Conversation
Co-authored-by: Daniel Sjöstrand <16033062+Danielsjostrand1979@users.noreply.github.com> (cherry picked from commit 65ed520)
…kTagModels A gateway that serves a thinking model without a server-side reasoning parser returns the chain of thought inside message.content as <think> blocks and sends neither reasoning_content nor reasoning_details, so Codex renders the whole chain of thought as the answer. reasoning_split, reasoning.effort and chat_template_kwargs are ignored by such a gateway, so the recovery can only happen client side. Adds the opt-in provider option inlineThinkTagModels. Listed models have their think blocks split back into reasoning on both the streamed and non-streamed openai-chat paths. Off by default: 66 registry providers share this adapter and a gateway that does parse reasoning must keep its visible content byte-exact. Once enabled the splitter still engages only for a response that opens with a thinking tag, so an answer that merely mentions one is never rewritten; after it engages it keeps splitting later blocks, because M-series models interleave thinking with answer segments. An unterminated block flushes as reasoning rather than being lost. The parser is the existing Kiro thinking parser, generalized and renamed to src/adapters/inline-think-tags.ts with an interleaved option. Kiro keeps its single-block behavior and its byte accounting unchanged. The file-size baseline is raised only for src/adapters/openai-chat.ts. The two other offenders the ratchet reports are already present on dev and are untouched. (cherry picked from commit f95a0ad)
Review feedback: trimming the remainder after every closing tag also ate indentation that belongs to the answer, which matters when a block sits inside markdown or code. Only the transition out of the leading block trims now; once answer text has been emitted the remainder is preserved byte-exact. Kiro is single-block, so its behavior is unchanged. (cherry picked from commit 1498eda)
(cherry picked from commit 011f98c)
…ries Keep inline parser answer whitespace and drain interleaved blocks without recursion. Preserve Kiro single-block behavior and document opt-in tag semantics, including code examples after activation. Honor explicit operator parser lists, including []. Use validated effort for omitted-summary visibility and register the source tests. Adapt the model-rename contribution to the existing extracted field classifier. The carried source message describes a historical cap increase; this integration does not carry that increase and keeps the current dev file-size baseline unchanged. Keep the original source commits and their review follow-up with -x provenance. Co-authored-by: Joonsuh Park <trckstr4422@gmail.com> Co-authored-by: Daniel Sjöstrand <16033062+Danielsjostrand1979@users.noreply.github.com> Co-authored-by: alexph-dev <alexph-dev@users.noreply.github.com> Co-authored-by: Yum-wu <1172989563@qq.com>
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: trueThanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
✅ Deterministic PR hygiene checks passed. |
리뷰 · 우선순위 61 / 80이 PR은 생각(reasoning)이 한 바퀴 돌 때 깨지던 세 가지 고침을 한 draft로 모은 작업입니다. 첫째, 서명한 thinking-only 어시스턴트 턴에 도구 호출이 없어도 빈 라인 - 메인테이너의 판단이 필요한 지점 이 한 PR에 replay placeholder, inline 태그 복구, summary/effort 표시 정책을 묶을지, 아니면 합친 검증만 유지하고 원본 세 갈래를 따로 머지할지. 또 combo의 너의 추천 draft 유지한 채, 영향 테스트 범위와 호스트 CI·전체 prepush·독립 보안 리뷰(특히 editor 정책)가 통과한 뒤에만 ready로 올리세요. 병합 시 #5449/#5205/#5491은 superseded로 닫고, 이 댓글은 grok-bot이 작성했습니다 |
|
Carried into #5619 at 8028c91 with your authorship and every co-author trailer kept. Follow-ups resolve the provider-guide conflict by keeping both paragraphs, correct the whitespace contract, and make the inline think-tag parser linear in both block count and leading-whitespace deltas. Closing in favor of #5619. Thank you! |
… fixes (#5619) * fix(cursor): bound capability reads and buffered tool budgets (#5533) Carries #5533 (and the closed #5233 it consolidates) onto current dev. Co-authored-by: Epinephrine <luvs01@hanmail.net> * fix(moonshot): bound normalized tool-schema expansion (#5547) Carries #5547, which consolidates #5464 and the request-wide inline budget, onto current dev. Co-authored-by: yeongjunyoo <47925973+yeongjunyoo@users.noreply.github.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Epinephrine <luvs01@hanmail.net> * fix(moonshot): restore rejected inline budgets and charge nested growth once A rejected sibling-reference expansion now restores the byte, node and expansion allowances it consumed, and outer growth no longer re-charges nested copies, so later independent expansions in the same request keep their allowance. Documents the provider-driven object type inference as a deliberate tradeoff and rewrites ADR-0355 in English. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * feat(reasoning): consolidate replay, opt-in tag parsing, and summary policy (#5566) Carries #5566, which consolidates #5449, #5205 and #5491, onto current dev. The provider guide keeps the current bridge replay paragraph and adds the inline-tag and summary paragraphs. Co-authored-by: Joonsuh Park <trckstr4422@gmail.com> Co-authored-by: Daniel Sjöstrand <16033062+Danielsjostrand1979@users.noreply.github.com> Co-authored-by: alexph-dev <alexph-dev@users.noreply.github.com> Co-authored-by: Yum-wu <1172989563@qq.com> * fix: bound Fernet slot runs, Kiro error-body read, and skill-path line slice (#5310) Carries #5310 onto current dev. The follow-up commit makes the Fernet run cap fail closed and moves the Kiro regression out of the capped stream suite. * docs(reasoning): reconcile inline-tag whitespace contract Interleaved inline-tag parsing preserves answer whitespace; only Kiro single-block mode drops the whitespace after its leading block. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(responses): fail closed on Fernet run overflow and keep the Kiro suite under its cap A slot with more than 64 structurally valid Fernet runs is now treated as unreadable or omitted as a whole, so no unexamined tail reaches the provider as text. The bounded Kiro fallback error-body regression moves byte for byte into a registered sibling file, and the Kiro, Responses and inbound contracts document the new bounds. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(reasoning): scan inline think tags with a moving cursor The parser copied, rescanned and reserved the whole remaining response after every block, so one upstream chunk carrying many short blocks cost quadratic work. It now scans each chunk from an offset and charges the translator budget only for retained carry: undecided leading input or a trailing tag fragment. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(reasoning): keep undecided leading whitespace incremental Before the format was decided, every content delta rebuilt, trimmed and re-reserved the whole leading prefix, so a stream of one-character whitespace deltas cost quadratic work. Leading whitespace is now kept in segments whose bytes are reserved once and joined only when the format is decided or the stream flushes. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(meta-muse): consolidate login admission and bounded response handling (#5591) Carries #5591, which consolidates the closed #5234 and #5432, onto current dev. The provider contract keeps the inline-tag paragraph and adds the Meta Muse admission paragraph. Co-authored-by: Epinephrine <luvs01@hanmail.net> * fix(claude-desktop): keep applied state consistent across profile edits (#5590) Carries #5590, which consolidates the closed #5337, onto current dev. Co-authored-by: Epinephrine <luvs01@hanmail.net> Co-authored-by: luvs01 <luvs01@users.noreply.github.com> * fix(claude-desktop): commit applied markers only over the observed baseline Both Desktop writers, provider-change auto-apply and client sync, now capture the desired profile and its applied marker before the Desktop write and commit the new marker only if profile presence, content, fingerprint and timestamp are unchanged. A concurrent edit, deletion or newer marker keeps its state and the write reports a skipped marker. The provider-change path no longer saves a whole stale config snapshot. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(claude-desktop): commit profile edits against the persisted marker The Desktop profile PUT built its response from an earlier snapshot and saved that whole snapshot, so a marker committed by another writer during the awaited state build could be replaced by an older one. The edit now commits in one persisted-config mutation that keeps the latest marker for unchanged content and answers 409 when the profile itself changed meanwhile. The Meta Muse overflow test now asserts that the bounded-body limit, not a generic failure, produced the error. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(claude-desktop): report an unreadable config separately from an edit conflict A missing or invalid config now answers 500 with its reason; only a concurrent profile change or exhausted rebase answers 409. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * feat(desktop): consolidate consent-based runtime takeover and ownership contracts (#5564) Carries #5564, which consolidates #5459 and #5457, onto current dev. The review screenshot stays in the pull request description rather than the tree. Co-authored-by: jun <bitkyc08@gmail.com> Co-authored-by: sanggyulee <andy53295774@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(desktop): bind takeover stop to the approved runtime and fail closed Desktop takeover re-resolves ownership immediately before stopping and passes the approved PID, endpoint, config home, CLI version and compatibility token to an opt-in guarded stop. The guard is checked under the ownership mutation lease before any manager or signal stop; the approved PID and endpoint must settle and the service manager must then be proven inactive, otherwise the stop answers approval-changed or manager-still-active and the desktop neither waits for silence nor claims. Unreadable or unparseable stop output is terminal as well. A second unreadable service-state read now blocks takeover, Windows managing-CLI discovery follows PATHEXT with file-only candidates and refuses command-interpreter metacharacters, the claim refusal test uses real sandbox state, and the runtime and desktop contracts record that the claim token is a consistency check rather than consent proof. Plain ocx stop is unchanged. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(desktop): keep plain stop entry points and format the takeover changes Desktop exit keeps its plain runtime_stop::run entry while takeover uses run_approved, AttachPlan::Ask no longer carries an unread field, the Rust changes follow rustfmt, the plain CLI stop path keeps its literal outcome return, the stop source oracles follow the reader and outcome union that now include the two guarded refusals, and the runtime contract fits its 600-line budget. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(desktop): run takeover seam tests without tokio macros and harden manager and shim checks The two async takeover seam tests now run on the shell runtime already used by the crate instead of tokio test macros, which this crate does not enable. Windows command-shim probes refuse command-interpreter metacharacters in every recorded argument as well as the executable, and the guarded stop re-inspects the service manager identity immediately before the manager command, answering approval-changed without stopping if it moved. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(responses): keep effort-based reasoning visible after routing Final-route normalization recomputed hideThinkingSummary without the validated active-effort condition, so routed Chat and Kiro requests with an active effort and an omitted summary still hid raw reasoning. It now uses the same predicate as the parser; explicit "none" and requests without an active effort stay hidden. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(service): match the running CLI case-insensitively only on Windows On case-sensitive filesystems a PATH executable that differs only in case is a different file, so it must get its own version probe instead of reporting the running CLI version. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(meta-muse): require the dashboard session for manual login codes The manual-code continuation now applies the same dashboard-session admission as the login start, so a management token cannot advance a pending Meta Muse login. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(reasoning): reserve the joined leading-whitespace copy Joining retained leading whitespace allocated a second copy outside the translator budget; the join is now reserved first and released once the segments are cleared. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(service): skip CLI probes for an absent runtime and treat failed systemd units as stopped Resolve no longer spawns managing-CLI version probes when no runtime is live, since takeover is only offered for a live runtime. A systemd unit reported failed with no main PID is stopped, so a guarded stop that leaves it failed succeeds and a leftover failed unit does not block takeover. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> * fix(service): keep failed systemd units fail-closed and assess takeover only for a live runtime in tests systemd can report failed before an automatic restart, so failed with no main PID is again treated as unknown rather than stopped. The resolve contract tests that assert ownership and takeover fields now use a live runtime, matching the skip of managing-CLI probes when no runtime is live. Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> --------- Co-authored-by: luvs01 <27862058+luvs01@users.noreply.github.com> Co-authored-by: Epinephrine <luvs01@hanmail.net> Co-authored-by: yeongjunyoo <47925973+yeongjunyoo@users.noreply.github.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Joonsuh Park <trckstr4422@gmail.com> Co-authored-by: Daniel Sjöstrand <16033062+Danielsjostrand1979@users.noreply.github.com> Co-authored-by: alexph-dev <alexph-dev@users.noreply.github.com> Co-authored-by: Yum-wu <1172989563@qq.com> Co-authored-by: luvs01 <luvs01@users.noreply.github.com> Co-authored-by: sanggyulee <andy53295774@gmail.com>
Summary
Consolidate the reasoning roundtrip changes from #5449, #5205 and #5491 into one attributed draft, preserving their distinct behavior changes:
inlineThinkTagModelsas an explicit model opt-in for Chat output that encodes reasoning in inline tags. Operator lists, including[], override registry defaults for this new field. Unlisted models pass through unchanged.summary: "none"stays hidden; invalid or absent effort does not accidentally opt in. Combo-injected defaults add summaryautoonly when the caller did not specify a summary.All three other-author originals remain open and unchanged. Current dev's extracted model-field classifier is preserved, and the source's size-cap increase is excluded. No provider preset is newly enabled.
Verification
8028c913ab00ed5b402cb0ab9efee65fbe9e7abb, based on deva6b54297b03fc218105273887ce147c901848d89. Four source commits preserve author and source SHA. Three carries have equal stable patch IDs; the initial inline-parser carry adapts the current classifier and excludes the cap change. Final integration commit retains all contributor trailers.Checklist
Co-authored-by: Joonsuh Park trckstr4422@gmail.com
Co-authored-by: Daniel Sjöstrand 16033062+Danielsjostrand1979@users.noreply.github.com
Co-authored-by: alexph-dev alexph-dev@users.noreply.github.com
Co-authored-by: Yum-wu 1172989563@qq.com