fix: exclude gpt-5.4-mini from reasoning_effort in /v1/chat/completions#76326
Closed
chinar-amrutkar wants to merge 4 commits into
Closed
fix: exclude gpt-5.4-mini from reasoning_effort in /v1/chat/completions#76326chinar-amrutkar wants to merge 4 commits into
chinar-amrutkar wants to merge 4 commits into
Conversation
Distinct WhatsApp contacts were colliding on the same :main session key,
causing shared .jsonl files and interleaved model context.
- Added dmScopeOverride to ResolveAgentRouteInput so callers can force a
specific dmScope regardless of the global config setting
- WhatsApp now passes dmScopeOverride: "per-channel-peer" when resolving
inbound routes, producing session keys of the form
agent:{agentId}:whatsapp:direct:{peerId}
- Added regression test verifying distinct peerId values produce distinct
route.sessionKey values
Closes openclaw#76263
Contributor
|
Codex review: needs changes before merge. Summary Reproducibility: yes. The linked OpenAI bug is source-reproducible because current main resolves Next step before merge Security Review findings
Review detailsBest possible solution: Keep the endpoint-scoped OpenAI fix, preserve documented WhatsApp account-level DM isolation, and either split the unrelated WhatsApp work or cover it with matching tests/docs/changelog before merge. Do we have a high-confidence way to reproduce the issue? Yes. The linked OpenAI bug is source-reproducible because current main resolves Is this the best way to solve the issue? No. The OpenAI API-scoped resolver direction is maintainable, but the branch must not collapse multi-account WhatsApp DMs and still needs the required OpenAI changelog entry. Full review comments:
Overall correctness: patch is incorrect Acceptance criteria:
What I checked:
Likely related people:
Remaining risk / open question:
Codex review notes: model gpt-5.5, reasoning high; reviewed against 85e4ec1fb1ac. |
chinar-amrutkar
force-pushed
the
fix/76176-gpt-54-mini-reasoning-effort
branch
2 times, most recently
from
May 3, 2026 00:19
c8873df to
f9e67ae
Compare
When using per-channel-peer dmScope, updateWhatsAppMainLastRoute now records the last-route against the per-contact sessionKey instead of skipping it. This ensures deliveryContext metadata is persisted for later session deliveries. Added test: "records last-route for per-contact session when using scoped dmScope"
… guard The pin guard (pinnedMainDmRecipient) applies only to main session updates. Per-contact sessions should always record their last-route since they are independent of the main session pin state. Updated test to use pinnedMainDmRecipient that differs from dmRouteTarget to verify the per-contact session is updated even when not the pinned owner.
Only suppress reasoning_effort for gpt-5.4-mini in chat/completions API. Responses API paths retain GPT_52 reasoning efforts since the model supports reasoning in that context. Fixes openclaw#76176
chinar-amrutkar
force-pushed
the
fix/76176-gpt-54-mini-reasoning-effort
branch
from
May 3, 2026 09:35
365780d to
14f6f57
Compare
openclaw-barnacle
Bot
added
docs
Contributor
|
Closing this bundled PR in favor of one PR per issue:
Thanks @chinar-amrutkar for the original fixes; the replacement PRs keep the issues split and preserve the WhatsApp multi-account isolation case. |
This was referenced May 3, 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
2 participants
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.
Summary
reasoning_effortin/v1/chat/completions, but OpenClaw was sending it, causing 400 errorsgpt-5.4-miniinresolveOpenAISupportedReasoningEffortsto return[], placed before the broadergpt-5.1andgpt-5patternsreasoning_effortsupportChange Type
Scope
Linked Issue/PR
Root Cause
gpt-5.4-minimatches/^gpt-5(?:-|$)/uand gets assignedGPT_5_REASONING_EFFORTS, but the model only supportsreasoning_effortin the Responses API, not/v1/chat/completionsgpt-5.4-minifrom chat completions reasoning effortUser-visible / Behavior Changes
Security Impact
Compatibility / Migration