OpenAI requires max_output_tokens >= 16, and slower providers like
Gemini Pro need more than 10s to respond.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Update CLI tests for restructured commands (models → top-level, run → run start)
- Remove sync-related tests (command was removed)
- Fix clone_on_copy clippy warnings in arc-api server
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace openapi-typescript types-only output with a full TypeScript Axios
client generated by openapi-generator-cli. The generated code is committed
so IDE support works without running codegen. arc-web consumes the client
via bun workspaces.
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>
- Add `labels: HashMap<String, String>` to RunConfig, written to manifest.json
- Add `--label KEY=VALUE` flag to `arc run` (repeatable)
- New `arc runs` command: list pipeline runs with table or --json output
- New `arc runs prune` command: delete old runs with --before, --pipeline,
--label, --orphans filters (dry-run by default, --yes to confirm)
- 13 new tests covering scan_runs, filter_runs, prune, and manifest labels
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The existing gradient logo (#c4dede-#495669) was designed for dark
backgrounds. Adds logotype-light.svg with the same paths but a
deeper gradient (#2a6b6b-#1c2a3a) for better contrast on white,
and swaps the src based on the current theme.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
A background tokio task polls EventEmitter.last_event_at(). When idle
time exceeds the graph-level stall_timeout (default 600s), it cancels
a CancellationToken that races against execute_with_retry via
tokio::select!, dropping the hung handler future.
- EventEmitter: AtomicI64 last_event_at field, touch() to seed, emit()
auto-updates
- Graph::stall_timeout(): reads Duration attr, defaults 600s, None for 0
- StallWatchdogTimeout event variant with warn-level trace()
- Engine: watchdog spawn before main loop, select! at handler call,
shutdown after loop
- CLI: format arms for summary and detail views
- Unit tests for emitter, graph accessor, event serialization, and
engine watchdog behavior (hung, keepalive, disabled)
- E2e integration tests: DOT-parsed pipelines with 100-200ms stall
timeouts verifying trigger, keepalive, disable, and timing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update logging strategy to explain that event enums have trace()
methods called automatically at emit sites, and that wrapper
variants are no-ops to prevent double-logging.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Inner events are already traced at origin by the sub-agent's own
EventEmitter, so the SubAgentEvent wrapper should not re-trace them.
This matches the pattern used by PipelineEvent::Agent and
PipelineEvent::ExecutionEnv.
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>
SdkError now produces hand-crafted signature hints (e.g.
"api_deterministic|openai|authentication") that are identical regardless
of error message wording, replacing fragile regex-normalized signatures
for API errors. ArcError.to_fail_outcome() centralizes fail outcome
construction with failure_class and failure_signature context_updates.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The .light CSS variable overrides were defined before the :root dark
defaults, so equal-specificity source-order caused the dark values to
always win. Move .light overrides after each :root block so they
correctly take effect.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Guard loop_restart edges to only allow transient_infra failures, matching
Kilroy's behavior. Non-transient failures (deterministic, structural,
budget_exhausted, canceled, compilation_loop) are now blocked immediately
instead of getting restart attempts before the circuit breaker fires.
Fix normalize_failure_reason truncation to use floor_char_boundary(240)
instead of a raw byte slice, preventing panics on multi-byte UTF-8 chars.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
max_node_visits used > while signature circuit breakers used >=, creating
an inconsistency where "limit" meant different things depending on the
mechanism. Kilroy uses >= for all three checks. This aligns Arc to match.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Defines structured logging conventions for the team: level guidelines
(INFO for production, DEBUG for on-demand investigation), structured
field patterns, and per-crate examples.
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>
Introduce semantic CSS custom properties (page, panel, fg, line, overlay,
etc.) that swap values via .light/.dark class on <html>. An inline script
reads localStorage / prefers-color-scheme before first paint to prevent
flash-of-wrong-theme.
- ThemeProvider + useTheme hook in app/lib/theme.tsx
- Sun/Moon toggle in desktop nav and mobile menu
- .light overrides for all semantic tokens, accent colors (WCAG AA on
white), atmosphere gradient, @pierre/diffs surfaces, and chart variables
- Migrated ~30 files from hardcoded color classes to semantic tokens
- GraphViz diagrams use getGraphTheme() for light/dark hex maps
- Chart gridlines and axis labels use CSS custom properties
- Workflow card colors reference CSS vars for automatic theme switching
- Pierre diffs switch between pierre-dark and pierre-light themes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Inject per-file toggle controls into the Pierre diff header bar via
renderHeaderMetadata. Each file gets independent split/unified and
background on/off state using the Pierre icon style.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add wall_clock_timeout field to SessionConfig that spawns a tokio timer
to cancel the session after a duration, reusing existing Aborted path
- Set 120s wall-clock timeout on retro agent to prevent unbounded runs
- Replace silent `let _ =` with logged warnings for checkpoint load and
retro save failures
- Reuse LLM client from initial from_env() call instead of creating a
second one for the retro agent
- Extract retro generation into generate_retro() helper and call it from
both run_command and run_from_branch (resume path)
- Tolerate mutex poisoning in retro agent with unwrap_or_else
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Hover any line in a diff hunk to see a "Steer" button on the right side.
Clicking opens an inline comment form; submitted comments persist as
read-only annotations. Uses onLineEnter/onLineLeave with absolute overlay
positioning to place the button at the row's right edge.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add git_cmd() helper disabling maintenance.auto and gc.auto on all
host-side git commands; add GIT_REMOTE constant for remote commands
- Use --force on branch creation for idempotent retry/resume
- Add replace_worktree() that does best-effort remove before add
- Add reset_hard() after parallel worktree setup for deterministic state
- Add sanitize_ref_component() to clean node IDs in branch names
- Add git_replace_worktree_remote() for remote sandbox environments
- Add tests for sanitize_ref_component, replace_worktree, reset_hard
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Verifications catalog (/verifications) shows all verification criteria
organized by category with search, mode filter, and grouped/list toggle.
Each criterion has a unique icon, type badge, mode badge, and evaluation
sparkline. List view adds F1 accuracy, pass@1, and category columns.
Per-run verifications tab (/runs/:id/verifications) shows the same
criteria with pass/fail status for a specific run.
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>
Instead of skipping the retro agent entirely in dry-run, use a
placeholder narrative so derive → apply_narrative → save all run.
This catches bugs in the merge/persistence path without LLM calls.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
After each pipeline run, auto-derive stats from the checkpoint (stages,
retries, cost, files touched) then run an Opus agent session that
explores progress.ndjson to produce qualitative analysis: smoothness
rating, intent, outcome, learnings, friction points, and open items.
Backend:
- retro.rs: data model, save/load, derive_retro(), extract_stage_durations()
- retro_agent.rs: post-pipeline agent session with submit_retro tool
- cli/run.rs: hook retro generation after final.json, before engine_result?
- server.rs: GET /pipelines/{id}/retro endpoint, auto-derive on completion
Frontend:
- data/retros.ts: TS types + mock data + smoothness color config
- routes/retros.tsx: list page with smoothness badges
- routes/run-retro.tsx: detail view (stats, intent, stages, learnings)
- routes.ts + run-detail.tsx: wire up retro route and tab
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Populated input/output cost per million tokens for OpenAI, Gemini,
Kimi, ZAI, MiniMax, and Inception models based on current public
API pricing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a toolbar above the diffs with a checkpoint dropdown (defaulting
to "All changes"), a GitHub-style +/- diff stat indicator with colored
blocks, and a settings cog button.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace CSS @keyframes animation with native SVG <animate> elements
for the pulsing glow on running nodes. CSS animations on SVG
presentation attributes (fill, stroke) are unreliable across browsers.
SVG SMIL animations work consistently in Chrome, Safari, and Firefox.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace DOT source code view with rendered SVG visualization using
viz.js. Running stages pulse with a teal glow animation, completed
stages are tinted green, and the graph supports pan/zoom/direction
controls matching the workflow diagram page.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add search bar and smoothness dropdown filter to retros list
- Replace Cost column with Frictions count on retros list
- Make retro table rows fully clickable
- Move Retro tab before Usage tab in run detail
- Move Stage Breakdown below Open Items on retro page
- Add per-model breakdown table to usage page with 3 models
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Parallel branches now get isolated git worktrees so concurrent file
writes don't collide. Works across Local, Docker (bind-mount), and
Daytona (remote exec_command) environments.
Key changes:
- git.rs: add create_branch_at() and merge_ff_only() helpers
- engine.rs: add GitState struct, remote worktree helpers
(git_create_branch_at_remote, git_add_worktree_remote, etc.)
- handler/mod.rs: add git_state field to EngineServices (RwLock)
- handler/parallel.rs: WorktreeEnv wrapper, per-branch worktree
setup/teardown, checkpoint commits per branch, ff-merge winner
before returning to engine
- handler/fan_in.rs: ff-merge to winner's HEAD, set best_head_sha
- E2E tests for Host (local) and Daytona (remote) modes
When git_state is None, behavior is unchanged.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Prevents truncation of large tool calls (e.g. write_file with big
content) when neither agent config nor model catalog provides a value.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Convert insights route to a parent layout with sidebar and two children:
- index route (insights-editor) with the existing SQL editor
- /insights/new with LLM input, template cards, and SQL link
Also fix wide layout detection in app-shell to check all matched routes
instead of only the last match.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
LLM-authored output can set failure_class to non-canonical strings like
"retryable", "transient", or "permanent". Expand FromStr to accept 30+
aliases with case-insensitive trimmed matching, matching Kilroy's
normalizedFailureClass(). Unknown values fail-closed to Deterministic
instead of returning Err.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
SQL query editor with line numbers, saved queries sidebar, history,
SQL AI dialog, chart/table results toggle, and query stats bar.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Absolute `cd` paths in shell commands (script/tool_command attributes) silently
override the engine's worktree CWD, breaking portability across machines,
containers, and worktrees. Ported from kilroy (danshapiro/kilroy d9c1fec).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix 4 test failures: add unconditional fallback edges to branching.dot
and conditions.dot to satisfy all_conditional_edges validation rule
- Fix clippy await_holding_lock: scope MutexGuard before await in
daytona_integration.rs
- Fix clippy unnecessary_get_then_check: use contains_key in script.rs
- Fix clippy expect_fun_call: use unwrap_or_else in integration.rs
- Run cargo fmt across entire workspace
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add 8 missing transient_infra patterns (crates.io registry, toolchain,
cross-device link errors), 2 structural hints (write_scope_violation
variants), and reorder heuristic priority to check transient_infra
before budget_exhausted to match Kilroy's classification behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Raise the Anthropic adapter fallback from 4096 to 16384 to prevent
truncation of large tool call JSON when the model isn't in the catalog.
Add max_tokens as a configurable DOT node attribute that flows through
SessionConfig to LLM requests, following the same pattern as
reasoning_effort. Priority: node attribute > catalog > provider default.
Ported from kilroy (danshapiro/kilroy) commits 99a5cd7 and 78fadad.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace simple CI dot indicators with rich check status data model
(CheckRun[] with per-check name, status, duration). Cards in Verify
and Merge columns show a full-width expandable status row with summary
icon and text. Clicking reveals individual check results. Pending
column cards now display the human-in-the-loop question above the
Answer Question button.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extract hint patterns into const arrays (TRANSIENT_INFRA_HINTS,
BUDGET_EXHAUSTED_HINTS, STRUCTURAL_HINTS) and add 28 new patterns
from Kilroy to prevent transient/budget failures from misclassifying
as deterministic. Add comprehensive regression test per pattern plus
count-guard tests to catch accidental additions/removals.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- AttractorError → ArcError across 30 source files
- .attractor/ → .arc/ for artifacts and skills paths
- ATTRACTOR_NODE_ID → ARC_NODE_ID env var
- attractor-rust → arc in Cargo.toml repository URLs
- attractor-spec.md → arc-spec.md with content updates
- Update server banner, test comments, README examples, and docs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
