Conversation
lidge-jun#1780 normalizes tool call ids in the Anthropic and Google adapters, but anthropicNativePassthrough bypasses the adapter by design and forwarded message bodies verbatim. Sessions that carry third-party tool call ids — e.g. `Bash:0#<hex>` minted by non-Anthropic models — therefore still 400 (`tool_use.id: String should match pattern '^[a-zA-Z0-9_-]+$'`) the moment the model is switched to a real Anthropic model with native credentials. Run the same createToolCallIdAllocator over *tool_use / *tool_result blocks before the body is serialized: conforming ids pass through byte-identical, non-conforming ids are rewritten deterministically with a hash suffix, and call/result pairing stays stable. Covers /v1/messages and /v1/messages/count_tokens, which share this branch.
Contributor
|
✅ Deterministic PR hygiene checks passed. |
Contributor
⏳ DRAFT
What to do
Review readiness checklist
0/4 boxes ticked. This PR stays in draft until every box above is ticked. |
Owner
리뷰 · 우선순위 64 / 80클로드 본사로 요청을 거의 그대로 넘기는 길에서는 도구 호출 번호(tool_use id)를 고치지 않았습니다. 번호 고치기는 번역 어댑터에만 있었습니다. 다른 모델이 만든 번호가 대화에 남아 있으면, 예를 들어 이 PR은 보내기 직전에 같은 고치기를 이 길에도 넣습니다. 규칙에 맞는 번호는 한 글자도 안 바꿉니다. 안 맞는 번호는 같은 입력이면 항상 같은 값으로 바뀌고, 호출과 결과의 짝은 유지됩니다. 라인 - 라인 - 라인 - 상태 · draft — 준비 체크리스트 네 칸이 비어 있습니다. 최신 메인테이너의 판단이 필요한 지점
빈 번호를 이번 PR에서 막을지, 너의 추천 닫지 않는 편이 맞습니다. 같은 수정을 담은 다른 열린 PR은 없습니다. 빈 번호는 요청에 남기지 말고, 번호가 겹치는 테스트를 하나 넣은 다음 체크리스트를 채우고 Ready로 올리면 됩니다. 이 댓글은 grok-bot이 작성했습니다 |
3 tasks
lidge-jun
added a commit
that referenced
this pull request
Sep 23, 2026
…riptions, launchd levers, passthrough tool ids (#5678) * test(claude): cover bounded skill marker paths and document pass-through Carries #5606. Adds the exact 4,096/4,097 UTF-16 code unit boundary cases for POSIX and Windows skill directory markers and a long newline-free carrier, and documents that a longer directory line is sent unchanged. The seven translated Claude Code guides now state the same pass-through rule as the English guide. Supersedes #5606. Co-authored-by: Epinephrine <27862058+luvs01@users.noreply.github.com> * fix(system-env): refresh and drop the launchd levers opencodex owns Carries #5622. A lever opencodex already tracks as injected is refreshed instead of skipped, a tracked lever the current config no longer produces is unset, and PUT /api/claude-code reconciles on every model slot and lever field, not only systemEnv and authMode. A launchd value the user set before injection is never touched. The management API structure note records the PUT reconciliation. Supersedes #5622. Co-authored-by: terin <100397903+sh940701@users.noreply.github.com> * feat(claude): describe routed models instead of "From gateway" Carries #5621. Readable Claude Code /v1/models rows carry a description naming the native model or provider/model they route to, which Claude Code 2.1.257 and later shows in the picker; the 1M copy keeps it and a Fast sibling appends " · Fast". The gateway-model cache preserves string descriptions. The Claude Desktop structure note records the picker description contract. Supersedes #5621. Co-authored-by: terin <100397903+sh940701@users.noreply.github.com> * fix(claude): keep routed model windows without disabling compact Carries #5665. Claude Code aliases are minted as ocx-claude-/ocx-claude2- so the picker keeps them while Claude Code applies CLAUDE_CODE_MAX_CONTEXT_TOKENS without DISABLE_COMPACT; saved claude-ocx-/claude-ocx2- ids keep decoding. maxContextTokens now injects only the window. The gateway cache mirrors the picker's contains-claude rule and keeps #5621's descriptions. Folded review fixes: native fallback recognizes the current prefixes; the context-window map keeps registering the legacy spellings at the same window; no compact lever is ever derived from maxContextTokens (pinned for values outside the 100k-1M compact range); the tracked DISABLE_COMPACT from older releases is removed by the system-env produced-key sweep instead of a one-off cleanup; the Claude Desktop structure note records the alias and env contract. Supersedes #5665. Co-authored-by: terin <100397903+sh940701@users.noreply.github.com> * fix(claude): sanitize tool_use ids on native Anthropic passthrough Carries #5628. The native passthrough bypasses the Anthropic adapter, so tool call ids minted by routed models (Devin's Bash:0#<hex>) reached api.anthropic.com verbatim and 400ed. The request-scoped allocator now rewrites non-conforming and overlength ids, keeps call/result pairing, and leaves conforming ids byte-identical. Folded review fixes: an empty id fails locally with a 400 before the upstream fetch instead of being forwarded; regressions cover the empty id, an overlength id and a collision with an existing valid id; the Claude Desktop structure note and the Claude Code guide in all eight languages describe the id rewrite. Supersedes #5628. Co-authored-by: wuwei <27188611+Haven2026@users.noreply.github.com> * fix(claude): keep legacy slot selectors and hand-edited DISABLE_COMPACT safe on upgrade Folds the bundle's adversarial review into the #5665 and #5622 carries. A legacy claude-ocx-/claude-ocx2- selector configured in an OpenCodex model slot is emitted in its current ocx-claude spelling on every env path. The route is identical, and Claude Code then applies the configured window instead of falling back to 200k accounting now that DISABLE_COMPACT is no longer paired with maxContextTokens. A selection saved by Claude Code's own picker stays a documented re-pick. The system-env sweep removes a tracked DISABLE_COMPACT only while it still holds the 1 older releases injected; a value the user changed by hand is released from tracking without being deleted. Co-authored-by: terin <100397903+sh940701@users.noreply.github.com> * fix(claude): keep legacy picker selectors on connected clients and Fable passthrough Folds the Codex and CodeRabbit review of the bundle. A legacy claude-ocx-native--claude-fable-* picker value compared only against the new ocx-claude spelling and fell off the native Anthropic passthrough; both spellings are accepted again, with the legacy value back in the endpoint test. The connected-client context-window map registers the legacy route and native spellings like the local map does, so a saved legacy selector keeps its [1m] subagent marker on a connected hub. Co-authored-by: terin <100397903+sh940701@users.noreply.github.com> --------- Co-authored-by: Epinephrine <27862058+luvs01@users.noreply.github.com> Co-authored-by: terin <100397903+sh940701@users.noreply.github.com> Co-authored-by: wuwei <27188611+Haven2026@users.noreply.github.com>
Owner
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
createToolCallIdAllocatorand wired it intoadapters/anthropic.tsandadapters/google.ts, so translated Anthropic requests replay cross-provider tool history safely.anthropicNativePassthroughinsrc/server/claude-messages.tsbypasses that adapter by design and serialized the request body verbatim — sessions carrying non-Anthropic tool call ids (e.g.Bash:0#<hex>minted by third-party models) still 400 withtool_use.id: String should match pattern '^[a-zA-Z0-9_-]+$'when switched to a native Claude model on a realsk-ant-*credential.*tool_use/*tool_resultblocks before the body is serialized. Conforming ids pass through byte-identical (prompt-cache keys untouched); non-conforming ids get the deterministic sanitize+hash rewrite with stable call/result pairing. Covers/v1/messagesand/v1/messages/count_tokens, which share the branch.Test plan
tests/claude-integration/claude-native-passthrough.test.ts: pollutedtool_use/server_tool_use/web_search_tool_result/tool_resultids rewritten to conforming wire ids, pairing preserved, conformingtoolu_*ids byte-identical, deterministic across requests (messages vs count_tokens)bun test tests/claude-integration/claude-native-passthrough.test.ts— 17/17 passbun run typecheck— cleanbun run structure:check— pass (no contract change: docs describe the passthrough as "forwards without translation"; id sanitization is the same class as the image normalization already applied on this branch)bun run privacy:scan— passbun run test:changed— 2626 pass / 20 fail; all 20 aremanagement-provider-validationcases that fail identically on cleandev(api.example.testprovider POST → 400; unrelated environment issue)Bash:0#<hex>history → 400 before this change, 200 after (claude-haiku-4-5 via passthrough)Refs #1767, #1780.
Review readiness checklist
This PR stays in draft until every box below is ticked. Tick all four boxes once the requirements are met:
Required local validation passed; commands, results, and any full-suite exception are documented.
I pushed my PR to the latest dev commit.
I resolved all correct Codex and CodeRabbit findings.
My PR is ready for review.