.22.0 — Provider Health + Capability Overrides ✅

Smallest shippable unit that unblocks routing. Track provider error rates and latency, add admin override layer for model capabilities.

Depends on: usage tracking (v0.10.0), capabilities resolver (v0.9.1).

Provider Health Tracking

provider_health table: provider_config_id FK, window_start (hourly buckets), request_count, error_count, timeout_count, total_latency_ms, max_latency_ms, last_error, last_error_at
In-memory health accumulator: goroutine-safe counters per provider, flushed to DB on interval (60s)
RecordSuccess/RecordError/RecordTimeout called from completion handler after every provider call (sync + streaming)
Provider status derivation: healthy / degraded / down based on error rate thresholds (5% = degraded, 25% = down)
GET /api/v1/admin/providers/:id/health endpoint: current status + hourly windows (configurable hours param)
GET /api/v1/admin/providers/health endpoint: summary status for all providers
(shipped v0.22.3) Health status included in GET /api/v1/models/enabled response (new provider_status field)
(deferred → v0.22.2) Auto-disable: optional policy to mark provider inactive when down for N consecutive windows
Background cleanup: prune health rows older than 7 days (6-hour cycle)

Capability Admin Overrides

capability_overrides table: provider_config_id (nullable for global), model_id, field, value, set_by, created_at
Three-tier resolution in ResolveIntrinsic(): catalog → heuristic → admin override (highest priority)
PUT /api/v1/admin/models/:id/capabilities endpoint: set individual capability overrides
DELETE /api/v1/admin/models/:id/capabilities/:overrideId endpoint: remove override
GET /api/v1/admin/models/:id/capabilities endpoint: show resolved caps with source annotation (catalog/heuristic/override)
GET /api/v1/admin/capability-overrides endpoint: list all overrides
Postgres + SQLite migrations (013_v0220_health.sql / sqlite 012_v0220_health.sql)

Search Provider Health (deferred → v0.22.1)

RecordOutcome for web_search and url_fetch tool calls (search provider tracking)
Rate limit tracking per provider config (requests/minute counter in health accumulator)

Workspace Pane Refactor (frontend)

.workspace flex container replaces .chat-area + .side-panel layout
.workspace-primary / .workspace-secondary independent pane model
.workspace-handle drag-resize between panes (replaces old side-panel-resize)
Surface layout declarations: primary, secondary, secondaryOpts per surface
Dual-view mode removed (was _dualMode, _splitRatio, _secondary in PanelRegistry)
Zoom selector updated for new class names

Bugfix (v0.21.7)

scanJSON driver buffer aliasing — copy []byte from database driver instead of aliasing slice header
CreateChannel RETURNING path uses scanJSON(&ch.Settings) instead of bare scan
UpdateChannel validates json.Valid() on settings before JSONB merge

v0.22.1 — Provider Extensions (Declarative Config) ✅

Replace hardcoded provider-specific behavior with data-driven configuration. Same model, different provider → different parameters.

Depends on: provider health (v0.22.0).

Provider Profiles

Profile schema per provider type: defines available settings, types, defaults, validation, dependency rules (providers/profile.go)
Built-in profile schemas for: openai, anthropic, venice, openrouter (unknown types fall back to openai-compatible)
System prompt injection: system_prompt_prefix setting prepended to first system message (all providers)
Thinking mode toggle: Anthropic extended_thinking + thinking_budget → injects thinking.type=enabled; Venice enable_thinking → disables Venice system prompt
(not needed) provider_profiles JSONB column — existing provider_configs.settings JSONB already serves this purpose

Request/Response Transforms

Hooks.PreRequest(cfg, req) — decorate request before dispatch (system prompt prefix, ExtraBody injection)
Hooks.PostStreamEvent(cfg, event) — normalize provider-specific response fields (Venice thinking extraction)
Hook implementations: Venice web search + thinking, Anthropic extended thinking + beta header, OpenRouter routing preferences + require_parameters, OpenAI frequency/presence penalty
Preset-level overrides: MergePresetSettings() merges persona overrides onto provider settings, respecting ProviderOnly fields
ProviderConfig.Settings fully utilized: hooks read from config, not hardcoded switch statements
CompletionRequest.ExtraBody field + mergeExtraBody() for provider-specific wire fields
Anthropic extended thinking stream support: thinking_delta content blocks → Reasoning field

Provider Type Registry

providers.Init() uses RegisterType() with full metadata (name, description, default endpoint, profile schema)
ProviderTypeMeta struct: ID, name, description, default_endpoint, profile_schema
GET /api/v1/admin/provider-types endpoint: list available provider types with their profile schemas
(deferred → v0.23) New provider types registrable via config file (openai-compatible endpoint + custom profile schema)

Search Provider Health (carried from v0.22.0)

(deferred → v0.22.2) RecordOutcome for web_search and url_fetch tool calls
(deferred → v0.22.2) Rate limit tracking per provider config

v0.22.2 — Routing Policies + Fallback Chains ✅

Rules-based routing engine — policy, not ML. Evaluated after resolveConfig() between "what model was requested" and "which provider serves it."

Depends on: provider health (v0.22.0), provider extensions (v0.22.1).

Routing Policies

routing_policies table: id, name, scope (global/team), team_id, priority (lower wins), policy_type, config (JSONB), is_active
Policy types: provider_prefer (ordered fallback list), team_route (restrict team to providers), cost_limit (heuristic cost cap), model_alias (alias → provider+model rewrite)
Policy evaluator: takes requested model + user context → returns ranked list of (providerConfigID, modelID) candidates
Integration point: evaluateRouting() called after resolveConfig, before provider dispatch — reloads winning config credentials on switch
(deferred → v0.23) capability_match policy type ("cheapest model with tool_calling")

Fallback Chains

Fallback runner: RunWithFallback() tries candidates in order with configurable max retries
Health-aware: skip providers with status down, prefer healthy over degraded
All-down graceful degradation: keeps candidates rather than failing
(deferred → v0.23) Latency-aware preference: track response time percentiles, prefer faster providers
(deferred → v0.23) Cost-aware preference with budget ceiling per request

Routing Metadata

X-Switchboard-Provider response header: providerID/configID on every completion
X-Switchboard-Route header: policy name when routing is active
routing_decision JSONB column on usage_log
POST /api/v1/admin/routing/test endpoint: dry-run policy evaluation with live health status
Admin CRUD: GET/POST/PUT/DELETE /api/v1/admin/routing/policies

v0.22.3 — Provider Admin UI + Deferred Polish ✅

Admin interfaces for v0.22.0–v0.22.2 features, plus deferred items from v0.21.x.

Depends on: routing policies (v0.22.2).

Admin UI

Provider health dashboard: status badges, error rate/latency/timeout metrics per provider, refresh button (loadAdminHealth)
Capability override editor: table listing all overrides with model, config, field, value; delete button per row (loadAdminCapabilities)
Routing policy builder: CRUD with name/priority/type/scope/team/config(JSON)/active toggle, dry-run test panel with candidate ranking and health status (loadAdminRouting, _showRoutingForm, _runRoutingTest)
New "Routing" admin category with Health, Routing, and Capabilities sections
Health status included in GET /api/v1/models/enabled response (provider_status field on UserModel)
(deferred → v0.23) Provider profile editor: key-value config per provider type, preview of effective settings
(deferred → v0.23) Fallback chain visualizer: drag-to-reorder provider priority per model family

Deferred from v0.22.0–v0.22.2

(deferred → v0.23) capability_match policy type ("cheapest model with tool_calling")
(deferred → v0.23) Latency-aware preference: track response time percentiles, prefer faster providers
(deferred → v0.23) Cost-aware preference with budget ceiling per request
(deferred → v0.23) New provider types registrable via config file (openai-compatible endpoint + custom profile schema)

Deferred from v0.21.x

(deferred → v0.23) Mobile: mode selector collapses to hamburger/bottom nav
(deferred → v0.23) Integration with extension loader (surfaces from manifest.json)
(deferred → v0.23) Workspace settings UI: git config section in channel/project settings
(deferred → v0.23) User Settings: git credentials management UI
(deferred → v0.23) .gitignore respect in workspace indexing
(deferred → v0.23) Drag-drop file reorder in editor file tree
(deferred → v0.23) Article tools: suggest_outline, expand_section, check_citations (AI-powered)
(deferred → v0.23) Drag-to-reorder outline sections in article mode
(shipped v0.22.4) PDF/DOCX export via pandoc in article mode
(shipped v0.22.4) Project-specific file uploads (full project-level upload architecture)

v0.22.4 — Provider Health UX + Project Files + Export ✅

Closes remaining provider infrastructure gaps and delivers UX features deferred from earlier releases.

Provider Infrastructure:

Rate limit tracking per provider config (HTTP 429 classified separately)
Tool health tracking (web_search, url_fetch → tool_health table)
Auto-disable policy (N consecutive "down" windows → deactivate provider)
Search provider health tracking via tool health pipeline
SQLite health store parity (rate_limit_count, tool health, auto-disable)
Config: PROVIDER_AUTO_DISABLE_THRESHOLD env var (default: 3)

UX:

Workspace settings UI: git config section in project panel (remote URL, branch, credential)
Project-specific file uploads (POST/GET endpoints, project panel UI)
PDF/DOCX export via pandoc (POST /api/v1/export, editor menu integration)
Admin health dashboard: rate limit count display with warning color

Frontend:

5 new API client methods (projectUploadFile, projectListFiles, exportDocument, updateWorkspace, listGitCredentials)
Health cards show rate limit counts
Git settings section appears when workspace is bound

v0.22.5 — Surfaces + Go Templates + Admin Bug Fixes ✅

Replaces monolithic client-side rendering with server-rendered Go templates organized as composable surfaces. Each page route renders a dedicated surface that owns its full layout below the classification banner. Reusable template components (model-select, team-select, file-upload) eliminate duplicated form-building logic and fix data population bugs by construction.

Template Engine:

html/template with //go:embed for compiled-in templates
Custom FuncMap (roleFilterType, toJSON, hasPrefix, dict)
CSP nonce generation per request
Data loaders per surface (pre-fetch exactly what templates need)
Base template with banner system (top + bottom, CSS custom properties)

Surfaces:

Chat surface (/, /chat/:chatID) — bridge to existing JS
Editor surface (/editor/:wsId) — server-rendered layout shell, fixes bugs #4 + #5
Notes surface (/notes/:noteId) — standalone with assist pane
Settings surface (/settings/:section) — full-page replaces modal
Admin surface (/admin/:section) — 5 categories, 10+ sections
Login page (/login) — standalone, cookie-based auth

Reusable Components:

model-select — type-filtered model dropdown (fixes bug #1)
team-select — pre-populated team picker (fixes bug #2)
file-upload — drop zone + file picker

Auth:

AuthOrRedirect middleware — cookie JWT, redirect to /login
RequireAdminPage() — role gate for admin pages
sb_token cookie sync on every token save/refresh

Editor File Upload (bug #3):

Upload button in toolbar + drag-and-drop on file tree
uploadWorkspaceFile() API method (binary-safe, respects quota)
Auto-open single uploaded text files

Cleanup:

Removed /legacy SPA fallback route
nginx.conf: page route proxy blocks before SPA fallback

v0.22.6 — Split Deployment Fix + CI Timeout + Code Pruning ✅

Hotfix for FE/BE split k8s deployment broken by v0.22.5 surfaces architecture, plus aggressive pruning of OBE client-side code now replaced by server-rendered surfaces.

BACKEND_URL env var on FE container for page route proxying
Entrypoint generates proxy_pass blocks for all surface routes
Works with both BASE_PATH="" and BASE_PATH="/prefix"
CI: -timeout 8m on all go test invocations
Removed router.js (322 lines) — hash routing replaced by server routes
Removed surfaces.js (368 lines) — client registry replaced by Go templates
Replaced index.html SPA shell (1,296 → 16 lines) with redirect stub
Stripped old Surfaces paths from editor-mode.js (~260 lines)
Simplified docker-entrypoint-fe.sh — requires BACKEND_URL, removed SPA-only path
Consolidated nginx.conf proxy blocks for unified container
Net: ~2,430 lines removed

v0.22.7 — Surface Prototypes (Theme + ChatPane + Splash) ✅

Foundation CSS/JS for the v0.22.5 surface architecture: theme system, reusable chat pane component, splash/login redesign, and UI primitive extensions. All files target the correct tree locations established in v0.22.5. Settings surface gains BYOK and User Personas feature gates.

Depends on: surfaces + Go templates (v0.22.5), code pruning (v0.22.6).

Theme System:

theme.css: CSS custom properties for light/dark themes via [data-theme] attribute
System preference auto-detection (prefers-color-scheme media query)
Variable bridge: new vars (--bg, --text) alias old vars (--bg-primary, --text-primary)
Shared component styles: toast stack, badges, buttons, icon buttons, form fields, confirm dialog, theme toggle, avatar upload, section headers
Surface layout styles: splash, chat-pane, admin, settings, editor
Google Fonts: DM Sans (UI) + JetBrains Mono (code)
base.html: data-theme on <html>, theme.css before styles.css

ChatPane Component:

chat-pane.js: factory pattern — ChatPane.create(opts) returns self-contained instance
Instance API: renderMessages, appendChunk, finalizeStream, appendTyping, removeTyping, scrollToBottom, showWelcome, clear, getInputValue, setInputValue, focusInput, destroy
Lookup: ChatPane.get(id), ChatPane.forChannel(channelId), ChatPane.active()
components/chat-pane.html: Go template partial for server-rendered mount points
Editor surface: chat-pane template in assist pane with ChatPane.create() boot

Splash / Login:

login.html rewritten: split hero + auth card layout
Animated grid canvas (40px grid, scrolling offset, --border color)
Auth tabs (Login / Register) with server-gated registration
Register form: username, display name, email, password, avatar upload
pages-splash.js: Pages.initSplash(), grid animation, POST login, POST register + PUT avatar
PageData gains InstanceName, LogoURL, Tagline, RegistrationOpen
loadBranding() + isRegistrationOpen() from GlobalConfig

UI Primitives Additions:

Toast: show/success/error/warning/info with auto-dismiss, stacking
renderBadge(): 6 color variants (accent, success, danger, warning, purple, muted)
renderIcon(): 20+ SVG icon set
renderIconBtn(): icon button factory with active state
Theme: init/set/get/resolved/renderToggle with localStorage
showConfirmDialog(): enhanced with variant, onConfirm/onCancel
mountAvatarUpload(): file input with preview, onUpload callback

Settings Surface Gates:

BYOK gate: My Providers, Model Roles, Usage tabs shown when user_providers.enabled
User Personas gate: My Personas tab shown when user_presets.enabled
Models tab added to base navigation
SettingsPageData gains BYOKEnabled, UserPersonasEnabled from GlobalConfig
BYOK status indicator in nav footer

Go Changes:

PageData: Theme, SurfaceSettings, InstanceName, LogoURL, Tagline, RegistrationOpen
Render() defaults Theme to "dark"
RenderLogin() populates splash fields from GlobalConfig
settingsLoader() reads feature gates

✅ v0.22.8 — Surface Integration (Wire into Existing JS)

Connect v0.22.7 prototypes to the existing frontend JS modules. ChatPane.primary replaces singleton UI.* calls. Theme system wired into appearance settings. Admin surface hybrid loader completed. Naming cleanup: preset → persona, APIConfigID → ProviderConfigID.

Depends on: surface prototypes (v0.22.7).

ChatPane Bridge:

ChatPane.primary creation in startApp() from server-rendered mount points
ui-core.js delegation: UI.renderMessages → ChatPane.primary.renderMessages, etc.
Branding init from window.__SETTINGS__ (instanceName, logoURL)

Theme Integration:

Wire Theme into appearance settings save/load cycle
CM6 theme sync on theme change
Persist theme preference to user settings API

Admin Surface:

Complete hybrid section loaders for all JS-loaded sections

Settings Surface:

Models visibility toggles (API.saveModelPreferences)
User Personas CRUD (add/edit/delete with confirm dialogs)
BYOK provider CRUD in settings context
Teams tab content

Naming Cleanup:

preset → persona: routes, JSON keys, Go structs, JS, CSS, DOM IDs, templates
APIConfigID → ProviderConfigID: all Go structs and JSON fields
Shared app-state.js extracted from app.js — available on all surfaces
Auth tokens loaded for all surfaces via base.html

✅ v0.23.0 — @mention Routing + Persona Handles + Proxy

@mention routing works in any chat against the full model catalog and persona registry. No roster, groups, or participant setup required — just type @handle or @model-id and send.

@mention Resolution

resolveMention(): direct DB lookup — persona handle (exact/prefix) → model catalog (exact/prefix)
Autocomplete popup on @ in any chat — all enabled models + personas
Handle field on personas: auto-generated from name, unique, editable
@mention pill rendering in message content (accent-colored, code-aware)
Context boundaries: persona→plain and persona→persona style isolation
Participant list injection: system prompt tells LLM who it can @mention

AI-to-AI Chaining

chainIfMentioned(): uses resolveMention() on assistant response content
Self-mention blocked, depth capped at 5
WebSocket delivery (message.created + typing indicators)
Same resolution path for user→LLM and LLM→LLM routing

Provider Proxy

proxy_mode (system/direct/custom) + proxy_url on provider_configs
All four providers use cfg.Client() with mode-aware HTTP transport
Bad custom URL falls back to system (not direct) — safe for mandatory-proxy environments

Channel Infrastructure

channel_participants table with polymorphic types and roles
channel_models partial indexes: persona entries keyed per-persona, raw models per-provider
Per-provider model preferences (composite keys in user_model_settings)
persona_groups + persona_group_members tables (schema ready, CRUD not yet wired)

Conversation type taxonomy (direct/dm/group/channel/workflow), three-section sidebar (Projects → Channels → Chats), folder system for chats, DM plumbing, channel configuration with ai_mode, presence heartbeat, and the unified active conversation model.

Depends on: @mention routing (v0.23.0), WebSocket infrastructure (exists). See DESIGN-0_23_1.md for the full spec.

Conversation Types:

Five-type taxonomy: direct (1:1 AI), dm (human-to-human), group (multi-participant), channel (named persistent), workflow (staged, deferred)
Channel type constraint extended: dm, channel added to type CHECK
ai_mode column on channels: auto | mention_only | off
ai_mode guard in completion handler — off returns 403, mention_only without @mention delivers without AI
topic column on channels for header display

Sidebar Architecture:

Three collapsible sections: Projects → Channels → Chats
renderChannelsSection() with # / person icons, unread badges, online dots
Channel items: context menu (rename, set topic, delete), ⋯ hover button
Section collapse/expand state in localStorage

Folder System:

chat_folders table, CRUD handler (handlers/folders.go)
Drag chats into/out of folders; folder context menu (rename, delete)
Folder delete modal: "Keep chats" / "Delete chats too" / Cancel
Unfiled drop zone when folders exist

DM Plumbing:

resolveMention() extended to resolve users (exact + prefix on username)
User @mention skips AI, delivers user.mentioned WebSocket notification
DM creation flow with user search modal
DM dedup guard — one channel per participant pair

Presence:

user_presence table with heartbeat upsert
POST /presence/heartbeat (30s interval), GET /presence?users=... (90s threshold)
Presence WebSocket events: presence.changed

Channel Participants:

channel_participants CRUD handler, auto-created on channel creation
Persona group CRUD endpoints wired (persona_groups, persona_group_members)
DM participant auto-creation from req.Participants

Migration:

016_v023_multiuser: ai_mode, topic, user_presence, channel type extension

✅ v0.23.2 — Multi-User Polish + Channel Lifecycle

Bug fixes, unified active conversation refactor, channel lifecycle (archive/delete), group chat leader routing, @all fan-out, message attribution, and deferred surface integration from v0.22.8.

Depends on: v0.23.1 sidebar and conversation taxonomy.

Unified Active Conversation:

App.activeConversation = { id, type } replaces currentChatId + currentChannelId
setActive(id, type), activeId getter, getActiveChat() helper
Send path, model bar, streaming, session restore all keyed off activeConversation.id
Sidebar highlight works across both chat and channel sections

Group Chat + Persona Groups:

Group leader default response: no @mention in group → leader persona responds
@all fan-out: routes to every persona participant, depth-1 only
Participant mutation guards: DMs keep ≥2 humans, groups keep ≥1 persona
"New Group Chat" flow with ad-hoc persona picker

Message Attribution:

Human sender display: other participants show avatar + display name (not "You")
Persona sender display verified for loaded history in channel context

Channel Lifecycle:

Archive action via context menu (is_archived, archived_at)
Delete gated by channel_retention.mode (flexible/retain)
Admin purge with purge_after_days floor
Retention config keys in global_config

Bug Fixes:

Channel persistence through refresh (resp.channels → resp.data)
Folder drag-and-drop (folderId mapping, drop handlers, unfiled zone)
DM creation 404 → added GET /users/search endpoint
Channel ⋯ menu consistency (replaced ✕ with hover ⋯ pattern)
Folder ⋯ button reflow (visibility:hidden instead of display:none)
Unread subquery using last_read_at (not migration-017-dependent column)
Settings Models section template wiring
u.avatar → u.avatar_url in ListMessages JOIN and treepath

Surface Integration (deferred v0.22.8):

ChatPane.primary bridge from server-rendered mount points
Theme save/load cycle wired to settings appearance
Admin hybrid section loaders completed
Settings surface: models toggles, persona CRUD, BYOK, teams

@mention UX:

Autocomplete includes users alongside personas and models
User mention pill styling (distinct color from persona pills)
user.mentioned WebSocket notification with toast

Migration:

017_unread: last_read_message_id on channel_participants

v0.24.0 — Auth Abstraction + User Identity ✅

Auth provider interface decoupling builtin auth from the handler/middleware layer. User model extended with auth_source, external_id, handle. @mention resolution upgraded to use handles. Zero behavior change for existing users — builtin mode goes through the new abstraction identically.

See DESIGN-0.24.0.md for the full spec including v0.24.1–v0.24.3 subversions.

Depends on: v0.23.0 (channel_participants), v0.16.0 (groups), v0.9.4 (vault).

Auth Provider Interface (server/auth/):

Provider interface: Mode(), Authenticate(), SupportsRegistration(), Register()
BuiltinProvider: extracts login/register from handlers/auth.go
UniqueHandle(): collision-safe handle generation with -2, -3 suffixes
ErrorToHTTPStatus(): maps auth errors to HTTP codes
ParseMode(): validates AUTH_MODE string with error return

Auth Handler Refactor:

AuthHandler gains provider auth.Provider field
Login() delegates to provider.Authenticate(), then vault unlock + JWT
Register() delegates to provider.Register(), then vault init + JWT
generateTokens() response includes handle, auth_source
BootstrapAdmin() / SeedUsers() backfill handles for existing users

User Model Extension:

AuthSource (builtin/mtls/oidc), ExternalID (nullable), Handle (unique)
All user store queries (PG + SQLite) include three new columns
GetByHandle(), GetByExternalID() on both store implementations
Unified scanOneUser / scanOne helpers replace per-method scan blocks

Config + Middleware:

AUTH_MODE env var (default builtin)
main.go dispatch: builtin wired, mTLS/OIDC fail-fast at startup
Middleware unchanged — JWT validation is auth-mode-agnostic

@mention Resolution:

resolveMention() uses LOWER(handle) instead of LOWER(username)
SearchUsers returns handle, filters on handle
Frontend autocomplete matches on handle, uses handle as @mention token

Migration:

018_auth_abstraction: auth_source, external_id, handle columns + unique indexes + backfill

v0.24.1 — mTLS + OIDC Providers ✅

Two external auth implementations plugging into v0.24.0's provider interface. Keycloak integration test environment via docker-compose overlay.

Depends on: auth abstraction (v0.24.0). See DESIGN-0.24.0.md §v0.24.1 for full spec.

mTLS provider: trusted header extraction, cert DN parsing, auto-provision
OIDC provider: well-known discovery, JWKS caching, token validation, claim extraction
OIDC authorization code flow: login redirect, code exchange, token handoff via fragment
Split-horizon issuer support (OIDC_EXTERNAL_ISSUER_URL for Docker/K8s)
OIDC claim → group mapping (external groups sync to internal groups with source=oidc)
Login page adapts by AUTH_MODE (form / cert status / SSO button)
Keycloak docker-compose overlay with pre-configured realm (ci/keycloak-realm.json)
QArgs() dialect adapter: handles Postgres $N reuse for SQLite arg expansion
database.QueryRow/Query/Exec wrappers with automatic arg expansion
Migration 019: oidc_auth_state table, groups.source column
Unit tests: mTLS (ParseDN, config), OIDC (discovery, auth URL, mode), QArgs (5 tests)
Regression test: TestIntegration_ChannelListWithTypeFilter
SQLite local dev fixes: _time_format DSN, store wiring, nginx resolver, extension assets

v0.24.2 — Fine-Grained Permissions

Groups become capability carriers. Permission model on top of existing group infrastructure.

Depends on: auth abstraction (v0.24.0). Parallel to v0.24.1. See DESIGN-0.24.0.md §v0.24.2 for full spec.

Permission constants (domain.action convention, code-level enum)
permissions JSONB column on groups
ResolvePermissions(): union of group permissions + DefaultUserPerms
RequirePermission() middleware
Token budgets: per-group daily/monthly ceilings, enforced in completion handler
Model access control: per-group model allowlists
Admin UI: permission checklist, budget fields, model picker on group edit
DefaultUserPerms override via global_config key default_permissions
Migration 020: permissions, budgets, allowed_models on groups

v0.24.3 — Anonymous / Session Participants

Unauthenticated visitors for workflow intake channels. Direct prerequisite for v0.25.0 (Workflow Engine).

Depends on: mTLS provider (v0.24.1) for cert-based anonymous identity. See DESIGN-0.24.0.md §v0.24.3 for full spec.

session_participants table (channel-scoped, ephemeral token)
Session JWT: SessionClaims{SessionID, ChannelID} — distinct from user JWT
SessionOrAuth() middleware: accepts either JWT type
Capability scoping: session participants limited to their bound channel
mTLS anonymous path: cert fingerprint as stable session identity
channels.allow_anonymous flag
Session display in participant list (team members see visitor identity)
Migration 021: session_participants table, allow_anonymous column

v0.25.0 — 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 for the conceptual model.

Depends on: multi-participant channels (v0.23.0), anonymous identity (v0.24.3).

(Shifted from v0.22.0 — no content changes, dependency refs updated)

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

Go Template Pages (server-rendered entry points)

Server-rendered HTML via Go html/template for pages that need SEO, OG tags, pre-auth rendering, or standalone access outside the SPA shell. Same binary, same auth middleware, same deployment — no second language runtime.

Template engine: Go html/template with shared base layout, partials for nav/footer
Route layer: /w/:slug for public workflow pages, /p/:id for shared project views
Workflow landing page: branded intake form, persona avatar, description — rendered server-side
Shared/embedded surface pages: /s/editor/:wsId, /s/article/:wsId/:path — server renders minimal shell, JS hydrates surface directly (replaces hash routing for public links)
Template data: workflow metadata, branding, environment banner — injected server-side
Auth gating: public pages skip auth, team pages require session, admin pages require role
Precursor: hash router (v0.21.6) handles in-app navigation; Go templates handle external/public entry points

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)

v0.26.0 — Tasks / Autonomous Agents

Unattended execution — workflows without a human in the loop. Depends on: workflow engine (v0.25.0).

(Shifted from v0.23.0 — no content changes, dependency refs updated)

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 — Additional Extensions

Image generation tool (browser or sidecar, provider-agnostic)
STT/TTS (browser extension, Web Speech API — personal use case)
Code execution sandbox (server-side, container isolation)

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

"Group" scope badge on model selector / KB list: show access-source annotation so users see why they have access (global, team, group grant). Requires backend to include access_source in list responses.
Per-provider model preferences: user_model_settings unique key is (user_id, model_id) — same model from different providers shares one visibility toggle. Needs provider_config_id dimension in DB constraint, store, API, and frontend hiddenModels keying. Frontend composite key (configId:modelId) already exists in App.models[].id.

Projects — Future

Project-specific files: full project-level upload (own endpoint, storage path, UI surface — not just channel attachment re-linking)
Project templates: create new projects from predefined configurations (persona, KBs, system prompt)
Project creation dialog: replace prompt() with proper modal (name, description, persona, KB picker)
Admin-level project management: cross-instance visibility, reassign ownership, enforce team policies (scope: enterprise only, BYOK personal projects stay private)
Sub-projects / nested hierarchy: child inherits parent KBs, system prompt, persona (deferred until usage patterns clarify need vs tags/labels)

Knowledge Bases — Future

KB auto-injection: top-K chunk prepend to system prompt, context budget aware, per-channel toggle (latency budgeting required)
Hybrid search: combine vector similarity with full-text tsvector, re-rank
Semantic chunking: embedding-based boundary detection for smarter splits
HNSW index: better query performance than IVFFlat for large datasets
Web scraping source: ingest URLs as KB documents (extends url_fetch)
Scheduled re-indexing: periodic rebuild when source documents update
~~Store cleanup: add UpdateDocumentStorageKey() to KnowledgeBaseStore interface~~ (done in v0.17.0) (currently uses direct database.DB.ExecContext in handler — works but bypasses store layer)

Memory — Future

Memory compaction: summarize old memories to save context tokens
Memory confidence decay: reduce confidence over time, prune low-confidence entries
Memory export/import: portable memory format across instances
Cross-persona memory sharing (opt-in): e.g. "coding assistant" can read facts from "project manager"
Memory analytics: dashboard showing what Personas are learning, memory growth trends

Platform

Rate limiting per user/team/tier (token budgets)
~~Provider health monitoring~~ → v0.22.0 + key rotation
Multi-tenant SaaS mode
Plugin/extension marketplace
Virtual scroll for long conversations
~~SQLite backend option (single-user / dev)~~ → v0.17.1
Helm chart. The k8s/ raw manifests with ${VAR} substitution have served well but are friction for external adopters and make values management manual. A Helm chart wraps the same backend + frontend deployments with a values.yaml (replicas, image tags, ingress host, storage class, secret refs, resource limits, feature flags). Target: helm install switchboard ./chart for a fresh cluster, helm upgrade for rolling deploys. Subcharts for optional Postgres (for dev/test — prod uses external). Candidate for v0.27+ or a parallel track once the core feature set stabilizes.

Pane Architecture (Workspace Container)

The main area to the right of the sidebar is a workspace container that holds 1+ panes. Each pane is a self-contained unit (chat, editor, notes, preview, etc.) with its own lifecycle. Panes compose side-by-side rather than replacing each other (current surface model).

Default layout: Left nav + single Chat pane (what exists today, zero cognitive overhead)
Power user: Left nav + Editor pane + Chat pane side by side. Or Editor + Notes. Or all three.
Workflow mode: Left nav hidden. Team member gets Chat + History. Customer gets just Chat.
User-resizable splits between panes, layout persists per-project or per-user preference
The current surface system was a stepping stone — proved out the region/activate/deactivate lifecycle. Panes reuse that contract but drop the "only one active at a time" constraint.
Sidebar tabs (Chats / Files) already decouple navigation from center content (v0.21.6)

Surfaces as Extensions

Surfaces (future: panes) become first-class extension types alongside block renderers and tool bridges
Surfaces.register() already defines the contract: name, regions, activate/deactivate callbacks — swap hardcoded JS modules for manifest + dynamically loaded bundles
Admin-installable surfaces: upload or enable from extension registry, scoped to team or global
Surface manifest in manifest.json: declares required regions, capabilities, dependencies
Surface IDE: built-in surface for building surfaces — Go template editor for server-rendered shells, JS/CSS editor for client behavior, live preview in sandboxed region. Eats its own dog food.
Surface marketplace: share custom surfaces across instances (presentation mode, kanban, form builder, dashboard, etc.)
Project-bound surface/pane defaults: project config specifies which panes are available and default layout

87 KiB Raw Blame History Unescape Escape

Roadmap — Chat Switchboard

Dependency Graph

Completed Releases

✅ v0.9.0 — Schema Consolidation + BYOK

✅ v0.9.1 — Capability Architecture + Docs

✅ v0.9.2 — Quick UX Wins + Hardening

✅ v0.9.3 — Content Visibility & Block Controls

✅ v0.9.4 — API Key Encryption + Vault

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

✅ v0.10.1 — Polish + UX

✅ v0.10.2 — Summarize & Continue + Role Cleanup

✅ v0.10.3 — Frontend Refactor

✅ v0.10.4 — Model Type Pipeline + Role Fixes

✅ v0.10.5 — UI Primitives + Extension Surfaces

✅ v0.11.0 — Extension Foundation (Browser Tier)

✅ v0.12.0 — File Handling + Vision

✅ v0.13.0 — Admin Panel Refactor

✅ v0.13.1 — Web Search + URL Fetch

✅ v0.14.0 — Knowledge Bases

✅ v0.15.0 — Compaction

✅ v0.15.1 — Context Recall Tools

✅ v0.16.0 — User Groups + Resource Grants

v0.17.0 — Persona-KB Binding + Enterprise KB Mode + QOL ✅

v0.17.1 — SQLite Backend ✅

v0.17.2 — CodeMirror 6 Integration ✅

v0.17.3 — Notes Graph + Wikilinks ✅

v0.18.0 — Memory (User + Persona Scopes) ✅

v0.18.1 — Side Panel Architecture ✅

✅ v0.19.0 — Projects / Workspaces

✅ v0.19.1 — Active Project + Project System Prompt + Detail Panel

✅ v0.19.2 — Project Persona Default + Archive + Channel Reorder

v0.20.0 — Notifications + @mention Routing + Multi-model ✅

v0.21.x — Workspace Platform + Extension Surfaces

v0.21.0 — Workspace Storage Primitive ✅

v0.21.1 — Workspace Tools + Channel/Project Binding ✅

v0.21.2 — Workspace Indexing + Semantic Search ✅

v0.21.3 — Surface Infrastructure + REPL ✅

v0.21.4 — Git Integration ✅

v0.21.5 — Editor Surface (Development Mode) ✅

v0.21.6 — Article Surface + Document Output Pipeline ✅

Bugfixes & DX (added post-initial)

v0.21.7 — Bugfix: scanJSON Driver Buffer Aliasing ✅

v0.22.0 — Provider Health + Capability Overrides ✅

v0.22.1 — Provider Extensions (Declarative Config) ✅

v0.22.2 — Routing Policies + Fallback Chains ✅

v0.22.3 — Provider Admin UI + Deferred Polish ✅

v0.22.4 — Provider Health UX + Project Files + Export ✅

v0.22.5 — Surfaces + Go Templates + Admin Bug Fixes ✅

v0.22.6 — Split Deployment Fix + CI Timeout + Code Pruning ✅

v0.22.7 — Surface Prototypes (Theme + ChatPane + Splash) ✅

✅ v0.22.8 — Surface Integration (Wire into Existing JS)

✅ v0.23.0 — @mention Routing + Persona Handles + Proxy

✅ v0.23.1 — Multi-User Navigation + Conversation Taxonomy

✅ v0.23.2 — Multi-User Polish + Channel Lifecycle

v0.24.0 — Auth Abstraction + User Identity ✅

v0.24.1 — mTLS + OIDC Providers ✅

v0.24.2 — Fine-Grained Permissions

v0.24.3 — Anonymous / Session Participants

v0.25.0 — Workflow Engine

v0.26.0 — Tasks / Autonomous Agents

TBD (unscheduled — real features, no immediate need)

87 KiB

Raw Blame History