1.9 KiB
summary, read_when
| summary | read_when | |||
|---|---|---|---|---|
| Debugging tools: watch mode, raw model streams, and tracing reasoning leakage |
|
Debugging
This page covers debugging helpers for streaming output, especially when a provider mixes reasoning into normal text.
Gateway watch mode
For fast iteration, run the gateway under the file watcher:
pnpm gateway:watch --force
This maps to:
tsx watch src/entry.ts gateway --force
Add any gateway CLI flags after gateway:watch and they will be passed through
on each restart.
Raw stream logging (Clawdbot)
Clawdbot can log the raw assistant stream before any filtering/formatting. This is the best way to see whether reasoning is arriving as plain text deltas (or as separate thinking blocks).
Enable it via CLI:
pnpm gateway:watch --force --raw-stream
Optional path override:
pnpm gateway:watch --force --raw-stream --raw-stream-path ~/.clawdbot/logs/raw-stream.jsonl
Equivalent env vars:
CLAWDBOT_RAW_STREAM=1
CLAWDBOT_RAW_STREAM_PATH=~/.clawdbot/logs/raw-stream.jsonl
Default file:
~/.clawdbot/logs/raw-stream.jsonl
Raw chunk logging (pi-mono)
To capture raw OpenAI-compat chunks before they are parsed into blocks, pi-mono exposes a separate logger:
PI_RAW_STREAM=1
Optional path:
PI_RAW_STREAM_PATH=~/.pi-mono/logs/raw-openai-completions.jsonl
Default file:
~/.pi-mono/logs/raw-openai-completions.jsonl
Note: this is only emitted by processes using pi-mono’s
openai-completionsprovider.
Safety notes
- Raw stream logs can include full prompts, tool output, and user data.
- Keep logs local and delete them after debugging.
- If you share logs, scrub secrets and PII first.