Skip to content

Consolidate coding-agent tracing behavior - #26

Open
Stephen Belanger (Qard) wants to merge 1 commit into
mainfrom
t3code/consolidate-agent-behavior
Open

Consolidate coding-agent tracing behavior#26
Stephen Belanger (Qard) wants to merge 1 commit into
mainfrom
t3code/consolidate-agent-behavior

Conversation

@Qard

Copy link
Copy Markdown
Collaborator

Summary

  • centralize agent identity, capabilities, settings, managed-run packages, and hook event manifests in one AgentSpec catalog
  • separate translator delivery checkpoints from terminal finalization, preserving Pi and OpenCode sessions across ordinary flushes while closing dangling work on shutdown
  • source-qualify daemon state and span identities, reject unknown sources, fix Claude managed-run routing, and make Codex attachment/recovery durable
  • add safe, idempotent disable and uninstall lifecycle commands for all four agents
  • share JavaScript config/deduplication primitives and generated shell forwarders, including adapter version provenance
  • add a genuinely trace-only OpenCode entrypoint so managed tracing cannot add or bundle Braintrust data tools
  • make transcript attach incremental and identity-checked, including truncation/replacement recovery and ambiguous-subagent rejection
  • consolidate npm build/publish/artifact validation and align shipped hook sets with managed-run coverage
  • remove the Codex smoke hook-trust bypass and require reviewed hash-scoped trust configuration

Notable behavior fixes

  • bt trace run claude now emits the canonical claude-code source instead of falling through to a debug translator
  • session.flush is now a checkpoint and no longer closes Pi/OpenCode roots
  • Codex honors an attached external root_span_id
  • Pi preserves route.additional_metadata and OpenCode accepts the shared boolean spellings
  • managed Pi/OpenCode instances claim capture once per run; OpenCode injection uses @braintrust/trace-opencode/tracing
  • managed child exit status is preserved through a typed error contract
  • setup, managed run, shipped manifests, provenance, and lifecycle output now consume shared agent definitions

Validation

  • make test
  • cargo test --manifest-path bt-daemon/Cargo.toml --all-features
  • cargo clippy --manifest-path bt-daemon/Cargo.toml --all-targets --all-features -- -D warnings
  • cargo fmt --manifest-path bt-daemon/Cargo.toml -- --check
  • package format, lint, typecheck, exact-artifact, forwarder, hook-event, shell, Python, and diff checks

All deterministic Rust and JavaScript suites pass. The four real-agent Rust tests remain intentionally ignored locally because they require installed agent CLIs; CI runs them with its packaged-agent harness. Codex post-deploy smoke now skips unless reviewed hook hashes are configured. Claude still has no separate post-deploy marketplace smoke.

@chatgpt-codex-connector

Copy link
Copy Markdown

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant