Skip to content

Commit 7a9496b

Browse files
feat: Sandbox jobs (nearai#4)
* Orchestrating jobs and running them in sandboxes * Fix heartbeat: dynamic max_tokens, empty content guard, notification fallback - Query /v1/models API for context_length and set max_tokens to half (floor 4096) instead of hardcoded 1024; reasoning models like GLM-4.7 need much larger budgets - Guard against empty LLM content (reasoning models can burn all tokens on chain-of-thought and return content: null) - Simplify notification routing: try configured channel first, fall back to broadcast_all so heartbeat alerts always reach someone - Add ModelMetadata struct and model_metadata() to LlmProvider trait - Refactor NearAiChatProvider::list_models into shared fetch_models() - Add standalone test_heartbeat example for isolated debugging Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add job detail view with drill-down from jobs list Click a job row to see full details across four sub-tabs: Overview (metadata grid, description, state transitions timeline), Actions (expandable tool call cards with input/output JSON), Thinking (conversation messages styled by role), and Files (embedded workspace tree browser). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Strip model-internal XML tags from LLM responses, fix Telegram parse_mode 400 Some models (GLM-4.7, etc.) emit <tool_call>tool_list</tool_call> in the content field instead of using the OpenAI tool_calls array. This XML leaks through to channels as text, and Telegram's Markdown parser chokes on the underscores, returning 400 "can't parse entities". Two fixes: - Generalize clean_response() to strip <tool_call>, <function_call>, <tool_calls>, and pipe-delimited variants (<|tool_call|>) alongside the existing <thinking> tag stripping - Add Telegram send_message helper with parse_mode fallback: try Markdown first, retry as plain text on "can't parse entities" 400 errors Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add SystemCommand submission type for thread-state-independent commands System commands (/help, /model, /version, /tools, /ping, /debug) now bypass thread-state checks and safety validation via a dedicated Submission::SystemCommand variant. Previously these flowed through process_user_input() which blocked them during Processing/AwaitingApproval /Completed states. - Add /model [name] for runtime model switching with provider validation - Add active_model_name()/set_model() to LlmProvider trait with RwLock hot-swap in both NEAR AI providers - Rewrite /help with aligned columns grouped by category - Expand REPL tab-completion from 10 to 23 slash commands - Remove REPL-local /help interception (now handled by agent) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add per-tool execution timeouts, auto-create sandbox project dirs, serve built files The sandbox e2e pipeline (agent -> container -> built website -> browsable URL) was broken by three gaps: hardcoded 60s timeouts killed sandbox jobs that need minutes, no auto-created project directory meant container output vanished, and no HTTP route to browse the built files. - Add `execution_timeout()` to the `Tool` trait (default 60s), replace all four hardcoded `Duration::from_secs(60)` call sites (agent_loop, worker, scheduler, worker/runtime) with the per-tool value - Override to 660s in `RunInSandboxTool` (10 min polling + 60s buffer) - Auto-create `~/.ironclaw/projects/{uuid}/` when no `project_dir` is specified, so every sandbox job gets a persistent bind mount - Include `project_dir` and `browse_url` in sandbox tool output JSON - Add `/projects/{id}` and `/projects/{id}/{path}` static file serving routes to the web gateway with path traversal protection and MIME type detection - Add `mime_guess` dependency for content-type detection Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Apply cargo fmt to wizard.rs after merge Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Persist sandbox jobs in DB, fix web UI, unify job model Sandbox container jobs were invisible to the web UI because they lived only in ContainerJobManager's in-memory HashMap while the API queried ContextManager. This persists them to the agent_jobs table and fixes all six front-end bugs (empty job list, broken back button, empty actions/thinking tabs, wrong files tab, stuck status, no persistence). Key changes: - V4 migration adds project_dir and user_id columns to agent_jobs - Embedded migrations via refinery (no external CLI needed) - SandboxJobRecord CRUD in Store with fire-and-forget DB writes - Unified job_id: sandbox tool generates UUID, passes to ContainerJobManager - Web API queries DB for sandbox jobs, merges with ContextManager direct jobs - New endpoints: restart, project file list/read with path traversal protection - Front-end: rebuild DOM on back navigation, sandbox-aware tabs, job cards in chat stream, source badges, restart button for failed/interrupted jobs - Gateway defaults to enabled, prints Web UI URL on startup - Stale jobs marked "interrupted" on restart for visibility and restartability Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Secure in-chat auth: tokens never touch the LLM or chat history Remove the token parameter from tool_auth so the LLM cannot pass raw API keys. Add dedicated REST (POST /api/chat/auth-token) and WebSocket (auth_token) endpoints that route tokens directly to ext_mgr.auth(), completely bypassing the message pipeline, turns, history, and compaction. Web UI shows an auth card (password input + OAuth button) when the agent enters auth mode, submitted via the dedicated endpoint. CLI auth mode interception is unchanged (already secure). New StatusUpdate::AuthRequired/AuthCompleted variants propagate through all channels (SSE, WebSocket, REPL, WASM). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Add Claude Code mode for sandbox jobs Run Claude Code CLI inside Docker containers as an alternative to the standard worker mode. The bridge spawns `claude -p` with stream-json output, posts events to the orchestrator, and supports follow-up prompts via `--resume`. Key additions: - `claude-bridge` CLI subcommand and ClaudeBridgeRuntime - JobMode enum (Worker vs ClaudeCode) with per-mode container config - Orchestrator endpoints for Claude events and prompt polling - SSE event variants for real-time Claude Code streaming to frontend - Claude Code sub-tab in web UI with terminal-style output and input bar - Database migration for job_mode column and claude_code_events table - ClaudeCodeConfig with env var support (CLAUDE_CODE_ENABLED, etc.) - Mode parameter on run_in_sandbox tool schema Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: Skip create_job tool when sandbox is enabled to prevent duplicate jobs When sandbox mode is on, the LLM would call create_job (creating a pending "direct" entry) then run_in_sandbox (creating a second "sandbox" entry), producing two jobs in the list for a single user request. Now register_job_tools() skips create_job when sandbox is enabled since run_in_sandbox already creates tracked jobs. Also improved the run_in_sandbox description to guide the LLM to use it directly and to mention wait=false for async execution. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Web gateway UI quality-of-life improvements Phase 1: Send button disabled state to prevent double-sends, copy button on code blocks, confirm() guards on destructive actions, SSE-driven job list auto-refresh, log filters re-applied on tab switch, jobEvents memory leak fix (cap at 500, cleanup after 60s). Phase 2: Toast notification system replacing chat-based system messages, memory search highlighting with centered snippets, keyboard shortcuts (Ctrl+1-5 tabs, Ctrl+K focus, Ctrl+N new thread, Escape close/blur), activity tab toolbar with event type filter and auto-scroll toggle. Phase 3: Thread sidebar with load/switch/create, thread_id passed with messages, collapsible to hamburger. Memory inline editing with textarea, Save/Cancel, POST to /api/memory/write. Phase 4: Gateway status popover on hover (polls every 30s), extension install form (name/URL/kind), markdown rendering in memory viewer for .md files, mobile responsive layout at 768px breakpoint. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Add routines system, remove non-sandbox job mode from web UI Routines: scheduled & reactive job system with cron and event triggers, lightweight (single LLM call) and full-job execution modes, guardrails (cooldown, max concurrent, dedup), and LLM-facing tools for CRUD. Web UI: remove ContextManager-backed "direct" job mode entirely. Jobs are now exclusively sandbox-backed (DB + container). Simplify job detail response, drop dead types (ActionInfo, MessageInfo, MessageToolCallInfo), fix Browse Files CSS loading (trailing-slash redirect), fix Activity tab event rendering. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: Re-enable chat input on agent completion, auto-auth on tool_activate, recover tool calls from content XML Three fixes: 1. Chat input stays disabled after agent finishes: the "Done" status SSE event now calls enableChatInput() as a safety net when the response event is empty or lost. Same for auth_completed and cancelAuth(). 2. tool_activate never triggers auth: when activation fails due to missing authentication, it now auto-initiates the auth flow (same pattern as the web API handler). detect_auth_awaiting() also matches tool_activate results now. 3. Models like GLM-4.7 emit tool calls as XML tags in content (<tool_call>tool_list</tool_call>) instead of using the structured tool_calls array. recover_tool_calls_from_content() extracts and validates these before falling back to plain text. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Add routines web UI tab, update docs for sandbox-jobs branch Add full routines management to the web gateway (list, detail, trigger, toggle, delete) with 7 new API endpoints, response types, and frontend (HTML, JS, CSS). Update FEATURE_PARITY.md (~23 rows), CLAUDE.md (new subsystems, config, TODOs), and README.md (architecture diagram, features, components, fix onboard command). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: Bind Telegram bot to owner account during setup Without owner binding, anyone who discovers the bot can send it messages. The setup wizard now prompts the user to message their bot, captures their Telegram user ID via getUpdates, and persists it as telegram_owner_id in settings. On startup, the owner_id is injected into the WASM channel config so the existing owner restriction logic drops messages from non-owners. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Move settings from disk to PostgreSQL database Settings previously lived in three JSON files on disk (settings.json, mcp-servers.json, session.json). This made them inaccessible from the web UI and caused redundant disk reads (Settings::load() called 8+ times during startup). Now all settings live in a `settings` table (user_id + key -> JSONB) with only 4 bootstrap fields remaining on disk (database_url, pool size, secrets key source, onboard_completed) since they're needed before the DB connection exists. - Add V8 migration for settings table - Add BootstrapConfig (thin disk file) and Settings DB round-trip - Add Store CRUD methods for settings (get/set/delete/list/bulk) - Refactor Config to load from DB (env > DB > default cascade) - Add SessionManager DB persistence for session tokens - Add DB-backed MCP server config load/save functions - Add 6 settings web API endpoints (list/get/set/delete/export/import) - Add one-time disk-to-DB migration on first boot - Make CLI config commands async with DB access (disk fallback) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Seed workspace on boot, fix gateway duplicate logs and URL auto-auth - Add Workspace::seed_if_empty() to create core identity files (README, MEMORY, IDENTITY, SOUL, AGENTS, USER, HEARTBEAT) when missing, called on every boot without overwriting existing user edits - Remove duplicate gateway log lines from web/mod.rs (main.rs has the useful clickable ?token= URL) - Auto-authenticate from ?token= URL parameter in the web UI and strip the token from the address bar after successful auth Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: Harden sandbox security (path traversal + orchestrator auth) Two vulnerabilities fixed: 1. project_dir path traversal: The create_job tool let the LLM specify arbitrary host paths for Docker bind mounts. Removed project_dir from the tool schema entirely, and added canonicalization + prefix validation at both resolve_project_dir() and the job_manager bind mount point. 2. Orchestrator API auth bypass: worker_auth_middleware was defined but never applied. Each handler manually called validate_token(), so any new endpoint that forgot would be publicly accessible. Applied the middleware as route_layer on all /worker/ routes, removed manual auth from all 7 handlers. Bind to 127.0.0.1 on macOS/Windows (Linux keeps 0.0.0.0 since containers reach host via docker bridge, not loopback). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Rework gateway chat with pinned assistant, pagination, and NEAR AI response chaining Implements the 4-phase plan for overhauling the web gateway chat: - Phase 1: Pinned "Assistant" thread at top of sidebar, regular threads below - Phase 2: Cursor-based history pagination with infinite scroll - Phase 3: NEAR AI previous_response_id chaining (delta-only messages), with fallback to full history on chain errors, and DB persistence of chain state across restarts - Phase 4: SSE thread isolation (events filtered by thread_id) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: Add per-request HTTP timeout to WASM host, redact credentials in errors Three fixes for WASM channel reliability: 1. Per-request timeout: Add optional timeout-ms parameter to http-request in both channel and tool WIT interfaces. Telegram long-poll now specifies 35s (outliving the 30s server-side hold), while regular API calls use the 30s default. Fixes the triple-30s timeout race that caused polling failures. 2. Credential redaction: reqwest::Error includes the full URL (with injected bot tokens) in its Display output. Scrub credential values from error messages before logging or returning to WASM. 3. Webhook route registration: Remove tunnel URL gate so webhook routes are always available when webhook channels exist, not only when TUNNEL_URL is configured. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: Fix clippy warnings in WASM tools and channels - slack channel: allow dead_code on signing_secret_name (forward compat field) - gmail tool: use div_ceil() instead of manual (n+2)/3 - google-calendar tool: extract CreateEventParams/UpdateEventParams structs to fix too-many-arguments warnings Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Fix approval flow * fix: Rebuild bundled telegram.wasm with updated WIT interface The bundled WASM binary must match the host's WIT definition. Previous binary was compiled against the old 4-arg http-request; this rebuild includes the new timeout-ms parameter. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: Load WASM channels from disk instead of bundling in binary Remove include_bytes! embedding of telegram.wasm. Channels are now loaded from their build output directories (channels-src/<name>/target/) during onboarding, then from ~/.ironclaw/channels/ at runtime. - bundled.rs: locate_channel_artifacts() finds WASM + capabilities from build output; IRONCLAW_CHANNELS_SRC env var overrides the default path - available_channel_names(): only lists channels with build artifacts - bundled_channel_names(): lists all known channels (manifest) - Setup wizard uses available_channel_names() to offer installable channels - Add *.wasm to .gitignore, remove tracked telegram.wasm Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: Persist gateway auth token, fix thread hydration race, polish auth screen Three web gateway UX fixes: 1. Token persistence: Store auth token in sessionStorage so refreshing the page doesn't force re-authentication. Hide the auth screen immediately when a saved token exists to prevent flash. 2. Thread hydration: Remove the !msgs.is_empty() bail-out in maybe_hydrate_thread so that even brand-new (empty) assistant threads get hydrated with their correct DB UUID. Previously resolve_thread would mint a fresh UUID, causing messages to land in the wrong conversation and duplicate threads to appear. 3. Auth screen: Redesign as a centered card with brand, tagline, labeled input, and hint text. Also adds 34 new tests covering session/thread lifecycle, thread resolution isolation (user, channel, external ID), hydration edge cases, serialization round-trips, approval flows, and stale mapping recovery. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: Use bindgen! for WASM tool wrapper, add dev tool loading Three changes: 1. Rewrite src/tools/wasm/wrapper.rs to use wasmtime::component::bindgen! instead of manual linker.root().func_wrap(). This fixes the "component imports instance 'near:agent/host', but a matching implementation was not found in the linker" error. All 6 host functions (log, now-millis, workspace-read, http-request, secret-exists, tool-invoke) are now properly registered under the near:agent/host namespace. Also adds WASI support, credential injection, and leak detection for HTTP requests made by WASM tools. 2. Add dev tool loading to src/tools/wasm/loader.rs. During startup, the loader now also scans tools-src/*/target/wasm32-wasip2/release/ for build artifacts that are newer than installed copies. This means during development you just rebuild the WASM and restart the host; no manual copy step needed. Set IRONCLAW_TOOLS_SRC to override the source dir. 3. Wire up load_dev_tools() in main.rs alongside the existing load_from_dir() call. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: Wire main startup and CLI to use DB-backed settings main.rs now reloads Config from the database after connecting, attaches the store to the session manager for dual-write tokens, and loads MCP servers from DB instead of disk. ExtensionManager and MCP CLI commands use DB when available with disk fallback. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1 parent 6ed6ffc commit 7a9496b

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

99 files changed

+17271
-1338
lines changed

.dockerignore

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
target/
2+
.git/
3+
.env
4+
.env.*
5+
*.md
6+
!CLAUDE.md
7+
node_modules/
8+
tools-src/

.gitignore

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,3 +4,6 @@
44

55
target/
66

7+
# WASM build artifacts (loaded from disk, not bundled)
8+
*.wasm
9+

CLAUDE.md

Lines changed: 78 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -11,8 +11,13 @@
1111
- **Always available** - Multi-channel access with proactive background execution
1212

1313
### Features
14-
- **Multi-channel input**: TUI (Ratatui), HTTP webhooks, Telegram, WhatsApp, Slack (WASM channels)
14+
- **Multi-channel input**: TUI (Ratatui), HTTP webhooks, WASM channels (Telegram, Slack), web gateway
1515
- **Parallel job execution** with state machine and self-repair for stuck jobs
16+
- **Sandbox execution**: Docker container isolation with orchestrator/worker pattern
17+
- **Claude Code mode**: Delegate jobs to Claude CLI inside containers
18+
- **Routines**: Scheduled (cron) and reactive (event, webhook) task execution
19+
- **Web gateway**: Browser UI with SSE/WebSocket real-time streaming
20+
- **Extension management**: Install, auth, activate MCP/WASM extensions
1621
- **Extensible tools**: Built-in tools, WASM sandbox, MCP client, dynamic builder
1722
- **Persistent memory**: Workspace with hybrid search (FTS + vector via RRF)
1823
- **Prompt injection defense**: Sanitizer, validator, policy rules, leak detection
@@ -59,7 +64,9 @@ src/
5964
│ ├── context_monitor.rs # Memory pressure detection
6065
│ ├── undo.rs # Turn-based undo/redo with checkpoints
6166
│ ├── submission.rs # Submission parsing (undo, redo, compact, clear, etc.)
62-
│ └── task.rs # Sub-task execution framework
67+
│ ├── task.rs # Sub-task execution framework
68+
│ ├── routine.rs # Routine types (Trigger, Action, Guardrails)
69+
│ └── routine_engine.rs # Routine execution (cron ticker, event matcher)
6370
6471
├── channels/ # Multi-channel input
6572
│ ├── channel.rs # Channel trait, IncomingMessage, OutgoingResponse
@@ -72,8 +79,33 @@ src/
7279
│ │ ├── overlay.rs # Approval overlays
7380
│ │ └── composer.rs # Message composition
7481
│ ├── http.rs # HTTP webhook (axum) with secret validation
75-
│ ├── slack.rs # Stub
76-
│ └── telegram.rs # Stub
82+
│ ├── repl.rs # Simple REPL (for testing)
83+
│ ├── web/ # Web gateway (browser UI)
84+
│ │ ├── mod.rs # Gateway builder, startup
85+
│ │ ├── server.rs # Axum router, 40+ API endpoints
86+
│ │ ├── sse.rs # SSE broadcast manager
87+
│ │ ├── ws.rs # WebSocket gateway + connection tracking
88+
│ │ ├── types.rs # Request/response types, SseEvent enum
89+
│ │ ├── auth.rs # Bearer token auth middleware
90+
│ │ ├── log_layer.rs # Tracing layer for log streaming
91+
│ │ └── static/ # HTML, CSS, JS (single-page app)
92+
│ └── wasm/ # WASM channel runtime
93+
│ ├── mod.rs
94+
│ ├── bundled.rs # Bundled channel discovery
95+
│ └── wrapper.rs # Channel trait wrapper for WASM modules
96+
97+
├── orchestrator/ # Internal HTTP API for sandbox containers
98+
│ ├── mod.rs
99+
│ ├── api.rs # Axum endpoints (LLM proxy, events, prompts)
100+
│ ├── auth.rs # Per-job bearer token store
101+
│ └── job_manager.rs # Container lifecycle (create, stop, cleanup)
102+
103+
├── worker/ # Runs inside Docker containers
104+
│ ├── mod.rs
105+
│ ├── runtime.rs # Worker execution loop (tool calls, LLM)
106+
│ ├── claude_bridge.rs # Claude Code bridge (spawns claude CLI)
107+
│ ├── api.rs # HTTP client to orchestrator
108+
│ └── proxy_llm.rs # LlmProvider that proxies through orchestrator
77109
78110
├── safety/ # Prompt injection defense
79111
│ ├── sanitizer.rs # Pattern detection, content escaping
@@ -96,6 +128,9 @@ src/
96128
│ │ ├── file.rs # ReadFile, WriteFile, ListDir, ApplyPatch
97129
│ │ ├── shell.rs # Shell command execution
98130
│ │ ├── memory.rs # Memory tools (search, write, read, tree)
131+
│ │ ├── job.rs # CreateJob, ListJobs, JobStatus, CancelJob
132+
│ │ ├── routine.rs # routine_create/list/update/delete/history
133+
│ │ ├── extension_tools.rs # Extension install/auth/activate/remove
99134
│ │ └── marketplace.rs, ecommerce.rs, taskrabbit.rs, restaurant.rs (stubs)
100135
│ ├── builder/ # Dynamic tool building
101136
│ │ ├── core.rs # BuildRequirement, SoftwareType, Language
@@ -236,6 +271,30 @@ HEARTBEAT_ENABLED=true
236271
HEARTBEAT_INTERVAL_SECS=1800 # 30 minutes
237272
HEARTBEAT_NOTIFY_CHANNEL=tui
238273
HEARTBEAT_NOTIFY_USER=default
274+
275+
# Web gateway
276+
GATEWAY_ENABLED=true
277+
GATEWAY_HOST=127.0.0.1
278+
GATEWAY_PORT=3001
279+
GATEWAY_AUTH_TOKEN=changeme # Required for API access
280+
GATEWAY_USER_ID=default
281+
282+
# Docker sandbox
283+
SANDBOX_ENABLED=true
284+
SANDBOX_IMAGE=ironclaw-worker:latest
285+
SANDBOX_MEMORY_LIMIT_MB=512
286+
SANDBOX_TIMEOUT_SECS=1800
287+
288+
# Claude Code mode (runs inside sandbox containers)
289+
CLAUDE_CODE_ENABLED=false
290+
CLAUDE_CODE_MODEL=claude-sonnet-4-20250514
291+
CLAUDE_CODE_MAX_TURNS=50
292+
CLAUDE_CODE_CONFIG_DIR=/home/worker/.claude
293+
294+
# Routines (scheduled/reactive execution)
295+
ROUTINES_ENABLED=true
296+
ROUTINES_CRON_INTERVAL=60 # Tick interval in seconds
297+
ROUTINES_MAX_CONCURRENT=3
239298
```
240299

241300
### NEAR AI Provider
@@ -297,13 +356,14 @@ Key test patterns:
297356

298357
## Current Limitations / TODOs
299358

300-
1. **Slack/Telegram channels** - Stubs only, need implementation
301-
2. **Domain-specific tools** - `marketplace.rs`, `restaurant.rs`, `taskrabbit.rs`, `ecommerce.rs` return placeholder responses; need real API integrations
302-
3. **Integration tests** - Need testcontainers setup for PostgreSQL
303-
4. **MCP stdio transport** - Only HTTP transport implemented
304-
5. **WIT bindgen integration** - Auto-extract tool description/schema from WASM modules (stubbed)
305-
6. **Capability granting after tool build** - Built tools get empty capabilities; need UX for granting HTTP/secrets access
306-
7. **Tool versioning workflow** - No version tracking or rollback for dynamically built tools
359+
1. **Domain-specific tools** - `marketplace.rs`, `restaurant.rs`, `taskrabbit.rs`, `ecommerce.rs` return placeholder responses; need real API integrations
360+
2. **Integration tests** - Need testcontainers setup for PostgreSQL
361+
3. **MCP stdio transport** - Only HTTP transport implemented
362+
4. **WIT bindgen integration** - Auto-extract tool description/schema from WASM modules (stubbed)
363+
5. **Capability granting after tool build** - Built tools get empty capabilities; need UX for granting HTTP/secrets access
364+
6. **Tool versioning workflow** - No version tracking or rollback for dynamically built tools
365+
7. **Webhook trigger endpoint** - Routines webhook trigger not yet exposed in web gateway
366+
8. **Full channel status view** - Gateway status widget exists, but no per-channel connection dashboard
307367

308368
### Completed
309369

@@ -320,6 +380,13 @@ Key test patterns:
320380
-**Tool approval enforcement** - Tools with `requires_approval()` (shell, http, file write/patch, build_software) now gate execution, track auto-approved tools per session
321381
-**Tool definition refresh** - Tool definitions refreshed each iteration so newly built tools become visible in same session
322382
-**Worker tool call handling** - Uses `respond_with_tools()` to properly execute tool calls when `select_tools()` returns empty
383+
-**Gateway control plane** - Web gateway with 40+ API endpoints, SSE/WebSocket
384+
-**Web Control UI** - Browser-based dashboard with chat, memory, jobs, logs, extensions, routines
385+
-**Slack/Telegram channels** - Implemented as WASM tools
386+
-**Docker sandbox** - Orchestrator/worker containers with per-job auth
387+
-**Claude Code mode** - Delegate jobs to Claude CLI inside containers
388+
-**Routines system** - Cron, event, webhook, and manual triggers with guardrails
389+
-**Extension management** - Install, auth, activate MCP/WASM extensions via CLI and web UI
323390

324391
## Adding a New Tool
325392

Cargo.lock

Lines changed: 45 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

Cargo.toml

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -58,6 +58,9 @@ axum = { version = "0.8", features = ["ws"] }
5858
tower = "0.5"
5959
tower-http = { version = "0.6", features = ["trace", "cors"] }
6060

61+
# Cron scheduling for routines
62+
cron = "0.13"
63+
6164
# Safety/sanitization
6265
regex = "1"
6366
aho-corasick = "1"
@@ -99,6 +102,7 @@ hyper-util = { version = "0.1", features = ["server", "tokio", "http1", "http2"]
99102
http-body-util = "0.1"
100103
bytes = "1"
101104
base64 = "0.22.1"
105+
mime_guess = "2.0.5"
102106

103107
# macOS keychain
104108
[target.'cfg(target_os = "macos")'.dependencies]

Dockerfile.worker

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,63 @@
1+
# Multi-stage Dockerfile for the IronClaw worker container.
2+
#
3+
# This image runs the ironclaw binary in worker mode inside Docker containers.
4+
# The orchestrator creates instances of this image for sandboxed job execution.
5+
#
6+
# Build:
7+
# docker build -f Dockerfile.worker -t ironclaw-worker .
8+
#
9+
# The image includes common development tools so workers can build software,
10+
# run tests, and execute shell commands.
11+
12+
FROM rust:1.85-bookworm AS builder
13+
14+
WORKDIR /build
15+
COPY . .
16+
17+
# Build only the ironclaw binary (release mode)
18+
RUN cargo build --release --bin ironclaw
19+
20+
# ---
21+
22+
FROM debian:bookworm-slim
23+
24+
# Install common development tools
25+
RUN apt-get update && apt-get install -y --no-install-recommends \
26+
ca-certificates \
27+
curl \
28+
git \
29+
build-essential \
30+
pkg-config \
31+
libssl-dev \
32+
nodejs \
33+
npm \
34+
python3 \
35+
python3-pip \
36+
python3-venv \
37+
&& rm -rf /var/lib/apt/lists/*
38+
39+
# Install Rust toolchain for the sandbox user
40+
ENV RUSTUP_HOME=/usr/local/rustup \
41+
CARGO_HOME=/usr/local/cargo \
42+
PATH=/usr/local/cargo/bin:$PATH
43+
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain 1.85.0 \
44+
&& chmod -R a+r /usr/local/rustup /usr/local/cargo
45+
46+
# Install Claude Code CLI (for claude-bridge mode)
47+
RUN npm install -g @anthropic-ai/claude-code@latest
48+
49+
# Copy the binary
50+
COPY --from=builder /build/target/release/ironclaw /usr/local/bin/ironclaw
51+
52+
# Create non-root user (UID 1000 matches the orchestrator's container config)
53+
RUN useradd -m -u 1000 -s /bin/bash sandbox \
54+
&& mkdir -p /workspace \
55+
&& chown sandbox:sandbox /workspace \
56+
&& mkdir -p /home/sandbox/.claude \
57+
&& chown sandbox:sandbox /home/sandbox/.claude
58+
59+
USER sandbox
60+
WORKDIR /workspace
61+
62+
# The orchestrator passes the full command via Docker cmd.
63+
ENTRYPOINT ["ironclaw"]

0 commit comments

Comments
 (0)