fix(responses): route raw reasoning through the expandable summary channel (lands #2007) - #2016
Merged
Conversation
…annel Codex renders the expandable reasoning trace from the Responses reasoning item summary[] channel only. Chat-completions providers (DeepSeek-style) deliver thinking as raw reasoning_content, which the bridge and the native Responses passthrough both shaped as summary:[] + content:[reasoning_text], so routed turns showed the timer with nothing to expand (issue #45). Route reasoning_raw_delta through the same summary path as thinking_delta in the streaming and buffered bridges, and add a payload rewrite for the native-Responses passthrough (DeepSeek /responses) that converts reasoning_text.delta/done and reasoning item content into the summary channel. Internal replay-cache handoff and hideThinkingSummary suppression are preserved. Tests: bridge summary-channel shape + hide parity, rewrite unit tests, replay-cache regressions all pass; tsc clean.
…model gate CodeRabbit follow-ups: - Apply the summary-channel rewrite to the bounded-JSON passthrough path too (plain JSON answers and forced JSON-to-SSE reframing both build from clientJson), handling both the SSE completed-event shape and the bare response document shape DeepSeek returns for stream:false. - Return the original reasoning item untouched when it carries no reasoning_text content, so summary-channel items are never cleared. - Normalize both sides of the preserveReasoningContentModels match so mixed-case configured ids still gate the rewrite.
…writes CodeRabbit follow-up: when the client asked for hidden thinking (no reasoning.summary in the request), the passthrough summary-channel rewrite must not surface upstream reasoning as visible summary output. Gate both the SSE payload rewrite and the bounded-JSON rewrite on parsed.options.hideThinkingSummary !== true, and cover the four hidden/visible x SSE/JSON combinations with handleResponses integration tests.
# Conflicts: # src/server/responses/core.ts
Contributor
|
✅ Deterministic PR hygiene checks passed. |
2 tasks
lidge-jun
added a commit
that referenced
this pull request
Aug 19, 2026
…d persist visibility (#2078) * docs(devlog): #2064 RCA — fixed on dev by #2016, version-ancestry proven * fix(replay): scope durable thought signatures per credential and bound persist visibility The durable thought-signature store keyed entries by thread + destination + model but not by credential, so account A's Gemini signatures could replay under account B on the same destination (#1926 gap 1). Keys now carry a salted-HMAC credential identity (installation-local salt persisted beside the store, full 256-bit output — never an unsalted digest of key material) derived from the persisted OAuth account-slot id, the API key, or the Codex account handle; a scope that cannot produce one fails closed instead of sharing a durable slot. STORE_VERSION 3 -> 4 drops old rows on load (not upgradable — no credential info was recorded). Gap 2: terminal frames could become externally visible before the queued signature persist settled. All async terminal paths (completed, truncation and adapter-EOF incompletes, failed) and both buffered JSON returns now await a bounded (250ms) durability barrier; the sync stall-timeout kill path keeps the pre-existing best-effort behavior, documented in place. Closes #1926 * fix(replay): wire durable lookup at adapter serialization; trust only pool account handles; harden salt perms Security-review fold-back: (1) the parser's durable lookup ran before the credential scope was bound, so the store was write-only at runtime — the google adapter now falls back to the durable store at serialization time, when the scope identity exists (regression-pinned); (2) the codex-forward durable handle no longer accepts the client-supplied chatgpt-account-id header (trusted pool context only; direct-forward fails closed); (3) the salt file re-asserts 0600 on every load.
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
Lands contributor PR #2007 (AlinJiang) on current
dev: content-channel raw reasoning is normalized through the expandable summary channel on the bounded-JSON path, matching the SSE rewrite. The one-hunk conflict against today'sbackfillResponsesFieldsJson(#1941) is composed: repair → model rewrite → field backfill → summary rewrite.Verification
tsc --noEmitcleanChecklist