agents-orchestrator/agent-orchestrator
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: update meta files for Codex/Ollama provider runners

Browse source
This commit is contained in:
Hibryda 2026-03-11 03:56:05 +01:00
parent 8309896e7d
commit ad7e24e40d
6 changed files with 68 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
.claude/CLAUDE.md
View file

@ -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 Conflict Detection + Provider Adapter Pattern): 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: core abstraction, settings UI, sidecar routing), dead v2 component cleanup. 202 vitest + 42 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): 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, dead v2 component cleanup. 256 vitest + 42 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.
@ -31,7 +31,7 @@
## 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 (currently only Claude registered).
- 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 singleton that routes sidecar events to the agent store. Provider-aware: sessionProviderMap routes messages through adaptMessage(provider, event) from message-adapters.ts. Handles subagent routing (project-scoped sessions skip layout pane, render in TeamAgentsPanel; detached mode creates layout pane). Session persistence via registerSessionProject(sessionId, projectId, provider) + persistSessionForProject() (saves state + messages to SQLite on complete).
@ -43,7 +43,7 @@
- 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` bundles SDK into claude-runner.mjs via esbuild (no --external, SDK included in bundle). Future providers will have separate runner bundles.
- 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".