将 Claude Code 缓存亲和逻辑改为可配置规则 - #4150
Open
FlamesCN wants to merge 2 commits into
Open
Conversation
Claude Code reached Codex through the /v1/messages compatibility path, but new-api dropped the session-derived cache key before the final Responses request. This preserved direct Responses caching while leaving Claude Code turns cold. The fix carries the Claude session id into prompt_cache_key, forces the equivalent session_id header on the compatibility path, and keeps Codex-only incompatible metadata out of the upstream request. Constraint: Codex only accepts /v1/responses and rejects metadata on the final upstream request Rejected: Rely on pass_headers alone | did not produce cache hits on the Claude compatibility path Rejected: Only sync prompt_cache_key without session_id header | direct probes still missed cache reads Confidence: high Scope-risk: moderate Reversibility: clean Directive: Keep Claude -> Responses compatibility preserving both prompt_cache_key and session_id together for Codex-backed models Tested: go test ./service/... ./relay/... Tested: manual production verification with Claude Code gpt-5.4 second-turn cache hit (cache_tokens=9472) Not-tested: upstream/main latest integration after cherry-pick
Claude Code cache reuse on the /v1/messages -> responses compatibility path should be driven by channel-affinity rules and override templates, not by hardcoded metadata parsing. This change adds request-header and nested JSON key extraction, exposes the resolved affinity key to override context, and lets templates sync that key into prompt_cache_key and session_id from the console. Constraint: Operators need to adapt to client header/metadata shape changes without shipping a new binary Rejected: Keep parsing metadata.user_id.session_id in convert.go | brittle to client request format changes Rejected: Add a separate Claude-specific settings surface | duplicates existing channel-affinity and param-override controls Confidence: high Scope-risk: moderate Reversibility: clean Directive: Keep Claude cache-affinity behavior driven by key_sources plus override templates; avoid reintroducing client-specific parsing in convert paths Tested: go test ./... Tested: bun run build Tested: production smoke test on 38.76.144.165 for /v1/messages -> gpt-5.4 with metadata-only and header-only session keys; second request hit cache in both cases Not-tested: GitHub PR creation via gh CLI (local auth token invalid)
Contributor
WalkthroughThis PR extends parameter override and channel affinity infrastructure to support context-based sync fields, nested JSON path extraction for key sources, and enhanced prompt caching. It adds a new Changes
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
web/src/components/table/channels/modals/ParamOverrideEditorModal.jsx (1)
276-277: Localize newly added sync-field labels/tags viat(...).The new
contextoption label and quick-tag texts are hardcoded, so they won’t participate in i18n.♻️ Proposed refactor
-const SYNC_TARGET_TYPE_OPTIONS = [ - { label: '请求体字段', value: 'json' }, - { label: '请求头字段', value: 'header' }, - { label: '上下文字段', value: 'context' }, -]; +const getSyncTargetTypeOptions = (t) => [ + { label: t('请求体字段'), value: 'json' }, + { label: t('请求头字段'), value: 'header' }, + { label: t('上下文字段'), value: 'context' }, +];+ const syncTargetTypeOptions = useMemo( + () => getSyncTargetTypeOptions(t), + [t], + ); ... - optionList={SYNC_TARGET_TYPE_OPTIONS} + optionList={syncTargetTypeOptions} ... - {'context:channel_affinity.key -> json:prompt_cache_key'} + {t('context:channel_affinity.key -> json:prompt_cache_key')} ... - {'context:channel_affinity.key -> header:session_id'} + {t('context:channel_affinity.key -> header:session_id')}As per coding guidelines: “Frontend i18n: Use
i18next+react-i18next... UseuseTranslation()hook and callt('中文key')in components.”Also applies to: 2991-3016
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@web/src/components/table/channels/modals/ParamOverrideEditorModal.jsx` around lines 276 - 277, The new hardcoded sync-field label ('上下文字段' for value 'context') and the quick-tag strings should be localized: in the ParamOverrideEditorModal component import and call useTranslation(), replace the literal label and all hardcoded quick-tag texts (the options array entry with label '上下文字段' and the quick-tag strings around the 2991-3016 region) with t('...') keys, and ensure you add appropriate i18n keys/strings rather than raw Chinese text so the labels/tags participate in i18n.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@web/src/components/table/channels/modals/ParamOverrideEditorModal.jsx`:
- Around line 276-277: The new hardcoded sync-field label ('上下文字段' for value
'context') and the quick-tag strings should be localized: in the
ParamOverrideEditorModal component import and call useTranslation(), replace the
literal label and all hardcoded quick-tag texts (the options array entry with
label '上下文字段' and the quick-tag strings around the 2991-3016 region) with
t('...') keys, and ensure you add appropriate i18n keys/strings rather than raw
Chinese text so the labels/tags participate in i18n.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 95c6cfff-ddf4-4d82-8f4f-4c39e42b3eac
📒 Files selected for processing (15)
constant/context_key.gorelay/channel/codex/adaptor.gorelay/chat_completions_via_responses.gorelay/common/override.gorelay/common/override_test.gorelay/common/relay_info.goservice/channel_affinity.goservice/channel_affinity_template_test.goservice/convert.goservice/openaicompat/chat_to_responses.goservice/openaicompat/chat_to_responses_test.gosetting/operation_setting/channel_affinity_setting.goweb/src/components/table/channels/modals/ParamOverrideEditorModal.jsxweb/src/constants/channel-affinity-template.constants.jsweb/src/pages/Setting/Operation/SettingsChannelAffinity.jsx
11 tasks
Calcium-Ion
force-pushed
the
main
branch
2 times, most recently
from
August 30, 2026 15:03
51fdfc5 to
2b6f1df
Compare
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.
这次把上一版里对 Claude metadata 的固定解析去掉了，改成走现有的渠道亲和和参数覆盖模板能力。
主要调整：
key_sources增加request_header和gjson.nested_pathsync_fields增加context:来源claude cli trace规则改成优先从X-Claude-Code-Session-Id取值，取不到再从metadata.user_id里按nested_path提session_id这样做的目的是把这块逻辑从兼容转换代码里拿出来，避免继续把某一种请求结构写死在
convert.go里。验证：
go test ./...bun run build38.76.144.165实测/v1/messages->gpt-5.4metadata.user_id.session_id：第一次cache_tokens=0，第二次cache_tokens=3200X-Claude-Code-Session-Id：第一次cache_tokens=0，第二次cache_tokens=2944如果这个方向没问题，后面再遇到客户端字段调整，应该只需要在控制台改规则，不需要再补一版代码。
Summary by CodeRabbit
New Features
Bug Fixes
UI Updates