Commit Graph

4855 Commits

Author SHA1 Message Date
Luis Pater
b285660f84 feat(api): expose standalone in-flight request count on management API
- Add a lightweight per-request in-flight tracker on the auth manager that covers selection, upstream calls, retry waits, and the full stream lifetime; it stays disabled in Home mode where the execution registry is authoritative.
- Register GET /v8/management/observability/requests/in-flight returning counts only (in_flight, oldest_started_at, by_provider) with no request bodies or credential identifiers.

Closes: #7476
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-13 03:06:02 +08:00
Luis Pater
1aaf56bc6a docs(readme): add VisionCoder provider listing to English, Chinese, and Japanese READMEs 2026-11-13 02:52:39 +08:00
Luis Pater
f7ae8feeb3 docs(readme): add OriginCoder provider listing to English and Japanese READMEs v8.0.69 2026-11-13 02:25:36 +08:00
Luis Pater
73b86c7fb9 feat(api): add opt-in server.shutdown-timeout for graceful request draining
- Add server.shutdown-timeout config (default 0 = immediate close, preserving #6094 behavior); positive values drain in-flight HTTP requests via http.Server.Shutdown bounded by the configured seconds, then force-close the rest.
- Bound the drain by the configured timeout even when the caller's context is more generous, while a tighter parent deadline still wins; hijacked WebSocket connections remain managed by their own handlers.
- Cover drain completion, budget-expiry fallback, tighter parent ctx, zero default, and v8/legacy config parsing in tests.

Closes: #7475
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-13 02:18:18 +08:00
Luis Pater
42f9adb9ac feat(tui): migrate management client to v8 routes with legacy fallback
- Prefer /v8/management endpoints for config, credentials, api-keys, logs, and OAuth flows, normalizing the v8 config tree to the TUI's flat view and falling back to /v0/management only when a route is genuinely unimplemented.
- Read access.api-keys from the same versioned root-config snapshot and write back with If-Match, refusing unconditional replaces and stale-index edits/deletes so concurrent changes are not lost.
- Return a non-zero exit via CheckManagementSupport when a server definitively exposes neither contract, while keeping transient probe failures and wrong-password retries non-fatal.

Closes: #7462
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
v8.0.68
2026-11-13 02:02:23 +08:00
Luis Pater
1cb14ceb78 docs(readme): link OriginCoder provider name in Chinese README 2026-11-13 01:59:17 +08:00
Luis Pater
4cc0cd40b6 docs(readme): add OriginCoder API provider listing 2026-11-13 01:53:03 +08:00
Luis Pater
1fcb143220 feat(models): update Devin catalog and add Gemini model variants
- Add Gemini 4 Hydrogen and Antigravity Gemini variants.
- Update Devin model versions while retaining previous entries.
2026-11-13 01:12:45 +08:00
Luis Pater
91aca317b0 fix(gemini): preserve thought signatures across tool-call round trips
- Restore Claude signature carriers onto their original Gemini parts with message and semantic boundaries.
- Return Gemini tool signatures in streaming and non-streaming Chat Completions responses without weakening provider compatibility.
- Cover delayed signatures, metadata, unsupported payloads, and payload-rule precedence with regression tests.

Closes: #7484
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-13 00:33:01 +08:00
Luis Pater
8e8e823102 test(api): verify WebSocket reauthorization with request logging enabled
- Run the reauthorization regression test with request logging both enabled and disabled.
- Drain WebSocket handlers and verify logging leaves no temporary files and records the revoked credential.
2026-11-12 23:58:23 +08:00
Luis Pater
e63179492e fix(auth): back off rejected refresh recovery jobs
- Preserve a positive refresh delay for expired credentials with an unknown refresh outcome to prevent immediate redispatch.
- Cover task completion, disabled credentials, diagnostic errors, and replacement-grant rescheduling with regression tests.

Closes: #7491
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-12 23:57:10 +08:00
Luis Pater
02ec93d004 fix(claude): preserve beta profiles across thread turns
- Reuse successful wire beta snapshots across thread turns and executor reloads.
- Keep continuations on their original credential and honor explicit payload/header policies.
- Recover snapshots through KV and publish state before streaming completion, with regression coverage.

Closes: #7470
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-12 21:07:10 +08:00
Luis Pater
f03f4cd8b0 fix(thinking): validate native responses reasoning efforts
- Normalize native Responses baseline and configuration updates against model capabilities without flattening the update timeline.
- Preserve supported efforts, suffix overrides, and final user payload rules across Codex SIWC transports.

Closes: #7478
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-12 18:09:32 +08:00
Luis Pater
07290e18da fix(translator): map upstream MAX_TOKENS to OpenAI finish_reason length
- Map upstream MAX_TOKENS to finish_reason "length" in the Antigravity and Gemini OpenAI Chat Completions translators (streaming and non-streaming), since "max_tokens" is not a valid OpenAI finish_reason and strict clients reject it.
- Keep native_finish_reason as the lowercased upstream value and preserve tool_calls precedence and content_filter handling, updating and adding regression test cases for each affected path.

Closes: #7463
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-12 16:21:38 +08:00
Supra4E8C
9a8ca1b577 Merge branch 'docs/add-deepsider-sponsor' into dev 2026-11-12 16:04:36 +08:00
Luis Pater
05fd8197f1 feat(tunnel): add server type metadata to WebSocket discovery
- Require and validate a free-form type for server peers, accepting it from the query string or `X-Tunnel-Type` header.
- Include server types in server lists and online/offline events.
- Update tunnel documentation and integration coverage.
2026-11-12 10:18:22 +08:00
Luis Pater
f93d5cba95 fix(cmd): return non-zero exit status on config load, TUI, and service startup failures
- Route pre-configuration startup logs to stderr and return exit status 1 from a deferred-safe run helper when config loading, store bootstrap, or TUI execution fails.
- Propagate synchronous proxy service build and runtime errors from StartServiceWithPluginHost to stderr and exit status 1 while preserving exit status 0 on graceful context cancellation.
- Add subprocess and unit regression tests covering missing config, malformed YAML, TUI failures, occupied ports, and interrupt shutdown.

Closes: #7459
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-12 03:23:19 +08:00
Luis Pater
c3a6c7416c fix(openai-responses): translate typed thinking content-part arrays in responses translator
- Parse typed delta.content arrays and structured reasoning fields in streaming responses to emit sequential reasoning and message items while preserving finalized message statuses across interleaved transitions.
- Extract thinking and visible text segments from non-streaming message.content arrays as reasoning fallback and assistant output text without leaking raw JSON arrays.
- Allow reasoning-only streams with an explicit finish_reason to finalize cleanly while keeping unfinished-stream guards intact.

Closes: #7455
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-12 03:18:30 +08:00
Supra4E8C
2d5ffa04d3 docs: add DeepSider API sponsor 2026-11-12 00:32:57 +08:00
Luis Pater
4787c7a3c4 feat(tunnel): add multi-tenant WebSocket data exchange tunnel (/v1/tunnel)
- Introduce internal/wstunnel implementing a multi-tenant, many-to-many
  opaque WebSocket data exchange hub over GET /v1/tunnel.
- Enforce strict access.api-keys authentication across all five standard
  credential sources, rejecting unconfigured keys with 401, isolating
  tenants per API key, and revoking removed keys on hot reload with
  WebSocket close code 1008.
- Enforce per-tenant cross-role device UUID uniqueness (409 Conflict on
  duplicates, generation-bound handshake reservations) while allowing
  duplicate human-readable device names.
- Multiplex discovery and data exchange over a single WebSocket per
  device: UTF-8 JSON TextMessage control frames (*ojson.Doc single-exit
  serialization for server_list, server_online, server_offline,
  list_servers, and error) and BinaryMessage frames carrying a 4-byte
  header, source/destination UUIDs, and up to 64 MiB opaque payloads
  with anti-spoofing and cross-role routing checks.
- Guard upgraded transports against post-upgrade socket deadlines
  (including wrapped non-ALPN TLS connections and RFC 6455 protocol
  error paths), enforce per-peer and per-tenant outbound byte budgets
  retained across in-flight writes, and bound non-blocking close
  reclamation.
- Mount /v1/tunnel on internal/api.Server (405 Allow: GET for non-GET
  methods while preserving CORS OPTIONS) and add English and Chinese
  integration guides under docs/websocket-tunnel.md and
  docs/websocket-tunnel_CN.md.
2026-11-12 00:03:24 +08:00
Luis Pater
a9e3ddcf02 fix(devin): fail over on empty completions and stop fake completion on canceled streams
- Classify clean-EOS zero-output completions and pre-output stream drops as HTTP 502 transient transport errors so Conductor rotates across credentials and fallback layers without cooling healthy Devin credentials, while marking mid-generation drops as stream-truncated.
- Record failed usage with any partial token details and upstream response summaries whenever unfinished Devin streams are canceled before completion instead of synthesizing fake interaction.completed events.
- Gate apply_patch error wrapping on observed patch tool-call activity and preserve stream-truncation and partial usage metadata across streaming and non-streaming failure paths.

Closes: #7442
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 18:02:32 +08:00
Luis Pater
1f5bf2a569 fix(codex): release refresh claims on pre-send errors and defer macOS wakes
- Classify request creation and pre-handoff connection failures separately from ambiguous post-connection errors so unsubmitted refresh grants release their journal claim and remain retryable.
- Implement owner-bound, single-attempt claim release across memory, file, PostgreSQL, Git, and S3 refresh journals while preserving replay protection for completed or uncertain exchanges.
- Apply macOS power-state readiness deferral to ordinary Codex refreshes and preserve a positive reschedule backoff in the auto-refresh manager.

Closes: #7450
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 17:49:05 +08:00
Luis Pater
8bba7a77c6 docs(README): add AICodeMirror sponsor banner to EN, CN, and JA readmes
- Add AICodeMirror sponsor row with logo, affiliate link, and promotional copy to README.md, README_CN.md, and README_JA.md.
- Include assets/aicodemirror.png logo image.
v8.0.67
2026-11-11 16:50:42 +08:00
Luis Pater
9d7d012b35 fix(auth): preserve large weighted pool fairness and force cooldowns
- Share smooth-weighted credits across dynamic large-pool subsets while isolating removed or re-registered credentials and bounding retained state.
- Preserve scheduler shard cursors and underlying weighted selectors across unrelated config and session-affinity reloads.
- Track and persist explicit ErrorCodeForceCooldown deadlines across disable-cooling reloads, interleaved errors, and cooldown state restores.

Closes: #7431
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 14:48:15 +08:00
Luis Pater
fa11a573b2 fix(claude): make server-side fallback opt-in and surface serving models
- Gate cloaked Claude server-side fallback injection behind an opt-in upstream.claude.server-side-fallback flag (default false) while preserving explicit caller fallbacks and payload filter precedence.
- Propagate authoritative upstream serving models and ordered fallback boundary metadata across OpenAI Chat Completions and Responses streaming and non-streaming translations.
- Track mid-stream fallback transitions in Claude response-model and usage observers and add regression coverage for single-hop, multi-hop, sticky default, and refusal paths.

Closes: #7440
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
v8.0.66
2026-11-11 11:37:35 +08:00
Luis Pater
ecebc71345 fix(auth): keep request retry rounds after scheduler plugin reject
- Separate plugin scheduler rejections from request-stop rules via dedicated boundary markers so a rejection after an intra-round attempt failure preserves the attempt error and allows outer request-retry rounds to proceed.
- Stop immediately on zero-attempt rejections and track terminal scheduler-rejected rounds so Antigravity credits fallback cannot bypass plugin rejection policies.
- Add regression tests covering Execute, ExecuteCount, ExecuteStream, sticky retry-round rejections, boundary error unwrapping, and Antigravity credits fallback suppression.

Closes: #7434
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 11:09:04 +08:00
Luis Pater
65de937cf1 feat(claude): consume Home credential_options cloak settings
- Extract Home credential_options.cloak and slice-valued cloak_sensitive_words under claudeDevicePoolMu without JSON round-tripping.
- Preserve shared DisableClaudeCloakMode defaults when cloak.mode is omitted and avoid splitting comma-containing sensitive-words.
- Report Claude cloak block additions, removals, and sensitive-words content updates in config change details.

Co-authored-by: lzt404 <2596933790@qq.com>
v8.0.65
2026-11-11 10:15:31 +08:00
Luis Pater
9a7e1e6b41 feat(executor): add sensitive-words-replace and harden Antigravity obfuscation
- Add sensitive-words-replace map support across Antigravity, Claude cloak, and Devin configurations, runtime cloning, comment-preserving YAML persistence, v8 management endpoints, and config diffing.
- Apply single-pass longest-match-first literal replacements alongside sensitive-word obfuscation across Antigravity, Claude, and Devin executors without cascading re-scans.
- Switch Antigravity system-instruction sensitive-word obfuscation from U+200B to per-subword U+034F (CGJ) while preserving non-matching instructions, tool definitions, and conversation messages.

Closes: #7428
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 08:58:13 +08:00
Luis Pater
f77a3c104b fix(meta): pass through explicit client prompt_cache_retention
- Preserve explicit non-empty string prompt_cache_retention values from client payloads across Meta request translation while leaving omitted, null, blank, and non-string values unset without injecting 24h by default.
- Synchronize prompt_cache_retention onto the translated original request document so payload default, override, and filter rules remain the final semantic barrier.
- Document the meta protocol option and opt-in prompt_cache_retention default rule in config.example.yaml and add regression tests.

Closes: #7424
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 08:46:36 +08:00
Luis Pater
69ed202a1a fix(registry): restore model listings once bounded cooldown deadlines expire
- Align client model projections with selector availabilityBlock semantics and carry bounded suspension deadlines while keeping disabled and terminal unauthorized gates open-ended.
- Track per-client suspension deadlines in ModelRegistry and fold live deadlines into availability cache expiration so /v1/models relists models automatically once cooldowns end.
- Add deterministic regression tests covering transient 408 cooldown expiry, forked aliases, open-ended gates, manual overrides, and bounded quota recovery.

Closes: #7421
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 07:41:33 +08:00
Luis Pater
ece3f52a41 fix(logging): preserve bounded upstream responses in error logs
- Capture bounded per-attempt upstream status, masked headers, response chunks, and transport or stream errors when request-log is false.
- Bind synchronized deferred capture to the HTTP request context and preserve partial HTTP bodies and WebSocket dial or reconnect failures.
- Mask Cookie headers alongside Set-Cookie so forced error logs do not expose session credentials.

Closes: #7420
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 03:31:39 +08:00
Luis Pater
949b43b330 fix(xai): classify non-stream terminal SSE errors and empty or incomplete streams
- Surface upstream SSE error, response.failed, and raw JSON failure payloads through xaiStatusErr with mapped HTTP status codes instead of 408 request_timeout.
- Return request-scoped 502 errors for empty and unclosed 2xx streams without triggering transient credential cooldown.
- Avoid misclassifying empty or unclosed non-stream responses as apply_patch argument errors when no custom apply_patch activity occurred.

Closes: #7419
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 02:51:36 +08:00
Luis Pater
cb70eacfa5 fix(claude): emit anthropic-ratelimit-unified headers on local cooldown 429s
- Retain and persist rejected Claude unified quota signals alongside active cooldown deadlines so out-of-order completions, restarts, and dual-layer quota wraps keep accurate window metadata.
- Populate anthropic-ratelimit-unified-* headers on Claude quota modelCooldownError responses aligned with Retry-After while keeping SafeResponseHeaders restricted to trusted retry headers.
- Exclude non-Claude, Cloudflare challenge, and ordinary per-minute rate-limit cooldowns from unified subscription quota header synthesis across selector and scheduler paths.

Closes: #7417
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-11 01:20:48 +08:00
Luis Pater
effbac168a feat(models): add Gemini 4 Carbon model entry to models.json
- Add Gemini 4 Carbon (High) with 1M context length and 1M max completion tokens.
- Include thinking levels (low, medium, high) with dynamic thinking support.
- Support text, image, audio, and video input modalities with text output.
- Enable web_search native capability for the new model.
2026-11-11 00:02:25 +08:00
Luis Pater
d1ea84f4b3 docs(readme): remove AICodeMirror sponsorship banner
- Remove AICodeMirror promotional block and affiliate link from README.md, README_CN.md, and README_JA.md.
- Delete unused sponsor asset image assets/aicodemirror.png.
2026-11-10 19:48:10 +08:00
sususu98
905637daa3 Merge pull request #7413 from sususu98/feat/codex-compat-compaction-7406
fix(codex): support local compaction for compatible Responses endpoints
v8.0.64
2026-11-10 19:35:43 +08:00
Luis Pater
6876a2eb41 fix(claude): treat cli-bg x-app header as native claude code client
- Accept both cli and cli-bg in the native X-App header check so Claude Code background sessions preserve their native request identity instead of receiving the pinned device profile rewrite.
- Add unit and executor regression tests verifying native detection and passthrough for X-App: cli-bg across messages, streaming, count_tokens, and measured helper requests.

Closes: #7412
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-10 19:33:26 +08:00
sususu98
d576416a0d fix(compaction): strip text format constraints and configuration_update from summary requests
Clear top-level text format constraints and filter configuration_update control items when preparing local compaction summary payloads so structured JSON schemas do not overwrite the summary output.
2026-11-10 19:22:38 +08:00
sususu98
61f1ad5e3e fix(codex): support local compaction for compatible Responses endpoints
Handle compaction triggers and capsule replay locally for is-compat models while preserving native Codex behavior. Harden duplex cancellation, event ordering, response ownership, settings inheritance, model aliases, and credential failure classification.

Add HTTP, streaming, duplex, handler, usage, and deterministic concurrency regression coverage.

Fixes #7406
2026-11-10 19:22:38 +08:00
Luis Pater
f0c9c2d018 fix(claude): embed tool schemas with rejected property names in descriptions
- Detect input_schema property keys outside Claude's ^[a-zA-Z0-9_.-]{1,64}$ pattern by walking JSON Schema subschema positions in tools[] and inline tool_addition definitions.
- Replace affected schemas with an open object and embed the original schema in the tool description before payload rules, so parameters keep their exact names without request or response rewriting.
- Apply the fallback on execute, stream and count_tokens paths with regression tests for Responses and native Claude sources, MCP aliasing and payload-rule ordering.

Closes: #7389
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-10 18:51:42 +08:00
Luis Pater
46d48eb5af fix(openai): start responses websocket keepalive after upgrade
- Start a connection-scoped downstream Ping keepalive loop immediately after upgrading the Responses WebSocket connection instead of waiting for stream forwarding to begin.
- Guard background Ping writes with non-blocking mutex acquisition so active data writes are not contended while blocked Ping writes are still interrupted on terminal close.
- Preserve the socket cancellation cause in response forwarding and add regression coverage for post-upgrade, upstream-bootstrap, and blocked-Ping close paths.

Closes: #7407
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
2026-11-10 17:36:17 +08:00
Luis Pater
1855209dcd Merge pull request #7403 from router-for-me/home
fix(home): only renew liveness on heartbeat pong
2026-11-10 16:40:33 +08:00
Luis Pater
0e0cab0de6 fix(openai): inject placeholder reasoning_content for compat Claude tool calls
- Add a single-space reasoning_content placeholder on assistant tool-call turns without replayable thinking text when is-compat and request reasoning are active.
- Reconcile tool-call placeholder reasoning after canonical thinking resolution so model suffixes and capability normalization govern final inclusion before payload rules.
- Add unit and executor regression tests covering absent/whitespace thinking, disabled thinking, suffix overrides, and final payload overrides/filters.

Closes: #7398
Co-authored-by: Dylan <1990016@gmail.com>
2026-11-10 16:39:16 +08:00
sususu98
40e5a40fd8 Merge pull request #7397 from sususu98/fix/request-scoped-errors-usage-fail-code
fix(usage,auth): propagate request-scoped error rule classification to usage fail.code
2026-11-10 14:46:58 +08:00
sususu98
18883a57b4 fix(usage,auth): propagate request-scoped error rule classification to usage fail.code 2026-11-10 14:17:12 +08:00
hkfires
c9dad84703 fix(home): only renew liveness on heartbeat pong
Preserve an absolute heartbeat deadline across config,
cluster, and telemetry messages so ordinary subscription
traffic cannot mask a stalled heartbeat. Only an
empty-payload PONG renews liveness and resets reconnect
failures, and messages arriving after the deadline are
treated as timeouts
2026-11-10 13:19:09 +08:00
Luis Pater
13fdcc5e09 fix(thinking): recognize claude thinking.display updates in summary pipeline
- Treat thinking.display="updates" as an enabled reasoning summary mode when extracting Claude summary configuration so translated requests emit target visibility controls such as Antigravity includeThoughts.
- Preserve an existing "updates" display mode when applying enabled summary configuration back onto Claude request documents instead of overwriting it with "summarized".
- Add unit and cross-protocol translation regression tests for Claude thinking.display="updates".

Closes: #7393
Co-authored-by: Dylan <1990016@gmail.com>
2026-11-10 10:56:32 +08:00
Luis Pater
845345845b docs(config): document X-Session-ID guidance for full-history compaction under session affinity
- Document in config.example.yaml and RoutingConfig.SessionAffinity that Merkle LCP compaction matching requires at least 2 shared trailing turns.
- Note that clients whose compaction replaces all earlier turns with a summary should send X-Session-ID or another explicit session ID to preserve credential affinity.

Closes: #7390
Co-authored-by: Dylan <1990016@gmail.com>
2026-11-10 10:50:25 +08:00
Luis Pater
6db7d4b839 fix(claude): extend preserved thinking and per-turn timing gates to Claude Fable 5.2
- Include claude-fable-5-2 in preserved-thinking block binding so replayed signed thinking blocks default to drop_block on prefix mismatch.
- Consolidate 2.1.321 per-turn effort and timing model capability checks to cover Fable 5.2, Sonnet 5.5, and Mythos 5.2 while keeping Haiku 5.5 excluded from timing.
- Update the baseline software profile test failure message to match 0.128.0/v26.12.1 and add regression tests for 2.1.321 timing and preserved thinking.

Closes: #7386
Co-authored-by: Dylan <1990016@gmail.com>
v8.0.63
2026-11-10 08:28:13 +08:00
Luis Pater
1649a002aa Merge pull request #7392 from adamentwistle/fix/claude-cli-baseline-2.1.321
fix(claude): bump Claude Code CLI fingerprint baseline to 2.1.321
2026-11-10 08:20:59 +08:00