Subagent lines (▸ subagent[...], ✓ subagent[...]) now render at 8-space
indent instead of 6, visually distinguishing them as children of the stage.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Wire up cancel_token in ExeSandbox::exec_command via tokio::select!
- Clone the local git repo into exe.dev VMs after initialization
- Add GitCredentialSandbox decorator for push credential refresh
- Enable GitCheckpointMode::Remote for exe.dev (rename daytona_* → remote_*)
- Rename setup_daytona_git → setup_remote_git (already sandbox-agnostic)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace `.filter(..).next_back()` with `.rfind(..)` to satisfy the
expanded `clippy::filter_next` lint on newer toolchains.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The opt-in change (7400a9d5) left these two tests with empty asset_globs,
which now means "no asset collection". Add the matching glob so the tests
actually exercise asset collection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Asset collection previously ran a full `find` scan before and after every
stage (~30s per scan), even when no assets were needed. This makes it
opt-in: only workflows with an `[assets] include = [...]` section in their
TOML config will run asset collection, and only with user-specified globs.
- Add AssetsConfig struct and wire through WorkflowRunConfig, RunDefaults,
and RunConfig
- Remove baseline snapshot approach; single post-execution scan using
user globs filtered by mtime and size budgets
- Delete hardcoded pattern constants, is_asset_candidate, matches_simple_glob,
FileFingerprint, and snapshot() — replaced by configurable globs
- Skip all asset work when asset_globs is empty (zero overhead default)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enrich Outcome with stage duration, Checkpoint with persisted node visit
counts (avoiding fragile reconstruction on resume), and Manifest with the
base branch name for offline analysis without git lookups.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The full failure message (including entire stdout/stderr) was shown inline,
making terminal output very noisy. Now only the last non-empty line is
displayed, truncated to 120 chars. The full error remains in the log file.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Embeds the ULID run_id directly in the directory name so logs dirs
can be easily correlated with runs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
CommandHandler was using tokio::process::Command to execute scripts
directly on the host machine, completely bypassing the configured
sandbox (local, Daytona, Docker). This meant script nodes in workflows
ran on the host while agent nodes ran in the sandbox, causing fix cycles
where agents edited files in the sandbox but lint checks ran on the host.
Now delegates to services.sandbox.exec_command() so all node types
execute in the same environment.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add GitCheckpointFailed variant to WorkflowRunEvent with node_id and error fields
- Add trace() arm at ERROR level per logging strategy (operation cannot continue)
- Add rename_fields rule to default node_label from node_id
- Emit the event before returning ArcError::Engine on checkpoint failure
- Update events-strategy.md with the new event in the checkpoints table
- Add rename_fields serialization test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The git checkpoint functions (host and remote) now return Result<String, String>
with descriptive error messages instead of Option<String>. When a checkpoint commit
fails, the engine returns ArcError::Engine with FailureClass::Deterministic,
stopping the run immediately. This prevents stuck cycles where an agent's edits
are silently lost between node transitions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Generate the run ULID early and display it before the logs directory,
then pass it into setup_worktree and setup_daytona_git instead of each
generating their own.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The Claude CLI native binary install was getting OOM-killed (exit 137)
in the default 1 GiB sandbox. Using the daytona-medium default snapshot
also pre-includes Node, making the prereq install step a no-op.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Codex CLI no longer reads OPENAI_API_KEY from the environment at
runtime. It requires `codex login --with-api-key` to store credentials
via its auth system. Add a login step after ensure_cli for codex.
Also pass API keys via exec_command's env_vars parameter as belt-and-
suspenders alongside the env file, to avoid fs-to-process race conditions
in the Daytona sandbox.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Use `cat file | command` instead of `command < file` for stdin piping
to avoid redirect issues in nested shell wrappers
- Include both stdout and stderr in error messages when CLI exits non-zero
(previously only showed stderr, hiding API errors in stdout)
- Install Node 20 via nodesource + bash/curl as prerequisites for CLI tests
- Use bash instead of sh for Claude CLI install script
The codex test still fails with 401 Unauthorized — the OPENAI_API_KEY
env var isn't reaching the codex process in the sandbox despite the env
file being sourced correctly (gemini works with the same mechanism).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Pass GitHub App credentials in create_env() and daytona_snapshot_sandbox
so private repo clones succeed
- Install git in sandbox before running git CLI in clone_private_repo test
- Use brynary/arc (where app is installed) instead of rust-lang/rust for
clone_public_repo_gets_credentials test
- Fix git_checkpoint_remote_emits_events assertion: expect 1 event (work
node only) since start is skipped and exit breaks before checkpoint
- Install Node 20 via nodesource and bash/curl in CLI test prerequisites
- Use bash instead of sh for Claude CLI install script
- Shorten toolbox_idle_diagnostic sleep durations to finish in ~12s
- Add nextest config with 120s per-test timeout
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Anthropic max_tokens: use model catalog limit instead of hardcoded 65536,
fixing claude-sonnet-4-5 (max_output=64000) API errors
- OCI feature tgz: detect actual filename from registry instead of
assuming devcontainer-feature.tgz (registries use suffixed names)
- Test LlmCodergenBackend: implement one_shot() for prompt handler support
- Quarantine all Inception/mercury-2 parity matrix tests (unreliable provider)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The pattern of filtering Error-severity diagnostics, collecting messages,
and returning ArcError::Validation appeared in three places. Extract it
into validation::raise_on_errors and use prepare_from_file in run_from_branch.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
FileInliningTransform was treated as a "custom" transform that every
caller had to remember to register manually. This caused arc validate
to break and left latent bugs in run_from_branch and SubWorkflowHandler.
Add prepare_with_file_inlining() and prepare_from_file() to WorkflowBuilder
so file inlining is a built-in concern. Rename prepare_workflow to
prepare_from_source for clarity. Fix the SubWorkflowHandler to use
prepare_from_file when reading from stack.child_dotfile paths.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Register FileInliningTransform in validate_command so @file references
(e.g. @prompts/simplify.md) are resolved during validation, matching
the behavior in run.rs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The missing_required_fields test was not updated when goal was changed
from String to Option<String> in c143d2c8.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Precedence: CLI --goal > TOML goal > DOT graph attribute. Previously
the TOML goal field was required but never applied to the graph.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Rust 1.94.0 introduced new clippy lints and rustls now rejects X.509 v1
certificates. This fixes all three CI jobs:
- Format: cargo fmt across the workspace
- Clippy: unnecessary_unwrap, useless_format, derivable_impls,
type_complexity, too_many_arguments, redundant_closure, map_or
simplification, and other new lints
- Tests: generate v3 certs (with extensions) for mTLS tests so newer
rustls accepts them
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The Run: line was using raw eprintln! without indentation or dimming,
making it visually inconsistent with the Logs: and Sandbox: lines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tests were failing locally because the Daytona sandbox needs GitHub App credentials to clone a private repository, but the exec tests were passing . This updates the tests to load the credentials and supply them during initialization.
A stalled Anthropic SSE stream caused a run to hang for 10 minutes
until the stall watchdog killed it. The HTTP connection succeeded but
no SSE events arrived, and with stream_read_timeout defaulting to None
the read blocked indefinitely.
- Set AdapterTimeout default stream_read to 300s (5 min), matching
the idle timeout used by OpenAI Codex
- Increase BackoffConfig default initial_delay_ms from 200ms to 5s
so transient LLM failures get meaningful recovery time before retry
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds two new tests to the Daytona integration suite:
1. `daytona_exec_command_cancelled`: verifies that an active token cancellation properly aborts a running command and yields a correct exit code/message.
2. `daytona_exec_command_local_timeout`: tests the recent fix that prevents commands from hanging indefinitely by enforcing a local timeout fallback.
The Daytona SDK HTTP client can sometimes hang indefinitely if the connection
drops or the server stops responding. Since `daytona_sandbox.rs` was awaiting
the `execute_command` call directly, this could cause the entire workflow engine
to stall, eventually triggering the stall watchdog.
This wraps the `execute_command` call in a `tokio::select!` block, enforcing
the requested `timeout_ms` locally (with a 5s grace period) and respecting
the `cancel_token`.
Co-Authored-By: Gemini CLI <noreply@google.com>
The start node is a no-op (StartHandler returns success immediately), so its
git checkpoint commit is always empty. Skipping it reduces noise in git history
without losing any data — the checkpoint JSON is still saved to disk, and the
next node's diff falls back to base_sha correctly.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Extract repeated `tool_calls.back().map_or(&spinner, |e| &e.bar)` into
`ActiveStage::last_bar()` (used in 4 places)
- Clean up existing compaction_bar before overwriting in CompactionStarted
- Tidy CompactionCompleted handler to inline the if-let chain
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Unresolved @file references in node prompts or graph goals silently
passed through as literal text. Now caught at validation time with
a clear error and fix hint.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The compaction progress bar was stored as a single global field on
ProgressUI, which meant parallel stages could clobber each other's
compaction bar. Move it into ActiveStage so each stage tracks its own.
Also clean up compaction_bar in finish_stage to prevent stale spinners.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
resolve_file_ref now expands tilde via dirs::home_dir() and uses
canonicalize() to resolve .., symlinks, and verify existence in one step.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Compaction events were previously only shown with `-v`. Since compaction
takes time and changes agent behavior, display a spinning progress bar
on CompactionStarted and a summary line on CompactionCompleted regardless
of verbose mode.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
