# Agent Orchestrator — Claude Behavioral Guide

## Workflow

- v1 is a single-file Python app (`bterminal.py`). Changes are localized.
- v2 docs are in `docs/`. Architecture in `docs/architecture.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 + Production Readiness Complete): project groups, workspace store, 15+ Workspace components, session continuity, multi-provider adapter pattern, worktree isolation, session anchors, Memora adapter, SOLID refactoring, multi-agent orchestration (btmsg/bttask, 4 Tier 1 roles, role-specific tabs), dashboard metrics, auto-wake scheduler, reviewer agent. Production: sidecar supervisor (auto-restart, exponential backoff), FTS5 search (3 virtual tables, Spotlight overlay), plugin system (Web Worker sandbox, permission-gated), Landlock sandbox (kernel 6.2+), secrets management (system keyring), OS+in-app notifications, keyboard-first UX (18+ palette commands, vi-nav), agent health monitoring (heartbeats, dead letter queue), audit logging, error classification (6 types), optimistic locking (bttask). Hardening: TLS relay, SPKI pinning (TOFU), WAL checkpoint (5min), subagent delegation fix, plugin sandbox tests (26), SidecarManager actor pattern, per-message btmsg acknowledgment, Aider autonomous mode. 507 vitest + 110 cargo + 109 E2E.
- Consult Memora (tag: `bterminal`) before making architectural changes.

## Documentation References

- System architecture: [docs/architecture.md](../docs/architecture.md)
- Architecture decisions: [docs/decisions.md](../docs/decisions.md)
- Sidecar architecture: [docs/sidecar.md](../docs/sidecar.md)
- Multi-agent orchestration: [docs/orchestration.md](../docs/orchestration.md)
- Production hardening: [docs/production.md](../docs/production.md)
- Implementation phases: [docs/phases.md](../docs/phases.md)
- Research findings: [docs/findings.md](../docs/findings.md)
- Progress logs: [docs/progress/](../docs/progress/)

## Rules

- Do not modify v1 code (`bterminal.py`) unless explicitly asked — it is production-stable.
- v2/v3 work goes on the `hib_changes` branch (repo: agent-orchestrator), not master.
- Architecture decisions must reference `docs/decisions.md`.
- When adding new decisions, append to the appropriate category table with date.
- Update `docs/progress/` after each significant work session.

## Key Technical Constraints

- WebKit2GTK has no WebGL — xterm.js must use Canvas addon explicitly.
- Agent sessions use `@anthropic-ai/claude-agent-sdk` query() function (migrated from raw CLI spawning due to piped stdio hang bug). SDK handles subprocess management internally. All output goes through the adapter layer (`src/lib/adapters/claude-messages.ts` via `message-adapters.ts` registry) — SDK message format matches CLI stream-json. Multi-provider support: message-adapters.ts routes by ProviderId to provider-specific parsers (claude-messages.ts, codex-messages.ts, ollama-messages.ts — all 3 registered).
- 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), `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). 7 operations: list_tasks, create_task, update_task_status, delete_task, add_comment, task_comments, review_queue_count. Frontend: TaskBoardTab.svelte (kanban 5 columns, 5s poll). CLI `bttask` tool gives agents direct access; Manager has full CRUD, Reviewer has read + status + comments, other roles have read-only + comments. On task→review transition, auto-posts to #review-queue btmsg channel (ensure_review_channels creates #review-queue + #review-log idempotently). Reviewer agent gets Tasks tab in ProjectBox (reuses TaskBoardTab). reviewQueueDepth in AttentionInput: 10pts per review task, capped at 50 (priority between file_conflict 70 and context_high 40). ProjectBox polls review_queue_count every 10s for reviewer agents → setReviewQueueDepth() in health store.
- btmsg/bttask SQLite conventions: Both btmsg.rs and bttask.rs open shared btmsg.db with WAL mode + 5s busy_timeout (concurrent access from Python CLIs + Rust backend). All queries use named column access (`row.get("column_name")`) — never positional indices. Rust structs use `#[serde(rename_all = "camelCase")]`; TypeScript interfaces MUST match camelCase wire format. TestingTab uses `convertFileSrc()` for Tauri 2.x asset URLs (not `asset://localhost/`).
- 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 + role-specific tabs. Three mount strategies: PERSISTED-EAGER (Model, Docs, Context — always mounted, display:flex/none), PERSISTED-LAZY (Files, SSH, Memory, Metrics, Tasks, Architecture, Selenium, Tests — mount on first activation via {#if everActivated} + display:flex/none). Tab type: `'model' | 'docs' | 'context' | 'files' | 'ssh' | 'memories' | 'metrics' | 'tasks' | 'architecture' | 'selenium' | 'tests'`. Role-specific tabs: Manager gets Tasks (kanban), Architect gets Arch (PlantUML), Tester gets Selenium+Tests. Metrics tab (all projects): MetricsPanel.svelte — Live view (fleet aggregates, project health grid, task board summary, attention queue) + History view (SVG sparklines for cost/tokens/turns/tools/duration, stats row, session table from session_metrics_load). 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).
- Provider adapter pattern: ProviderId = 'claude' | 'codex' | 'ollama'. ProviderCapabilities flags gate UI (hasProfiles, hasSkills, hasModelSelection, hasSandbox, supportsSubagents, supportsCost, supportsResume). ProviderMeta registered via registerProvider() in App.svelte onMount. AgentPane receives provider + capabilities props. SettingsTab has Providers section with collapsible per-provider config panels. ProjectConfig.provider field for per-project selection. Settings persisted as `provider_settings` JSON blob.
- Sidecar build: `npm run build:sidecar` builds all 3 runners via esbuild (claude-runner.mjs, codex-runner.mjs, ollama-runner.mjs). Each is a standalone ESM bundle. Codex runner dynamically imports @openai/codex-sdk (graceful failure if not installed). Ollama runner uses native fetch (zero deps).
- Agent preview terminal: `AgentPreviewPane.svelte` is a read-only xterm.js terminal (disableStdin:true) that subscribes to an agent session's messages via `$derived(getAgentSession(sessionId))` and renders tool calls/results in real-time. Bash commands shown as cyan `❯ cmd`, file ops as yellow `[Read] path`, results as plain text (80-line truncation), errors in red. Spawned via 👁 button in TerminalTabs (appears when agentSessionId prop is set). TerminalTab type: `'agent-preview'` with `agentSessionId` field. Deduplicates — won't create two previews for the same session. ProjectBox passes mainSessionId to TerminalTabs.
- Maximum 4 active xterm.js instances to avoid WebKit2GTK memory issues. Agent preview uses disableStdin and no PTY so is lighter, but still counts.
- Store files using Svelte 5 runes (`$state`, `$derived`) MUST have `.svelte.ts` extension (not `.ts`). Import with `.svelte` suffix. Plain `.ts` compiles but fails at runtime with "rune_outside_svelte".
- Session persistence uses rusqlite (bundled) with WAL mode. Data dir: `dirs::data_dir()/bterminal/sessions.db`.
- Layout store persists to SQLite on every addPane/removePane/setPreset/setPaneGroup change (fire-and-forget). Restores on app startup via `restoreFromDb()`.
- Session groups: Pane.group? field in layout store, group_name column in sessions table, collapsible group headers in sidebar. Right-click pane to set group.
- File watcher uses notify crate v6, watches parent directory (NonRecursive), emits `file-changed` Tauri events.
- Settings use key-value `settings` table in SQLite (session/settings.rs). Frontend: `settings-bridge.ts` adapter. v3 uses SettingsTab.svelte rendered in sidebar drawer panel (v2 SettingsDialog.svelte deleted in P10). SettingsTab has two sections: Global (single-column layout, split into Appearance [theme dropdown, UI font dropdown with sans-serif options + size stepper, Terminal font dropdown with monospace options + size stepper] and Defaults [shell, CWD] — all custom themed dropdowns, no native `<select>`, all persisted via settings-bridge with keys: theme, ui_font_family, ui_font_size, term_font_family, term_font_size, default_shell, default_cwd) and Group/Project CRUD.
- Notifications use ephemeral toast system: `notifications.svelte.ts` store (max 5, 4s auto-dismiss), `ToastContainer.svelte` display. Agent dispatcher emits toasts on agent complete/error/crash.
- StatusBar → Mission Control bar: running/idle/stalled agent counts (color-coded), total $/hr burn rate, "needs attention" dropdown priority queue (up to 5 cards sorted by urgency score, click-to-focus), total tokens + cost. Uses health.svelte.ts store (not workspace store for health signals).
- health.svelte.ts store: per-project health tracking via ProjectTracker map. ActivityState = inactive|running|idle|stalled (configurable per-project via stallThresholdMin in ProjectConfig, default 15 min, range 5–60 min step 5, synced via setStallThreshold() API). Burn rate from 5-min EMA costSnapshots. Context pressure = tokens/model limit. File conflict count from conflicts.svelte.ts. Attention scoring: stalled=100, error=90, ctx>90%=80, file_conflict=70, ctx>75%=40. 5-second tick timer (auto-stop/start). API: trackProject(), recordActivity(), recordToolDone(), recordTokenSnapshot(), getProjectHealth(), getAttentionQueue(), getHealthAggregates().
- conflicts.svelte.ts store: per-project file overlap + external write detection. Records Write/Edit/Bash-write tool_call file paths per session. Detects when 2+ sessions in same worktree write same file. S-1 Phase 2: inotify-based external write detection via fs_watcher.rs — uses 2s timing heuristic (AGENT_WRITE_GRACE_MS) to distinguish agent writes from external. EXTERNAL_SESSION_ID='__external__' sentinel. Worktree-aware. Dismissible. recordExternalWrite() for inotify events. FileConflict.isExternal flag, ProjectConflicts.externalConflictCount. Session-scoped, no persistence.
- tool-files.ts utility: shared extractFilePaths(tc) → ToolFileRef[], extractWritePaths(tc) → string[], extractWorktreePath(tc) → string|null. Bash write detection via regex (>, >>, sed -i, tee, cp, mv). Used by ContextTab (all ops) and agent-dispatcher (writes + worktree tracking for conflict detection).
- ProjectHeader shows status dot (green pulse=running, gray=idle, orange pulse=stalled, dim=inactive) + external write badge (orange ⚡ clickable, shown when externalConflictCount > 0) + agent conflict badge (red ⚠ clickable with ✕) + context pressure badge (>90% red, >75% orange, >50% yellow) + burn rate badge ($/hr). Health prop from ProjectBox via getProjectHealth(). ProjectBox starts/stops fs watcher per project CWD via $effect.
- wake-scheduler.svelte.ts store: Manager auto-wake with 3 user-selectable strategies (persistent=resume prompt, on-demand=fresh session, smart=threshold-gated on-demand). Configurable via SettingsTab (strategy segmented button + threshold slider for smart). 6 wake signals from tribunal S-3 hybrid: AttentionSpike(1.0), ContextPressureCluster(0.9), BurnRateAnomaly(0.8), TaskQueuePressure(0.7), ReviewBacklog(0.6), PeriodicFloor(0.1). Pure scorer in wake-scorer.ts (24 tests). Types in types/wake.ts. GroupAgentConfig: wakeStrategy, wakeThreshold fields. ProjectBox registers managers via $effect. AgentSession polls wake events every 5s. Cleared on group switch via clearWakeScheduler().
- session_metrics SQLite table: per-project historical session data (project_id, session_id, timestamps, peak_tokens, turn_count, tool_call_count, cost_usd, model, status, error_message). 100-row retention per project. Tauri commands: session_metric_save, session_metrics_load. Persisted on agent completion via agent-dispatcher.
- Session anchors (S-2): Preserves important turns through compaction chains. Types: auto (on first compaction, 3 turns, observation-masked — reasoning preserved in full, only tool outputs compacted), pinned (user-created via pin button in AgentPane), promoted (user-promoted from pinned, re-injectable). Configurable budget via AnchorBudgetScale ('small'=2K|'medium'=6K|'large'=12K|'full'=20K) — per-project slider in SettingsTab, stored as ProjectConfig.anchorBudgetScale in groups.json. Re-injection: anchors.svelte.ts → AgentPane.startQuery() → system_prompt field → sidecar → SDK. ContextTab shows anchor section with budget meter (derived from scale) + promote/demote. SQLite: session_anchors table. Files: types/anchors.ts, adapters/anchors-bridge.ts, stores/anchors.svelte.ts, utils/anchor-serializer.ts.
- Agent tree (AgentTree.svelte) uses SVG with recursive layout. Tree data built by `agent-tree.ts` utility from agent messages.
- ctx integration opens `~/.claude-context/context.db` as SQLITE_OPEN_READ_ONLY — never writes. CtxDb uses Option<Connection> for graceful absence if DB doesn't exist.
- SSH sessions spawn TerminalPane with shell=/usr/bin/ssh and args array. No SSH library needed — PTY handles it natively.
- Theme system: 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. ThemeId replaces CatppuccinFlavor. getCurrentTheme()/setTheme() are primary API (deprecated wrappers exist). THEME_LIST has ThemeMeta with group metadata for custom dropdown UI. Open terminals hot-swap via onThemeChange() callback registry in theme.svelte.ts. Typography uses --ui-font-family/--ui-font-size (UI elements, sans-serif fallback) and --term-font-family/--term-font-size (terminal, monospace fallback) CSS custom properties (defined in catppuccin.css). initTheme() restores all 4 font settings (ui_font_family, ui_font_size, term_font_family, term_font_size) from SQLite on startup.
- Detached pane mode: App.svelte checks URL param `?detached=1` and renders a single pane without sidebar/grid chrome. Used for pop-out windows.
- Shiki syntax highlighting uses lazy singleton pattern (avoid repeated WASM init). 13 languages preloaded. Used in MarkdownPane and AgentPane text messages.
- Cargo workspace at v2/ level: members = [src-tauri, bterminal-core, bterminal-relay]. Cargo.lock is at workspace root (v2/), not in src-tauri/.
- EventSink trait (bterminal-core/src/event.rs) abstracts event emission. PtyManager and SidecarManager are in bterminal-core, not src-tauri. src-tauri has thin re-exports.
- RemoteManager (src-tauri/src/remote.rs) manages WebSocket client connections to bterminal-relay instances. 12 Tauri commands prefixed with `remote_`.
- remote-bridge.ts adapter wraps remote machine management IPC. machines.svelte.ts store tracks remote machine state.
- Pane.remoteMachineId?: string routes operations through RemoteManager instead of local managers. Bridge adapters (pty-bridge, agent-bridge) check this field.
- bterminal-relay binary (v2/bterminal-relay/) is a standalone WebSocket server with token auth, rate limiting, and per-connection isolated managers. Commands return structured responses (pty_created, pong, error) with commandId for correlation via send_error() helper.
- RemoteManager reconnection: exponential backoff (1s-30s cap) on disconnect, attempt_tcp_probe() (TCP-only, no WS upgrade), emits remote-machine-reconnecting and remote-machine-reconnect-ready events. Frontend listeners in remote-bridge.ts; machines store auto-reconnects on ready.
- v3 workspace store (`workspace.svelte.ts`) replaces layout store for v3. Groups loaded from `~/.config/bterminal/groups.json` via `groups-bridge.ts`. State: groups, activeGroupId, activeTab, focusedProjectId. Derived: activeGroup, activeProjects.
- v3 groups backend (`groups.rs`): load_groups(), save_groups(), default_groups(). Tauri commands: groups_load, groups_save.
- Telemetry (`telemetry.rs`): tracing + optional OTLP export to Tempo. `BTERMINAL_OTLP_ENDPOINT` env var controls (absent = console-only). TelemetryGuard in AppState with Drop-based shutdown. Frontend events route through `frontend_log` Tauri command → Rust tracing (no browser OTEL SDK — WebKit2GTK incompatible). `telemetry-bridge.ts` provides `tel.info/warn/error()` convenience API. Docker stack at `docker/tempo/` (Grafana port 9715).
- E2E test mode (`BTERMINAL_TEST=1`): watcher.rs and fs_watcher.rs skip file watchers, wake-scheduler disabled via `disableWakeScheduler()`, `is_test_mode` Tauri command bridges to frontend. Data/config dirs overridable via `BTERMINAL_TEST_DATA_DIR`/`BTERMINAL_TEST_CONFIG_DIR`. E2E uses WebDriverIO + tauri-driver, single session, TCP readiness probe. Phase A: 7 data-testid-based scenarios in `agent-scenarios.test.ts` (deterministic assertions). Phase B: 6 scenarios in `phase-b.test.ts` (multi-project grid, independent tab switching, status bar fleet state, LLM-judged agent responses/code generation, context tab verification). LLM judge (`llm-judge.ts`): raw fetch to Anthropic API using claude-haiku-4-5, structured verdict (pass/fail + reasoning + confidence), `assertWithJudge()` with configurable threshold, skips when `ANTHROPIC_API_KEY` absent. CI workflow (`.github/workflows/e2e.yml`): unit + cargo + e2e jobs, xvfb-run, path-filtered triggers, LLM tests gated on secret. Test fixtures in `fixtures.ts` create isolated temp environments. Results tracked via JSON store in `results-db.ts`.
- v3 SQLite additions: agent_messages table (per-project message persistence), project_agent_state table (sdkSessionId, cost, status per project), sessions.project_id column.
- v3 App.svelte: VSCode-style sidebar layout. Horizontal: left icon rail (GlobalTabBar, 2.75rem, single Settings gear icon) + expandable drawer panel (Settings only, content-driven width, max 50%) + main workspace (ProjectGrid always visible) + StatusBar. Sidebar has Settings only — Sessions/Docs/Context are project-specific (in ProjectBox tabs). Keyboard: Ctrl+B (toggle sidebar), Ctrl+, (settings), Escape (close).
- v3 component tree: App -> GlobalTabBar (settings icon) + sidebar-panel? (SettingsTab) + workspace (ProjectGrid) + StatusBar. See `docs/architecture.md` for full tree.
- MarkdownPane reactively watches filePath changes via $effect (not onMount-only). Uses sans-serif font (Inter, system-ui), all --ctp-* theme vars. Styled blockquotes with translucent backgrounds, table row hover, link hover underlines. Inner `.markdown-pane-scroll` wrapper with `container-type: inline-size` for responsive padding via `--bterminal-pane-padding-inline`.
- AgentPane UI (redesigned 2026-03-09): sans-serif root font (`system-ui, -apple-system, sans-serif`), monospace only on code/tool names. Tool calls paired with results in collapsible `<details>` groups via `$derived.by` toolResultMap (cache-guarded by tool_result count). Hook messages collapsed into compact `<details>` with gear icon. Context window meter inline in status strip. Cost bar minimal (no background, subtle border-top). Session summary with translucent surface background. Two-phase scroll anchoring (`$effect.pre` + `$effect`). Tool-aware output truncation (Bash 500 lines, Read/Write 50, Glob/Grep 20, default 30). Colors softened via `color-mix()`. Inner `.agent-pane-scroll` wrapper with `container-type: inline-size` for responsive padding via shared `--bterminal-pane-padding-inline` variable.
- ProjectBox uses CSS `style:display` (flex/none) instead of `{#if}` for tab content panes — keeps AgentSession mounted across tab switches (prevents session ID reset and message loss). Terminal section also uses `style:display`. Grid rows: auto auto 1fr auto.
- Svelte 5 event syntax: use `onclick` not `on:click`. Svelte 5 requires lowercase event handler attributes (no colon syntax).

## Memora Tags

Project tag: `bterminal`
Common tag combinations: `bterminal,architecture`, `bterminal,research`, `bterminal,tech-stack`

## Operational Rules

All operational rules live in `.claude/rules/`. Every `.md` file in that directory is automatically loaded at session start by Claude Code with the same priority as this file.

### Rule Index

| # | File | Scope |
|---|------|-------|
| 01 | `security.md` | **PARAMOUNT** — secrets, input validation, least privilege |
| 02 | `error-handling.md` | **PARAMOUNT** — handle every error visibly |
| 03 | `environment-safety.md` | **PARAMOUNT** — verify target, data safety, K8s isolation, cleanup |
| 04 | `communication.md` | Stop on ambiguity, scope discipline |
| 05 | `git-practices.md` | Conventional commits, authorship |
| 06 | `testing.md` | TDD, unit tests, E2E tests |
| 07 | `documentation.md` | README, CLAUDE.md sync, docs/ |
| 08 | `branch-hygiene.md` | Branches, naming, clean state before refactors |
| 09 | `dependency-discipline.md` | No deps without consent |
| 10 | `code-consistency.md` | Match existing patterns |
| 11 | `api-contracts.md` | Contract-first, flag breaking changes (path-conditional) |
| 12 | `performance-awareness.md` | No N+1, no unbounded fetches (path-conditional) |
| 13 | `logging-observability.md` | Structured logging, OTEL (path-conditional) |
| 14 | `resilience-and-config.md` | Timeouts, circuit breakers, externalized config (path-conditional) |
| 15 | `memora.md` | Persistent memory across sessions |
| 16 | `sub-agents.md` | When to use sub-agents and team agents |
| 17 | `document-imports.md` | Resolve @ imports in CLAUDE.md before acting |
| 18 | `relative-units.md` | Use rem/em for layout, px only for icons/borders |
| 20 | `testing-gate.md` | Run full test suite after major changes |
| 51 | `theme-integration.md` | All colors via --ctp-* CSS vars, never hardcode |
| 52 | `no-implicit-push.md` | Never push unless explicitly asked |