fix(parser): stop warning on normal observation responses (#2074)

Browse Source

parseSummary runs on every agent response, not just summary turns. When the
turn is a normal observation, the LLM correctly emits <observation> and no
<summary> — but the fallthrough branch from #1345 treated this as prompt
misbehavior and logged "prompt conditioning may need strengthening" every
time. That assumption stopped holding after #1633 refactored the caller to
always invoke parseSummary with a coerceFromObservation flag.

Gate the whole observation-on-summary path on coerceFromObservation. On a
real summary turn, coercion still runs and logs the legitimate "coercion
failed" warning when the response has no usable content. On an observation
turn, parseSummary returns null silently, which is the correct behavior.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

Alex Newman

2026-04-19 16:30:05 -07:00

committed by GitHub

parent e6e5751ef5

commit 2337997c48

4 changed files with 254 additions and 253 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

72

plugin/scripts/mcp-server.cjs

File diff suppressed because one or more lines are too long

382

plugin/scripts/worker-service.cjs

File diff suppressed because one or more lines are too long

22

plugin/ui/viewer-bundle.js

File diff suppressed because one or more lines are too long