docs: update meta files for multi-agent orchestration

- v3-progress.md: full session log for agent orchestration work
- v3-task_plan.md: 7 new decisions (agent rendering, env passthrough,
  re-injection, shared DB, role tabs, PlantUML encoding)
- CLAUDE.md: updated overview, key paths, component list
- .claude/CLAUDE.md: updated workflow, ProjectBox tabs, orchestration docs

.claude/CLAUDE.md

@@ -5,7 +5,7 @@
 - v1 is a single-file Python app (`bterminal.py`). Changes are localized.
 - v2 docs are in `docs/`. Architecture decisions are in `docs/task_plan.md`.
 - v2 Phases 1-7 + multi-machine (A-D) + profiles/skills complete. Extras: SSH, ctx, themes, detached mode, auto-updater, shiki, copy/paste, session resume, drag-resize, session groups, Deno sidecar, Claude profiles, skill discovery.
-- v3 Mission Control (All Phases 1-10 Complete + S-1 Phase 1/1.5/2/3 + S-2 Session Anchors + Provider Adapter Pattern + Provider Runners + Memora Adapter + SOLID Phase 2): project groups, workspace store, 12 Workspace components, session continuity, workspace teardown, file overlap conflict detection, inotify-based external write detection, multi-provider adapter pattern (3 phases + Codex/Ollama runners), worktree isolation, session anchors, Memora adapter (read-only SQLite), SOLID refactoring (agent-dispatcher split → 4 utils, session.rs split → 7 sub-modules), dead v2 component cleanup. 286 vitest + 49 cargo tests.
+- v3 Mission Control (All Phases 1-10 Complete + S-1 Phase 1/1.5/2/3 + S-2 Session Anchors + Provider Adapter Pattern + Provider Runners + Memora Adapter + SOLID Phase 3 + Multi-Agent Orchestration): project groups, workspace store, 15 Workspace components, session continuity, workspace teardown, file overlap conflict detection, inotify-based external write detection, multi-provider adapter pattern (3 phases + Codex/Ollama runners), worktree isolation, session anchors, Memora adapter (read-only SQLite), SOLID refactoring (agent-dispatcher split → 4 utils, session.rs split → 7 sub-modules, branded types), multi-agent orchestration (btmsg inter-agent messaging, bttask kanban task board, agent prompt generator, BTMSG_AGENT_ID env passthrough, periodic re-injection, role-specific tabs: Manager=Tasks, Architect=Arch, Tester=Selenium+Tests), dead v2 component cleanup. 286 vitest + 49 cargo tests.
 - v3 docs: `docs/v3-task_plan.md`, `docs/v3-findings.md`, `docs/v3-progress.md`.
 - Consult Memora (tag: `bterminal`) before making architectural changes.
 
@@ -35,10 +35,14 @@
 - Sidecar uses per-provider runner bundles (`sidecar/dist/{provider}-runner.mjs`). Currently only `claude-runner.mjs` exists. SidecarManager.resolve_sidecar_for_provider(provider) finds the right runner file. Deno preferred (faster startup), Node.js fallback. Communicates with Rust via stdio NDJSON. Claude CLI auto-detected at startup via `findClaudeCli()` — checks ~/.local/bin/claude, ~/.claude/local/claude, /usr/local/bin/claude, /usr/bin/claude, then `which claude`. Path passed to SDK via `pathToClaudeCodeExecutable` option. Agents error immediately if CLI not found. Provider env var stripping: strip_provider_env_var() strips CLAUDE*/CODEX*/OLLAMA* vars (whitelists CLAUDE_CODE_EXPERIMENTAL_*). Dual-layer: (1) Rust env_clear() + clean_env, (2) JS runner SDK `env` option. Session stop uses AbortController.abort(). `agent-runner-deno.ts` exists as standalone alternative runner but is NOT used by SidecarManager.
 - AgentPane does NOT stop agents in onDestroy — onDestroy fires on layout remounts, not just explicit close. Stop-on-close is handled externally (was TilingGrid in v2, now workspace teardown in v3).
 - Agent dispatcher (`src/lib/agent-dispatcher.ts`) is a thin coordinator (260 lines) routing sidecar events to the agent store. Delegates to extracted modules: `utils/session-persistence.ts` (session-project maps, persistSessionForProject), `utils/subagent-router.ts` (spawn + route subagent panes), `utils/auto-anchoring.ts` (triggerAutoAnchor on compaction), `utils/worktree-detection.ts` (detectWorktreeFromCwd pure function). Provider-aware via message-adapters.ts.
-- AgentQueryOptions supports `provider` field (defaults to 'claude', flows Rust -> sidecar), `provider_config` blob (Rust passes through as serde_json::Value), `permission_mode` (defaults to 'bypassPermissions'), `setting_sources` (defaults to ['user', 'project']), `system_prompt`, `model`, `claude_config_dir` (for multi-account), `additional_directories`, `worktree_name` (when set, passed as `extraArgs: { worktree: name }` to SDK → `--worktree <name>` CLI flag).
+- AgentQueryOptions supports `provider` field (defaults to 'claude', flows Rust -> sidecar), `provider_config` blob (Rust passes through as serde_json::Value), `permission_mode` (defaults to 'bypassPermissions'), `setting_sources` (defaults to ['user', 'project']), `system_prompt`, `model`, `claude_config_dir` (for multi-account), `additional_directories`, `worktree_name` (when set, passed as `extraArgs: { worktree: name }` to SDK → `--worktree <name>` CLI flag), `extra_env` (HashMap<String,String>, injected into sidecar process env; used for BTMSG_AGENT_ID).
+- Multi-agent orchestration: Tier 1 (management agents: Manager, Architect, Tester, Reviewer) defined in groups.json `agents[]`, converted to ProjectConfig via `agentToProject()`, rendered as full ProjectBoxes. Tier 2 (project agents) are regular ProjectConfig entries. Both tiers get system prompts. Tier 1 prompt built by `generateAgentPrompt()` (utils/agent-prompts.ts): 7 sections (Identity, Environment, Team, btmsg docs, bttask docs, Custom context, Workflow). Tier 2 gets optional `project.systemPrompt` as custom context. BTMSG_AGENT_ID env var injected for Tier 1 agents only (enables btmsg/bttask CLI usage). Periodic re-injection: AgentSession runs 1-hour timer, sends context refresh prompt when agent is idle (autoPrompt → AgentPane → startQuery with resume=true).
+- bttask kanban: Rust bttask.rs module reads/writes tasks table in shared btmsg.db (~/. local/share/bterminal/btmsg.db). 6 operations: list_tasks, create_task, update_task_status, delete_task, add_comment, task_comments. Frontend: TaskBoardTab.svelte (kanban 5 columns, 5s poll). CLI `bttask` tool gives agents direct access; Manager has full CRUD, other roles have read-only + comments.
+- ArchitectureTab: PlantUML diagram viewer/editor. Stores .puml files in `.architecture/` project dir. Renders via plantuml.com server using ~h hex encoding (no Java dependency). 4 templates: Class, Sequence, State, Component. Editor + SVG preview toggle.
+- TestingTab: Dual-mode component (mode='selenium'|'tests'). Selenium: watches `.selenium/screenshots/` for PNG/JPG, displays in gallery with session log, 3s poll. Tests: discovers files in standard dirs (tests/, test/, spec/, __tests__/, e2e/), shows content.
 - Worktree isolation (S-1 Phase 3): Per-project `useWorktrees` toggle in SettingsTab. When enabled, AgentPane passes `worktree_name=sessionId` in queryAgent(). Agent runs in `<repo>/.claude/worktrees/<sessionId>/`. CWD-based detection: `utils/worktree-detection.ts` `detectWorktreeFromCwd()` matches `.claude/worktrees/`, `.codex/worktrees/`, `.cursor/worktrees/` patterns on init events → calls `setSessionWorktree()` for conflict suppression. Dual detection: CWD-based (primary, from init event) + tool_call-based `extractWorktreePath()` (subagent fallback).
 - Claude profiles: claude_list_profiles() reads ~/.config/switcher/profiles/ with profile.toml metadata. Profile set per-project in Settings (project.profile field), passed through AgentSession -> AgentPane `profile` prop -> resolved to config_dir for SDK. Profile name shown as info-only in ProjectHeader.
-- ProjectBox has project-level tab bar: Model | Docs | Context | Files | SSH | Memory. Three mount strategies: PERSISTED-EAGER (Model, Docs, Context — always mounted, display:flex/none), PERSISTED-LAZY (Files, SSH, Memory — mount on first activation via {#if everActivated} + display:flex/none). Tab type: `'model' | 'docs' | 'context' | 'files' | 'ssh' | 'memories'`. Model tab = AgentSession+TeamAgentsPanel. Docs tab = ProjectFiles (markdown viewer). Context tab = ContextTab.svelte (LLM context window visualization: stats bar, segmented token meter, file references, turn breakdown; reads from agent store via sessionId prop; replaced old ContextPane ctx database viewer). Files tab = FilesTab.svelte (VSCode-style directory tree + CodeMirror 6 editor with 15 language modes, dirty tracking, Ctrl+S save, save-on-blur setting, image display via convertFileSrc, 10MB gate; CodeEditor.svelte wrapper; PdfViewer.svelte for PDF files via pdfjs-dist with canvas multi-page rendering + zoom 0.5x–3x; CsvTable.svelte for CSV with RFC 4180 parser, delimiter auto-detect, sortable columns). SSH tab = SshTab.svelte (CRUD for SSH connections, launch spawns terminal tab in Model tab). Memory tab = MemoriesTab.svelte (pluggable via MemoryAdapter interface in memory-adapter.ts; MemoraAdapter registered at startup, reads ~/.local/share/memora/memories.db via Rust memora.rs). Rust backend: list_directory_children + read_file_content + write_file_content (FileContent tagged union: Text/Binary/TooLarge). Frontend bridge: files-bridge.ts.
+- ProjectBox has project-level tab bar: Model | Docs | Context | Files | SSH | Memory + role-specific tabs. Three mount strategies: PERSISTED-EAGER (Model, Docs, Context — always mounted, display:flex/none), PERSISTED-LAZY (Files, SSH, Memory, Tasks, Architecture, Selenium, Tests — mount on first activation via {#if everActivated} + display:flex/none). Tab type: `'model' | 'docs' | 'context' | 'files' | 'ssh' | 'memories' | 'tasks' | 'architecture' | 'selenium' | 'tests'`. Role-specific tabs: Manager gets Tasks (kanban), Architect gets Arch (PlantUML), Tester gets Selenium+Tests. Conditional on `isAgent && agentRole`. Model tab = AgentSession+TeamAgentsPanel. Docs tab = ProjectFiles (markdown viewer). Context tab = ContextTab.svelte (LLM context window visualization: stats bar, segmented token meter, file references, turn breakdown; reads from agent store via sessionId prop; replaced old ContextPane ctx database viewer). Files tab = FilesTab.svelte (VSCode-style directory tree + CodeMirror 6 editor with 15 language modes, dirty tracking, Ctrl+S save, save-on-blur setting, image display via convertFileSrc, 10MB gate; CodeEditor.svelte wrapper; PdfViewer.svelte for PDF files via pdfjs-dist with canvas multi-page rendering + zoom 0.5x–3x; CsvTable.svelte for CSV with RFC 4180 parser, delimiter auto-detect, sortable columns). SSH tab = SshTab.svelte (CRUD for SSH connections, launch spawns terminal tab in Model tab). Memory tab = MemoriesTab.svelte (pluggable via MemoryAdapter interface in memory-adapter.ts; MemoraAdapter registered at startup, reads ~/.local/share/memora/memories.db via Rust memora.rs). Tasks tab = TaskBoardTab.svelte (kanban board, 5 columns, 5s poll, Manager only). Arch tab = ArchitectureTab.svelte (PlantUML viewer/editor, .architecture/ dir, plantuml.com ~h hex encoding, Architect only). Selenium tab = TestingTab.svelte mode=selenium (screenshot gallery, session log, 3s poll, Tester only). Tests tab = TestingTab.svelte mode=tests (test file discovery, content viewer, Tester only). Rust backend: list_directory_children + read_file_content + write_file_content (FileContent tagged union: Text/Binary/TooLarge). Frontend bridge: files-bridge.ts.
 - ProjectHeader shows CWD (ellipsized from START via `direction: rtl`) + profile name as info-only text on right side. AgentPane no longer has DIR/ACC toolbar — CWD and profile are props from parent.
 - Skill discovery: claude_list_skills() reads ~/.claude/skills/ (dirs with SKILL.md or .md files). claude_read_skill() reads content. AgentPane `/` prefix triggers autocomplete menu. Skill content injected as prompt via expandSkillPrompt().
 - claude-bridge.ts adapter wraps profile/skill Tauri commands (ClaudeProfile, ClaudeSkill interfaces). provider-bridge.ts wraps claude-bridge as generic provider bridge (delegates by ProviderId).

CLAUDE.md

@@ -2,7 +2,7 @@
 
 ## Project Overview
 
-Terminal emulator with SSH and Claude Code session management. v1 (GTK3+VTE Python) is production-stable. v2 redesign (Tauri 2.x + Svelte 5 + Claude Agent SDK) Phases 1-7 + multi-machine (A-D) + profiles/skills complete. Packaging: .deb + AppImage via GitHub Actions CI. v3 Mission Control (All Phases 1-10 Complete + Sidebar Redesign): multi-project dashboard with project groups, per-project Claude sessions with session continuity, team agents panel, terminal tabs, VSCode-style left sidebar (icon rail + expandable drawer + always-visible workspace), dead v2 component cleanup.
+Terminal emulator with SSH and Claude Code session management. v1 (GTK3+VTE Python) is production-stable. v2 redesign (Tauri 2.x + Svelte 5 + Claude Agent SDK) Phases 1-7 + multi-machine (A-D) + profiles/skills complete. Packaging: .deb + AppImage via GitHub Actions CI. v3 Mission Control (All Phases 1-10 Complete + Sidebar Redesign + Multi-Agent Orchestration): multi-project dashboard with project groups, per-project Claude sessions with session continuity, team agents panel, terminal tabs, VSCode-style left sidebar, multi-agent orchestration (Tier 1 management agents: Manager/Architect/Tester with role-specific tabs, btmsg inter-agent messaging, bttask kanban task board, BTMSG_AGENT_ID env passthrough, periodic system prompt re-injection, custom context for all tiers).
 
 - **Repository:** github.com/DexterFromLab/BTerminal
 - **License:** MIT
@@ -37,7 +37,8 @@ Terminal emulator with SSH and Claude Code session management. v1 (GTK3+VTE Pyth
 | `v2/src-tauri/src/groups.rs` | Groups config (load/save ~/.config/bterminal/groups.json) |
 | `v2/src-tauri/src/fs_watcher.rs` | ProjectFsWatcher (inotify per-project recursive file change detection, S-1 Phase 2) |
 | `v2/src-tauri/src/lib.rs` | AppState + setup + handler registration (~170 lines) |
-| `v2/src-tauri/src/commands/` | 11 domain command modules (pty, agent, watcher, session, persistence, knowledge, claude, groups, files, remote, misc) |
+| `v2/src-tauri/src/commands/` | 12 domain command modules (pty, agent, watcher, session, persistence, knowledge, claude, groups, files, remote, misc, bttask) |
+| `v2/src-tauri/src/bttask.rs` | Task board backend (list, create, update status, delete, comments; shared btmsg.db) |
 | `v2/src-tauri/src/sidecar.rs` | SidecarManager (thin re-export from bterminal-core) |
 | `v2/src-tauri/src/event_sink.rs` | TauriEventSink (implements EventSink for AppHandle) |
 | `v2/src-tauri/src/remote.rs` | RemoteManager (WebSocket client connections to relays) |
@@ -81,7 +82,9 @@ Terminal emulator with SSH and Claude Code session management. v1 (GTK3+VTE Pyth
 | `v2/src/lib/adapters/memora-bridge.ts` | Memora IPC bridge + MemoraAdapter (read-only SQLite via Tauri commands) |
 | `v2/src/lib/adapters/fs-watcher-bridge.ts` | Filesystem watcher IPC wrapper (project CWD write detection) |
 | `v2/src/lib/adapters/anchors-bridge.ts` | Session anchors IPC wrapper (save, load, delete, clear, updateType) |
+| `v2/src/lib/adapters/bttask-bridge.ts` | Task board IPC adapter (listTasks, createTask, updateTaskStatus, deleteTask, comments) |
 | `v2/src/lib/adapters/telemetry-bridge.ts` | Frontend telemetry bridge (routes events to Rust tracing via IPC) |
+| `v2/src/lib/utils/agent-prompts.ts` | Agent prompt generator (generateAgentPrompt: identity, env, team, btmsg/bttask docs, workflow) |
 | `docker/tempo/` | Docker compose: Tempo + Grafana for trace visualization (port 9715) |
 | `v2/src/lib/stores/machines.svelte.ts` | Remote machine state store (Svelte 5 runes) |
 | `v2/src/lib/utils/attention-scorer.ts` | Pure attention scoring function (extracted from health store, 14 tests) |
@@ -108,7 +111,7 @@ Terminal emulator with SSH and Claude Code session management. v1 (GTK3+VTE Pyth
 | `v2/src/lib/utils/tool-files.ts` | Shared file path extraction from tool_call inputs (extractFilePaths, extractWritePaths, extractWorktreePath) |
 | `v2/src/lib/components/StatusBar/StatusBar.svelte` | Mission Control bar (agent states, $/hr burn rate, attention queue, cost) |
 | `v2/src/lib/components/Notifications/ToastContainer.svelte` | Toast notification display |
-| `v2/src/lib/components/Workspace/` | v3 components: GlobalTabBar, ProjectGrid, ProjectBox, ProjectHeader, AgentSession, TeamAgentsPanel, AgentCard, TerminalTabs, ProjectFiles, FilesTab, SshTab, MemoriesTab, CommandPalette, DocsTab, SettingsTab |
+| `v2/src/lib/components/Workspace/` | v3 components: GlobalTabBar, ProjectGrid, ProjectBox, ProjectHeader, AgentSession, TeamAgentsPanel, AgentCard, TerminalTabs, ProjectFiles, FilesTab, SshTab, MemoriesTab, CommandPalette, DocsTab, SettingsTab, TaskBoardTab, ArchitectureTab, TestingTab |
 | `v2/src/lib/types/groups.ts` | TypeScript interfaces (ProjectConfig, GroupConfig, GroupsFile) |
 | `v2/src/lib/adapters/session-bridge.ts` | Session/layout/group persistence IPC wrapper |
 | `v2/src/lib/components/Markdown/MarkdownPane.svelte` | Markdown file viewer (marked.js + shiki, live reload) |

docs/v3-progress.md

@@ -789,3 +789,97 @@ Ran nemezis-audit on Rust backend. 0 verified exploitable findings, 10 recon tar
 - [x] vitest: 286/286 pass (5 worktree tests moved to new file)
 - [x] cargo check: clean
 - [x] cargo test: 49/49 pass
+
+### Session 2026-03-11 (SOLID Phase 3 — Branded Types)
+
+#### Implementation
+- [x] Introduced SessionId/ProjectId branded types (types/ids.ts)
+- [x] Applied branded types to conflicts.svelte.ts and health.svelte.ts Map keys
+- [x] Branded sessionId at sidecar boundary in agent-dispatcher
+- [x] Applied branded types at Svelte component call sites
+
+#### Results
+- [x] cargo check: clean
+- [x] vitest: 286/286 pass
+
+### Session 2026-03-11 — Multi-Agent Orchestration System
+
+#### btmsg Group Agent Messenger CLI
+- [x] Created btmsg CLI tool — inter-agent messaging (inbox, send, reply, contacts, history, channels)
+- [x] btmsg graph command — visual agent hierarchy with status
+- [x] Admin role (tier 0), channel messaging (create/list/send/history), mark-read, global feed
+
+#### btmsg Rust Backend + Tauri Bridge
+- [x] Created btmsg.rs module — SQLite-backed messaging (shared DB: ~/.local/share/bterminal/btmsg.db)
+- [x] 8+ Tauri commands: btmsg_inbox, btmsg_send, btmsg_read, btmsg_contacts, btmsg_feed, btmsg_channels, etc.
+- [x] CommsTab: sidebar chat interface with activity feed, DMs, channels (Ctrl+M)
+
+#### Agent Unification (Tier 1 → ProjectBoxes)
+- [x] agentToProject() converter in groups.ts — Tier 1 agents rendered as full ProjectBoxes
+- [x] getAllWorkItems() in workspace store combines agents + projects for ProjectGrid
+- [x] GroupAgentsPanel: click-to-navigate agent cards to their ProjectBox
+
+#### Agent System Prompts
+- [x] Created utils/agent-prompts.ts — generateAgentPrompt() builds comprehensive introductory context
+  - Sections: Identity, Environment, Team hierarchy, btmsg docs, bttask docs, Custom context, Workflow
+  - Role-specific workflows (Manager: check inbox → review board → coordinate; Architect: code review focus; Tester: write/run tests)
+- [x] AgentSession builds system prompt: Tier 1 gets full generated prompt, Tier 2 gets custom context
+
+#### BTMSG_AGENT_ID Environment Passthrough (5-layer chain)
+- [x] agent-bridge.ts: added extra_env?: Record<string,string> to AgentQueryOptions
+- [x] bterminal-core/sidecar.rs: added extra_env: HashMap<String,String> with #[serde(default)]
+- [x] claude-runner.ts: extraEnv merged into cleanEnv after provider var stripping
+- [x] codex-runner.ts: same extraEnv pattern
+- [x] AgentSession injects { BTMSG_AGENT_ID: project.id } for agent projects
+
+#### Tier 1 Agent Config in SettingsTab
+- [x] Agent cards: icon + name + role badge + enable toggle + CWD + model + wake interval (manager)
+- [x] Custom Context textarea per agent (appended to auto-generated prompt)
+- [x] Collapsible preview of full generated introductory prompt
+- [x] updateAgent() function in workspace store for Tier 1 config persistence
+
+#### Custom Context for Tier 2 Projects
+- [x] Custom Context textarea in SettingsTab project cards
+- [x] Stored as project.systemPrompt, passed through AgentSession → AgentPane
+
+#### Periodic System Prompt Re-injection
+- [x] AgentSession: 1-hour timer (REINJECTION_INTERVAL_MS = 3,600,000ms)
+- [x] Checks every 60s if elapsed > 1 hour, sets contextRefreshPrompt
+- [x] AgentPane: autoPrompt prop consumed only when agent is idle (done/error state)
+- [x] Different refresh messages: Tier 1 (check inbox + task board), Tier 2 (review instructions)
+
+#### bttask Kanban Backend + UI
+- [x] Created bttask.rs — Task/TaskComment structs, 6 operations (list, comments, update_status, create, delete, add_comment)
+- [x] Created commands/bttask.rs — 6 Tauri commands registered in lib.rs
+- [x] Created bttask-bridge.ts — TypeScript IPC adapter
+- [x] Created TaskBoardTab.svelte — Kanban board with 5 columns (todo/progress/review/done/blocked)
+  - Task creation form (title, description, priority)
+  - Expandable task detail with status actions, comments, delete
+  - 5-second polling
+  - Pending count badge
+
+#### ArchitectureTab (PlantUML Diagrams)
+- [x] Created ArchitectureTab.svelte — PlantUML diagram viewer/editor
+  - Sidebar with diagram list + new diagram form (4 templates: Class, Sequence, State, Component)
+  - PlantUML source editor + SVG preview via plantuml.com server (~h hex encoding)
+  - Stores .puml files in .architecture/ directory
+  - Read/write via files-bridge.ts
+
+#### TestingTab (Selenium + Automated Tests)
+- [x] Created TestingTab.svelte — dual-mode component
+  - Selenium mode: screenshot gallery (.selenium/screenshots/), session log viewer, 3s polling
+  - Tests mode: discovers test files in standard dirs (tests/, test/, spec/, __tests__/, e2e/), file content viewer
+
+#### Role-Specific Tabs in ProjectBox
+- [x] Extended ProjectTab type: added 'tasks' | 'architecture' | 'selenium' | 'tests'
+- [x] Conditional tab buttons: Manager→Tasks, Architect→Arch, Tester→Selenium+Tests
+- [x] PERSISTED-LAZY rendering via {#if everActivated[tab]} pattern
+- [x] .ptab-role CSS class (mauve accent color for agent-specific tabs)
+
+#### Bug Fix
+- [x] Fixed FileContent type case: 'text' → 'Text' in ArchitectureTab and TestingTab (files-bridge uses capital T)
+
+#### Verification
+- [x] cargo check: clean (bttask module + commands)
+- [x] svelte-check: 0 project errors
+- [x] Sidecar rebuilt with extraEnv support

docs/v3-task_plan.md

@@ -335,6 +335,12 @@ All 10 phases complete. Detailed checklists in [v3-progress.md](v3-progress.md).
 | Unmount/remount on group switch | Serialize xterm scrollbacks, destroy, remount new group. <100ms perceived. Frees ~80MB. | 2026-03-07 |
 | All themes map to --ctp-* CSS vars | 17 themes in 3 groups: 4 Catppuccin + 7 Editor (VSCode Dark+, Atom One Dark, Monokai, Dracula, Nord, Solarized Dark, GitHub Dark) + 6 Deep Dark (Tokyo Night, Gruvbox Dark, Ayu Dark, Poimandres, Vesper, Midnight). All map to same 26 --ctp-* CSS custom properties — zero component changes needed. | 2026-03-07 |
 | Typography via CSS custom properties | --ui-font-family/--ui-font-size + --term-font-family/--term-font-size in catppuccin.css :root. Restored by initTheme() on startup. Persisted as ui_font_family/ui_font_size/term_font_family/term_font_size SQLite settings. | 2026-03-07 |
+| Tier 1 agents as ProjectBoxes via agentToProject() | Agents render as full ProjectBoxes (not separate UI). getAllWorkItems() merges agents+projects. Unified rendering = less code, same capabilities. | 2026-03-11 |
+| extra_env 5-layer passthrough for BTMSG_AGENT_ID | TS → Rust AgentQueryOptions → NDJSON → JS runner → SDK env. Minimal surface — only agent projects get env injection. | 2026-03-11 |
+| Periodic system prompt re-injection (1 hour) | LLM context degrades over long sessions. 1-hour timer re-sends role/tools reminder when agent is idle. autoPrompt/onautopromptconsumed callback pattern between AgentSession and AgentPane. | 2026-03-11 |
+| btmsg/bttask shared SQLite DB | Both CLI tools share ~/.local/share/bterminal/btmsg.db. Single DB simplifies deployment, agents already have path. Read-only for non-Manager roles via CLI permissions. | 2026-03-11 |
+| Role-specific tabs via conditional rendering | Manager=Tasks, Architect=Arch, Tester=Selenium+Tests. PERSISTED-LAZY pattern (mount on first activation). Conditional on isAgent && agentRole. | 2026-03-11 |
+| PlantUML via plantuml.com server (~h hex encoding) | Avoids Java dependency. Hex encoding simpler than deflate+base64. Works with free tier. Trade-off: requires internet. | 2026-03-11 |
 
 ## Errors Encountered