Validates mTLS certs (PEM parsing, expiry), JWT public/private keys
(Ed25519 PEM with base64 support), and session secret (hex, 256-bit
minimum) when the corresponding auth strategies are configured.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Checks openssl, node, gh, and dot for presence, version, and command
success. Reports errors for missing/broken required tools and warnings
for optional ones. Also fixes pre-existing build break from
ApiAuthenticationStrategy -> ApiAuthStrategy rename.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Support mutual TLS as an authentication strategy alongside JWT.
The server accepts both auth methods on the same port — mTLS if a
client cert is presented, JWT via Bearer header otherwise.
Config changes:
- Replace `authentication_strategy` (singular) with
`authentication_strategies` (list of "jwt" and/or "mtls")
- Add `[api.tls]` section for cert, key, and CA paths
New files: tls.rs (rustls ServerConfig builder)
Modified: server_config.rs, jwt_auth.rs, serve.rs, lib.rs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Extract apply_live_result() helper to deduplicate connectivity-result
handling across check_api, check_web, and check_brave_search
- Merge probe_api/probe_web into single probe_url function
- Share one reqwest::Client across all HTTP probes
- Run LLM probes concurrently via futures::future::join_all instead of
sequential loop (saves wall-clock time with multiple providers)
- Compute daytona_configured once before the live/offline branch
- Move live flag from DoctorReport struct field to render() parameter
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Styles fields change from &'static str (raw ANSI escape codes) to
console::Style, removing unsafe Send/Sync impls and manual reset
handling. The console crate handles TTY detection and NO_COLOR natively.
Also adds live connectivity probes to arc doctor (--live flag).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Move auth config under [web.auth] in arc.toml to group web-specific
settings together. Add WebConfig with url field (default localhost:5173).
Add `arc doctor` command with checks for config, API, web, LLM providers,
Brave Search, sandbox, and GitHub App. Extract Provider::api_key_env_vars
and has_api_key to deduplicate validation logic.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add ANSI color to `arc models` and `arc models test` output when stdout
is a TTY: bold model IDs, dim provider/aliases, cyan speed, green/red
test results. Add `Styles::detect_stdout()` to arc-util.
Also fix pre-existing clippy warnings: derive Default instead of manual
impls for enums in server_config, remove unused FailureDetail imports
in arc-workflows error tests, inline print literal in test_models header.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Some deployment environments (e.g. container orchestrators) make it
easier to pass secrets as single-line base64 strings rather than
multi-line PEM. Both env vars now auto-detect the format: if the value
starts with "-----" it's treated as raw PEM, otherwise base64-decoded.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Standalone crate that reads devcontainer.json (with JSONC support), fetches
OCI Features via oras, and produces a resolved config containing a generated
Dockerfile, lifecycle hooks, environment variables, and forwarded ports.
Supports image, Dockerfile, and Docker Compose modes with devcontainer
variable substitution. No coupling to arc-workflows or DaytonaSandbox.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Create openapi/arc-api.yaml as source of truth for all API endpoints
- Add arc-types crate with build.rs using typify to generate Rust structs
from the spec's component schemas
- Refactor server.rs to use generated types instead of hand-written ones
- Add route coverage conformance test validating router matches spec
- Add openapi-typescript to arc-web for TypeScript type generation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Every emitted event now produces a structured tracing log line so
developers can debug after the fact via ~/.arc/logs/. Each event
variant gets an appropriate log level (info/debug/warn/error) with
structured fields. Streaming noise variants (TextDelta,
ToolCallOutputDelta) are no-ops, and wrapper variants (Agent,
ExecutionEnv on PipelineEvent) delegate to the inner event's trace.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tracing events (e.g. 13 calls in arc-mcp) were silently dropped because
no subscriber was configured. This adds a file-based tracing subscriber
that logs to ~/.arc/logs/YYYY-MM-DD.log with INFO as the default level,
controllable via the ARC_LOG env var.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduces durable storage so pipeline run data survives restarts.
The new arc-db crate provides SQLite connection helpers, a
PRAGMA user_version migration system, and a WorkflowRun model.
AppConfig (arc.toml) controls data_dir; the server initializes
the DB at startup and threads the pool through AppState.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move HTTP server (Axum routes, JWT auth, serve CLI command, server
config) from arc-workflows into a dedicated arc-api crate. This
improves separation — arc-workflows is a pipeline engine library,
not a web server.
- Create crates/arc-api with server.rs, jwt_auth.rs, serve.rs,
server_config.rs and their integration tests
- Remove server feature flag and optional deps from arc-workflows
- Update arc-cli to depend on arc-api for ServeArgs and serve_command
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Change GitCheckpointMode::Remote to Remote(PathBuf) so both variants
carry a repo path for MetadataStore shadow commits
- Unify init_run and shadow write logic to work with either Host or
Remote mode, eliminating Host-only gates
- Add trailers (Arc-Run, Arc-Completed, Arc-Checkpoint) to remote
checkpoint commits via write_file + git commit -F to avoid shell
escaping issues with multi-line messages
- Wire up meta_branch for Daytona in run.rs (was only set for worktree)
- Fix sandbox name collisions by adding random hex suffix
- Fix pre-existing build_router() test compilation errors from JWT auth
- Add E2E tests for Host shadow branch and Daytona shadow branch
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Ed25519 asymmetric JWT: arc-web signs with private key, arc-attractor verifies
with public key. Adds AuthenticatedService axum extractor to all routes, jose
dependency for TypeScript signing, and key generation script.
Startup behavior: ARC_JWT_PUBLIC_KEY set → enforce JWT auth; not set +
ARC_INSECURE_DISABLE_AUTHENTICATION=true → allow unauthenticated; neither →
refuse to start with clear error.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three separate binaries are replaced by a single `arc` CLI with subcommands:
arc llm prompt/models, arc agent, arc run, arc validate, arc serve
Extract public CLI modules (arc_llm::cli, arc_agent::cli::AgentArgs/run_with_args)
so the new arc-cli crate can dispatch to each library. Integration tests migrate
to crates/arc-cli/tests/cli.rs.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Git checkpoint commits (stage-level snapshots, diff.patch, GitCheckpoint
events) previously only ran for Local execution. This extends support to
Docker (bind-mount uses host git, same as Local) and Daytona (runs git
commands remotely via exec_command).
- Add GitCheckpointMode enum (Host/Remote) replacing RunConfig.work_dir
- Extract git_checkpoint_host/git_diff_host helpers from inline code
- Add git_checkpoint_remote/git_diff_remote using exec_command
- Enable git_clean check for Docker alongside Local
- Add setup_daytona_git to create run branch in remote sandbox
- Switch Daytona wrap_bash_command from quote-escaping to base64 encoding
(matches TypeScript/Python/Ruby Daytona SDKs, avoids nested quote issues)
- Add e2e tests for both Host mode and Remote mode (Daytona, live-tested)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Rename crate directories, package names, binary names, path
dependencies, use statements, qualified paths, clap command names,
and string literals across the workspace.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New `mcp` crate using rmcp v0.15.0 with stdio and HTTP transports.
MCP tools are registered as regular `RegisteredTool` instances in the
agent's `ToolRegistry`, sharing the same `execute_one_tool` path as
built-in tools. Tools are namespaced as `mcp__{server}__{tool}`.
Includes end-to-end test: real MCP server subprocess (Python echo
server) → mock LLM issues tool call → MCP bridge executes → result
flows back through the session loop.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
web_fetch now converts HTML responses to clean markdown using the htmd
crate (stripping script/style tags), and supports an optional prompt
parameter that makes a secondary LLM call to answer questions about the
fetched content. Each provider profile picks a cheap/fast summarizer
model (Haiku, gpt-4o-mini, gemini-2.0-flash).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the placeholder web_fetch tool with a working implementation
that executes curl within the execution environment, respecting
Docker/Daytona network sandboxing.
- Build curl command with shell-escaped URL, follow redirects, custom
user agent, and configurable timeout (default 30s, max 60s)
- Validate URL scheme (http/https only) to prevent misuse
- Truncate responses exceeding 100KB to protect context window
- Register web_fetch in Anthropic and OpenAI profiles (was Gemini-only)
- Add web_fetch guidance to all three profile system prompts
- Add captured_command to MockExecutionEnvironment for test assertions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the placeholder web_search tool with a real implementation backed
by the Brave Search API. Register it in all three profiles (Anthropic,
OpenAI, Gemini) so every provider has web search capability.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Merges two small utility crates into a single `util` crate to reduce
workspace clutter. No behavioral changes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update daytona-sdk-rust to 5d370099 which fixes multipart file upload
(upload_file was sending an empty form). Add E2E test that verifies
artifact pointers are rewritten and files uploaded to a live Daytona
sandbox.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the `--docker` boolean flag with `--execution-env <local|docker|daytona>`
to support three execution environments. The new `DaytonaExecutionEnvironment`
uses the Daytona cloud sandbox SDK to run agent tools remotely, auto-cloning the
current git repo into the sandbox via `gh auth token` credentials.
Setup commands from TOML task configs now run inside the execution environment
(via `exec_command` after `initialize()`) rather than locally, so they work
correctly for both Docker and Daytona sandboxes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Entire-Checkpoint: 306da8ff6de1
Support `attractor run task.toml` as an alternative to `.dot` files.
Auto-detects format by file extension. TOML bundles pipeline config
(graph path, model, setup commands, working directory) into a single
file with precedence: CLI flag > TOML > DOT graph attrs > defaults.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Entire-Checkpoint: 8744d57d6053
Apply redact::redact_jsonl_line at all three serialization sites so
secrets (AWS keys, GitHub PATs, private keys, etc.) are scrubbed
before reaching disk or the network.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Entire-Checkpoint: e23c92750cd9
Skills are markdown files with YAML frontmatter that define reusable
prompt templates (e.g., /commit, /review-pr). When a user references
/skill-name in their input, the skill template expands in place with
{{user_input}} receiving the remaining text.
- Add skills.rs with parse, expand, discover, and formatting functions
- Discover skills from ~/.attractor/skills/, <git-root>/.attractor/skills/,
and <git-root>/skills/ (overridable with --skills-dir CLI flag)
- Inject available skills into system prompt between project docs and
user instructions
- Expand skill references in session input before recording user turn
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Entire-Checkpoint: 2a8ed77f26c5
Layered library for blob/tree/commit/ref operations without touching
the working directory. Four modules: gitobj (primitives), branchstore
(key-value on a branch), snapshot (working dir captures), trailerlink
(commit message trailers). 56 tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Entire-Checkpoint: 1e40b3267885
Logs from `attractor run` were cluttering project directories. Now defaults
to ~/.attractor/logs/attractor-run-TIMESTAMP instead of ./attractor-run-TIMESTAMP.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The previous approach scanned LLM response text for JSON containing
routing fields (extract_status_fields), which was fragile and violated
the spec's abstraction boundary. Replace with two clean mechanisms:
- Backend registers a report_outcome tool that the LLM calls to declare
routing decisions (status, preferred_next_label, context_updates, etc.)
- Handler auto-generates a routing preamble listing available edge labels,
appended to the prompt only when 2+ labeled unconditional edges exist
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Test 1 (llm crate): Multi-turn cache verification runs 6 conversation turns
with a large system prompt (~5460 tokens) and verifies cache_read_tokens on
the final turn. Anthropic threshold 0.5, OpenAI/Gemini 0.0 (automatic
caching not guaranteed).
Test 2 (agent crate): Cross-provider parity matrix with 15 scenarios
(file CRUD, shell, grep/glob, editing, steering, reasoning effort, loop
detection, error recovery, etc.) across Anthropic, OpenAI, and Gemini.
41 total tests. Some scenarios excluded for OpenAI due to gpt-4o-mini
limitations (no reasoning.effort, is_error rejection, weak editing).
Test 3 (attractor crate): E2E pipeline with real LLM using AgentBackend,
AutoApproveInterviewer, and default_registry. Verifies pipeline success,
artifact files, goal gate outcomes, and checkpoint state.
All tests are #[ignore] and require API keys to run.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Thread CancellationToken into tool executors and exec_command so that
running processes are killed (SIGTERM -> 2s -> SIGKILL) when abort fires,
rather than only checking the flag between LLM calls. Key changes:
- ToolExecutor type gains CancellationToken parameter
- ExecutionEnvironment::exec_command gains cancel_token param
- LocalExecutionEnvironment uses tokio::select! (completion vs timeout
vs cancellation) with extracted sigterm_then_kill helper
- DockerExecutionEnvironment uses same select! pattern
- Session replaces Arc<AtomicBool> with CancellationToken, passes
child_token() per tool call
- Shell tool forwards cancel token to exec_command
- CLI SIGINT handler calls cancel_token.cancel()
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Interactive TTY sessions now use dialoguer widgets (Select, MultiSelect,
Confirm, Input) instead of raw eprintln/read_line. Non-TTY input falls
back to the existing line-based reader. Suppresses redundant "Stage
started" inform message for wait.human nodes since the prompt itself
serves as notification.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Drop event_tx from ManagedPipeline when pipeline completes/cancels/fails so
SSE streams end promptly instead of blocking until timeout (3.5s → 0.02s)
- Switch reqwest from native-tls to rustls-tls to avoid 500ms macOS cert store
load per process (0.67s → 0.005s per OpenAI adapter test)
- Replace hardcoded sleep(500ms)/sleep(200ms)/sleep(100ms) in server and
integration tests with 10ms poll loops (0.2-0.5s → 0.02-0.03s each)
- Add env_clear() to ullm prompt tests to prevent .env from triggering real
Anthropic API calls (0.45s → 0.15s)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implements ExecutionEnvironment trait backed by Docker containers via
bollard. Host working directory is bind-mounted; all file ops, commands,
grep, and glob execute inside the container via docker exec. Extracts
shared format_lines_numbered() helper from LocalExecutionEnvironment.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move ANSI Styles struct from agent/cli.rs into a shared terminal crate
so both binaries can use it. Add green and yellow color codes. Prettify
all attractor CLI output: bold headers, colored diagnostics by severity,
green/red status, yellow warnings, dimmed event details, and styled
interviewer prompts. Move pipeline status output from stdout to stderr.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The agent-cli binary was a thin wrapper over the agent library with
nothing else depending on it. Moving it into the agent crate as a
`pub mod cli` with a `[[bin]]` entry reduces workspace complexity
and follows the attractor crate pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduce `ToolApprovalFn` callback in `SessionConfig` to gate tool
execution by permission level. Create `agent-cli` crate as a thin CLI
binary wrapping `Session` with provider/model resolution, permission
model (read-only/read-write/full), interactive approval prompts,
real-time event rendering, debug middleware, and SIGINT handling.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
