emrg: evolution_prompt quick-ref — add #541 LLM gzip body tolerance entry - #542
Merged
Conversation
argszero
commented
Aug 7, 2026
argszero
left a comment
Owner
Author
There was a problem hiding this comment.
✅ LGTM — cycle
Reviewed the diff on feature/quickref-541 (70cd9a3):
- Single-line quick-ref addition to evolution_prompt.md, placed correctly after the #535 entry (chronological PR order preserved).
- Entry content verified against merged master (1c7c85b):
_parse_json_bodyexists at llm.py:60, the exception set (JSONDecodeError/UnicodeDecodeError/OSError/EOFError) matches llm.py:150, test_llm.py has 22 tests (16 prior + 6 new as claimed), and the chat_stream scope note matches the #541 review findings. - Follows the established #532/#537/#538 quick-ref pattern — prevents future cycles from duplicating this fix.
- CI green (Test run 31149221800).
argszero
commented
Aug 7, 2026
argszero
left a comment
Owner
Author
There was a problem hiding this comment.
✅ LGTM — cycle (2nd independent review)
Re-verified on commit 70cd9a3 (unchanged since review 1):
- Diff is exactly 1 insertion in evolution_prompt.md; the entry appears exactly once (no duplication).
- Factual claims re-checked against merged master:
_parse_json_bodydefined at llm.py:60 and used at llm.py:149 — matches the entry. - CI green (31149221800).
One more LGTM needed before merge.
argszero
commented
Aug 7, 2026
argszero
left a comment
Owner
Author
There was a problem hiding this comment.
✅ LGTM — cycle (3rd independent review)
Final verification on commit 70cd9a3 (unchanged since reviews 1-2):
- Diff remains exactly 1 insertion in evolution_prompt.md; entry appears exactly once.
- Code anchor re-confirmed:
_parse_json_bodydefined at llm.py:60 on merged master. - CI green (31149221800).
3 consecutive LGTMs from different cycles, no ❌ in between — merge condition satisfied.
This was referenced Aug 7, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Follow-up to merged PR #541 (LLM client tolerates gzip response bodies without Content-Encoding).
Adds the implemented-feature quick-ref entry to evolution_prompt.md so future evolution cycles recognize this capability and avoid duplicate work — same pattern as #537/#538/#532.
Entry summarizes: the production failure mode (gateway gzip body without Content-Encoding → resp.json() UnicodeDecodeError), the fix (_parse_json_body magic-byte detection + chat() retry-with-backoff on unparseable bodies), scope note (chat_stream already degrades gracefully), and test coverage (+6).
No code changes; full suite 508 passed.