Every PipelineEvent is now logged as a JSON envelope with timestamp,
run_id, and event fields — matching the Kilroy reference implementation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
LLM API calls should not have HTTP-level request or stream-read timeouts.
These are better controlled at the application level via TimeoutConfig
(total/per_step). The connect timeout is increased from 10s to 30s since
network conditions vary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Removed the workspace-level clippy lint config that enabled all, pedantic, nursery,
and cargo lint groups. Removed all #[allow(clippy::...)] annotations that were only
needed to suppress those extra lints, and fixed the few default clippy warnings that
were uncovered.
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>
Downstream nodes in multi-model pipelines reference response.<node_id>
context keys in their prompts. The codergen handler was only storing
last_response (truncated) and last_stage, so these references resolved
to nothing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Surface LLM token consumption and dollar cost at every verbosity level:
default mode appends per-stage tokens/cost, verbose modes include it in
event summary/detail, and the Pipeline Result section shows a total.
Cost is computed from the catalog pricing for Anthropic models; providers
without pricing (OpenAI, Gemini) show token counts only. Dry runs with
zero tokens omit the cost line entirely.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Use `status: "incomplete"` instead of `is_error` for OpenAI tool results (fixes rejection)
- Add merge_provider_options to forward unknown anthropic provider options to API body
- Derive Clone on Client to enable subagent session factory
- Enable error_recovery scenario for all providers now that OpenAI is fixed
- Improve subagent_spawn test to actually exercise spawn/wait/read workflow
- Adjust multi-turn cache test temperature to 0.5
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>
Show per-stage completion/failure timing and total pipeline duration
in the result block, even without -v flag. Uses a new
format_duration_human helper for human-readable durations (ms/s/m s).
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>
- Stylesheet: add bare-word Shape selector (specificity between Universal and Class)
- LLM: apply per_step timeout to connection and total timeout to stream (Section 4.7)
- Interviewer: add MultiSelect question type alongside MultipleChoice
- Session: move SessionStart/SessionEnd to initialize()/close(), deduplicate close logic
- Engine: return Ok(fail outcome) instead of error when goal gate unsatisfied with no retry_target
- Docker: mark Docker-dependent tests with #[ignore]
- Validation: add extensive unit test coverage for all rule types
- Integration: update tests to match engine/fidelity changes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Prevents tests from loading .env and making real API calls without
manipulating environment state.
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>
Add status, preferred_label, and suggested_next_ids fields to the
StageCompleted event so pipeline flow decisions are visible in CLI
output and the web UI, making it easier to debug why a pipeline
took a particular path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ParallelHandler and SubPipelineHandler needed Arc<HandlerRegistry> at
construction time but also lived inside the registry, creating a circular
dependency. The previous fix special-cased ParallelHandler as a separate
field on PipelineEngine with a resolve_handler() override.
Instead, add an EngineServices struct (registry + emitter) passed through
Handler::execute(). ParallelHandler and SubPipelineHandler become unit
structs that get what they need at execution time. No special-casing,
both register normally in default_registry() like every other handler.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The test criteria incorrectly said FAIL outcomes should be retried.
The pseudocode (Section 3.5) and the C reference implementation both
return immediately on FAIL. Only RETRY status triggers the retry loop.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The spec says "exactly one" exit node in the shape table (line 184),
exit handler docs (line 648), and test criteria (line 1834). The lint
rule table (line 1437) says "at least one" but is the minority. The
previous commit incorrectly reverted this — the terminal node change
was not causing the test failures (all three were from retry-on-Fail).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Revert two incorrect behavioral changes introduced in ceaa9bf:
1. StageStatus::Fail must return immediately, not retry. Fail is a
deliberate routing outcome (e.g. to take a "fail" edge). Retrying it
caused conditional_branching and manager_loop tests to hang.
2. Pipelines can legitimately have multiple terminal nodes. The
"exactly one" constraint broke branching_loop_back_on_failure.
Restore "at least one" validation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The parallel handler was never registered in default_registry() due to a
circular dependency (ParallelHandler::new needs Arc<HandlerRegistry>).
Break the cycle by storing ParallelHandler as a separate field on
PipelineEngine, created after Arc-wrapping the registry and emitter.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Break out of streaming loop on abort and drop the stream before emitting
SessionEnd to properly cancel the HTTP connection
- Emit ToolCallOutputDelta events for tool call results in both sequential
and parallel execution paths
- Retry on StageStatus::Fail in addition to Retry in pipeline engine
- Set preferred_label on WaitHumanHandler choice outcomes
- Enforce exactly one terminal node in pipeline validation
- Downgrade unreachable node diagnostic from Error to Warning
- Update context window test to match 1M token limit
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Strip the CWD prefix from string arguments in format_tool_args so tool
call output shows relative paths instead of absolute ones.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The Anthropic streaming API sends thinking block signatures via a
signature_delta event, not in content_block_start or content_block_stop.
The parser was ignoring this event type, falling back to the empty
placeholder signature from content_block_start, causing "Invalid
signature in thinking block" errors on multi-turn conversations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The Anthropic API requires a `signature` field on thinking blocks when
they are sent back in conversation history. Previously, thinking blocks
were stored as plain text in Turn::Assistant.reasoning, losing the
signature. Now Thinking/RedactedThinking content parts are preserved
in provider_parts (which retains signatures), and the lossy
reconstruction path is skipped when provider_parts already contains
thinking blocks.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When CodergenHandler receives CodergenResult::Text, it now extracts
preferred_next_label, suggested_next_ids, and context_updates from
the last JSON object in the response. This enables edge selection
via condition matching and preferred label instead of always falling
through to unconditional edges.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Switch default model from claude-sonnet-4-5 to claude-opus-4-6 across
run and serve commands. Enable the 1M token context window via the
context-1m-2025-08-07 beta header for opus-4-6 requests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Updates the default Gemini model from gemini-3-pro-preview to
gemini-3.1-pro-preview across agent, attractor, and ullm CLIs.
Adds "Using model:" output to stderr in both agent and ullm CLIs
so users can see which model is being used.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bun-based React app with pipeline dashboard UI including event log,
graph view, context/checkpoint panels, question panel, and status bar.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Updates the default Anthropic model from claude-sonnet-4-5 to
claude-opus-4-6 and replaces beta headers with adaptive thinking
provider options for 4.6 models.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When --docker is passed, agent tools execute inside a Docker container
via DockerExecutionEnvironment instead of running on the host. The host
working directory is bind-mounted into the container at /workspace.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a list endpoint that returns all in-memory pipelines with their
status, and a "Recent Pipelines" section in the start form that polls
every 3s so users can navigate to any pipeline started since server launch.
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>
ApiQuestion now includes options and allow_freeform fields so API clients
can render multiple-choice questions. submit_answer accepts an optional
selected_option_key to produce AnswerValue::Selected instead of always
creating AnswerValue::Text.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Long Opus responses hit the 120s request timeout with complete(). With
stream(), the request timeout only covers initial connection + first
chunk, then the 30s stream_read timeout guards against stalls between
chunks. Also emits AssistantTextDelta events during streaming.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The handler was converting all backend errors into Ok(Outcome::fail(...)),
which the engine treats as a terminal result. Retryable errors (timeouts,
network failures) are now propagated as Err so the engine retry loop kicks in.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Requests were always sent with max_tokens: None, which defaulted to
4096 in the Anthropic provider, causing large outputs to be truncated.
Now build_request() looks up the model's max_output from the catalog
and passes it through, giving each model its full output capacity.
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>
Add a Styles struct that pre-resolves ANSI escape codes based on whether
stderr is a TTY. Tool calls show as "● tool_name(args)" with bold+cyan
names, errors use red "✗", summaries are dimmed, and debug/verbose
middleware output is styled. No ANSI codes emitted when piped.
Also passes tool call arguments through to EventData::ToolCall so the
event handler can format them inline.
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>
