fix(agent-core-v2): restore thinking for the openrouter reasoning dialect - #3910
Merged
sailist merged 1 commit intoSep 18, 2026
Merged
Conversation
…lect Keep string reasoning fields when a reasoning_details array is present, stamp each think part by source, and replay those fields on the next request.
🦋 Changeset detectedLatest commit: 4c860c3 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
commit: |
This was referenced Sep 18, 2026
Merged
7723qqq
added a commit
to 7723qqq/kimi-code
that referenced
this pull request
Sep 20, 2026
Compaction pre-shrinks the summarizer's history to the model's effective window before the first request (MoonshotAI#3911), replayed thinking on OpenAI-compatible transports rides the declared `reasoning_key` (MoonshotAI#3910), the catalog endpoints expose each provider's resolved `base_url` (MoonshotAI#3909), usage telemetry fires for the swarm transition, external hooks, remote-control toggles and tower entry/exit (MoonshotAI#3897), a steered message carries its prompt's identity end to end (MoonshotAI#3906 / MoonshotAI#3891), and the rating survey payload gains the per-turn trace id plus copilot statistics (MoonshotAI#3907).
7723qqq
added a commit
to 7723qqq/kimi-code
that referenced
this pull request
Sep 21, 2026
The module header and translate_global's doc comment both said the workspace lane and plugin events "do not exist yet" — the workspace fold arm sits forty lines below that comment, and the plugin arm above it. Verified against the code: all four workspace mutation routes publish event.workspace.created|updated|deleted on the global lane (server/mod.rs:4147, 4279, 4305 plus set_trusted), translate_global folds them into WorkspaceMessage from a per-connection cache seeded at connect, and the tests pass (37 workspace + 12 ws_v3). The one lane with nothing to translate is capability, and the reason is narrower than "static list": upstream declares event.capability.changed but never constructs it anywhere in its own tree, so there is no producer to port. Both notes now say that. ROADMAP §8.10 records the same finding: the "still open" list shrinks to capability (no upstream producer) and MoonshotAI#3910's reasoning_details stamping (deliberate).
6 tasks
Leeeon233
added a commit
to LodyAI/acp-extension-kimi
that referenced
this pull request
Sep 24, 2026
* feat(kimi-code): carry turn trace id and copilot stats in rating surveys (MoonshotAI#3907) * feat: expose resolved base_url on models.dev catalog provider items (MoonshotAI#3909) * fix(agent-core-v2): restore thinking for the openrouter reasoning dialect (MoonshotAI#3910) Keep string reasoning fields when a reasoning_details array is present, stamp each think part by source, and replay those fields on the next request. * ci: release packages (MoonshotAI#3862) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * docs(changelog): sync 2.0.1 from apps/kimi-code/CHANGELOG.md (MoonshotAI#3912) * fix(agent-core-v2): pre-shrink compaction history to the effective model window (MoonshotAI#3911) * fix(vscode): ignore Enter during IME composition in question dialog (MoonshotAI#3915) * fix(kap-server): deliver session-level interaction events past agent filters (MoonshotAI#3901) * revert(kap-server): drop the flat entity message protocol (v3 WS + history API) (MoonshotAI#3532) (MoonshotAI#3920) This reverts 64505e3. The v1 WS + legacy REST + transcript surfaces are alive on main and remain the single protocol surface; kimi-inspect returns to the transcript-based data model (keeping MoonshotAI#3747's removal of the prompt input, which adapted to the agent-core-v2 prompt-queue fold). * feat(oauth): parse goods_version from the managed /me profile payload (MoonshotAI#3921) * fix: keep turn ids above the wire-wide max and fold cold transcripts over the active branch (MoonshotAI#3922) * fix(agent-core-v2): floor the human turn clock at the wire-wide max on engine journal reset * fix(kap-server): fold the cold transcript snapshot over the restorable branch chain * fix(agent-core-v2): advance the human turn clock when a turn starts * fix(kap-server): split reused wire turn ids in the live transcript projector * fix(kap-server): adopt the completed cold tip for mid-turn attach events Continuation deltas after a lazy transcript attach belong on the last cold turn, not a newly split export id. * fix(agent-core-v2): remove the project-root assertion for cwd from the system prompt (MoonshotAI#3929) Co-authored-by: 7Sageer <7sageer@djwcb.cn> * chore: remove the tdd skill (MoonshotAI#3932) * fix(agent-core-v2): don't record turn.steer when an unconsumed steer seeds the next turn (MoonshotAI#3933) * chore: sync web dist from code-app (MoonshotAI#3934) * chore: sync web dist from code-app code-app: 44d7281c7a63ee3c7a907f9406e490efdbec7411 * chore: collapse web dist sync changesets into one summary entry * ci: release packages (MoonshotAI#3913) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * feat: generate native Kimi ACP session titles (#15) --------- Co-authored-by: Grapedge <shiwang.lj@alibaba-inc.com> Co-authored-by: liruifengv <liruifeng1024@gmail.com> Co-authored-by: Haozhe <yanghaozhe@moonshot.ai> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: 7Hanrui <qihanrui@moonshot.ai> Co-authored-by: 7Sageer <7sageer@djwcb.cn> Co-authored-by: Zixuan Chen <remch183@outlook.com>
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
1 participant
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.
Related Issue
Resolve #3900
Problem
See linked issue. After #3492, OpenAI-compatible providers that return a
reasoningstring next to areasoning_detailsarray of unrecognizedreasoning.textitems (and noreasoning_content) drop the thinking chain on the way in, so the TUI stays blank.What changed
reasoning_detailsis present, then still converts officialsummary/encrypteddetails.reasoning,reasoning_content, and official details back independently.#3492details +reasoning_contentreplay and thetrait.reasoningKeydetails skip for interleaved models are unchanged. Unrecognizedreasoning.textarray items are still ignored.Checklist
/approve).gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.