debug-symphony

Solid

Investigate stuck runs and execution failures by tracing Symphony, Pi runner, and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.

Code & Development 61 stars 6 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
60
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Debug ## Goals - Find why a run is stuck, retrying, or failing. - Correlate tracker issue identity to a Pi or Codex session quickly. - Read the right logs in the right order to isolate root cause across the primary Pi path and the explicit Codex app-server continuity path. ## Log Sources - Primary runtime log file: `<logs-root>/log/symphony.log` - When Symphony runs with `--logs-root` or `SYMPHONY_LOG_ROOT`, it writes rotating JSON logs under this path (see `apps/symphony/README.md`). - Includes orchestrator, agent runner, Pi RPC bridge, and Codex app-server lifecycle logs. - Rotated runtime logs: `<logs-root>/log/symphony.log*` - Check these when the relevant run is older than the active file. - Stdout fallback: structured JSON log stream - Without `--logs-root`/`SYMPHONY_LOG_ROOT`, TUI mode suppresses stdout logs; use `--no-tui` to stream structured logs to stdout. ## Correlation Keys - `issue_identifier`: human ticket key (example: `MT-625`) - `issue_id`: tracker internal ID (stable backend identifier) - `session_id`: agent session identifier. For the Pi runner this is the stable session ID returned by pi RPC. For the Codex backend this is the Codex thread-turn pair (`<thread_id>-<turn_id>`). - `agent.backend` / config backend: `kata-cli` (aliases: `kata`, `pi`) is the primary/default Pi path; `codex` is the explicit Codex app-server path. These fields are emitted by Symphony runtime lifecycle logs (notably in `apps/symphony/src/orchest...

Details

Author
gannonh
Repository
gannonh/kata-symphony
Created
5 months ago
Last Updated
3 days ago
Language
Rust
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category