Commit Graph
2779 Commits
Author SHA1 Message Date
elky 668bf5e40f test(data): include latest migration snapshot 2026-09-03 12:27:12 +08:00
elky 77f93c638d Merge codex/routing-strategy-consolidation into main 2026-09-03 12:00:51 +08:00
elky d0c0996b9f Merge origin/main into provider billing form fix 2026-09-03 11:36:49 +08:00
fawney 2cb4d554aa feat(routing): consolidate scheduling strategy configuration 2026-09-03 11:05:59 +08:00
elky 214f3d6406 fix(providers): hide billing fields in provider form 2026-09-02 23:17:01 +08:00
fawney e8d9877b79 Merge remote-tracking branch 'origin/main' 2026-09-02 22:08:36 +08:00
fawney19 cae9aa4134 Merge pull request #784 from fawney19/worktree-linear-enchanting-bunny
feat(routing): move sticky-key retries into routing policy with lazy attempts
2026-09-02 20:56:03 +08:00
elky 7323d41fbe feat(routing): move sticky-key retries into routing policy with lazy attempts
Replace the provider/endpoint max_retries fields as the source of same-key
retries with a routing policy setting, sticky_key_attempts (default 2). Only
the first-ranked candidate is retried on the same key; every failover
candidate gets a single attempt so failover keeps advancing instead of
retrying each fallback key.

Materialize exactly one attempt per candidate and derive same-key retries in
the attempt loop after a candidate-scoped failure, so the retry budget no
longer inflates up-front materialization and needs no upper bound. The budget
travels in the report context; retries reuse the plan with a fresh candidate
id and incremented retry index. Pool groups only retry their first key within
the retry-index stride.

Expose the setting in the routing profile editor and the set_scheduling rule
action, and drop the max_retries input from the provider form.
2026-09-02 20:48:40 +08:00
fawney19 e3644c6142 Merge pull request #779 from fawney19/worktree-linear-enchanting-bunny
feat(routing): make routing profiles the sole scheduler policy source
2026-09-02 17:16:57 +08:00
elky 415b2da81b feat(routing): make routing profiles the sole scheduler policy source
Bootstrap an enabled system-default routing group from the legacy
scheduler config keys on startup, resolve the default ordering config
from that group before falling back to the legacy keys, and stop merging
keep_priority_on_conversion with the legacy flag when a policy is
resolved. Thread the policy-derived ordering config into candidate
preselection so it no longer reads system config independently.

Add per-API-format key priority overrides so a key serving several
formats keeps independent ordering, matching the legacy
global_priority_by_format semantics. Expose keep_priority_on_conversion
in the routing profile editor and read the effective policy in the
model routing preview, monitoring metrics and provider page badge.
2026-09-02 17:04:04 +08:00
elky 166236c2ee Merge origin/main into CI dependency fix 2026-09-02 12:30:31 +08:00
ZheFox 0371a961d6 Merge pull request #777 from zhefox/main
Fix detection of DeepSeek custom relay models in gateway
2026-09-02 11:24:55 +08:00
ZheFox 144a28f544 feat(admin-users): add plan entitlement revocation flow 2026-09-02 11:23:24 +08:00
elky 611c29f1f5 ci: install VSCodex web dependencies in nightly build 2026-09-02 11:17:06 +08:00
ZheFox 6540c1e46a Merge branch 'fawney19:main' into main 2026-09-02 10:26:07 +08:00
ZheFox 24bf92a8bf Merge pull request #776 from zhefox/fix/deepseek-reasoning-text-replay
fix(gateway): detect DeepSeek custom relay models
2026-09-01 23:04:51 +08:00
zhefox 7ae984df4b fix(gateway): detect DeepSeek custom relay models 2026-09-01 22:49:35 +08:00
zhefox e2154629ca fix(gateway): detect DeepSeek custom relay models 2026-09-01 22:49:25 +08:00
ZheFox 0bfd48b9db Merge pull request #774 from Kayphoon/codex/fix-openai-responses-ping
fix(formats): ignore Responses ping stream events
2026-09-01 22:17:18 +08:00
Kayphoon 88d2b002be fix(formats): ignore Responses ping stream events 2026-09-01 12:58:21 +00:00
fawney 30a75832f8 feat(vscodex): add remote Codex collaboration module 2026-09-01 20:25:35 +08:00
fawney 5059093d29 feat(vscodex): add remote Codex collaboration module 2026-09-01 20:08:36 +08:00
ZheFox 5a69cfe40d Merge pull request #772 from zhefox/main
fix(gateway): handle pool saturation and malformed Gemini calls
2026-09-01 19:31:44 +08:00
ZheFox 3d87bbf230 style(rust): apply workspace formatting 2026-09-01 19:31:13 +08:00
ZheFox 633363e190 fix(gateway): handle pool saturation and malformed Gemini calls 2026-09-01 19:25:00 +08:00
fawney19 715f2773c3 Merge pull request #773 from fawney19/codex/codex-fingerprint-convergence
refactor(codex): generalize fingerprint convergence
2026-09-01 17:27:04 +08:00
elky d07dc86376 refactor(codex): generalize fingerprint convergence 2026-09-01 17:05:54 +08:00
elky ef7caa40e7 ci: publish nightly builds from main 2026-09-01 16:43:29 +08:00
fawney19 7fb8d5fc0a Merge pull request #771 from fawney19/codex/codex-context-stability
Merge Phase 1 Codex context and fingerprint convergence changes.
2026-09-01 16:07:41 +08:00
elky 3e540ce589 fix(gateway): route Codex context through transport facade 2026-09-01 15:53:47 +08:00
ZheFox 6c71f87589 fix(frontend): align Antigravity quota summaries 2026-09-01 15:38:00 +08:00
elky a39048ecce feat(codex): stabilize identity across retries 2026-09-01 15:33:40 +08:00
ZheFox b538aa2d66 Merge pull request #770 from zhefox/main
fix(pool): show Antigravity quota reset times
2026-09-01 12:09:41 +08:00
ZheFox 57abb20778 fix(pool): show Antigravity quota reset times 2026-09-01 11:29:48 +08:00
ZheFox d117a0cd13 Merge pull request #769 from zhefox/main
fix(pool): restore Antigravity quota progress bars
2026-09-01 10:43:05 +08:00
ZheFox ee55f46962 fix(pool): restore Antigravity quota progress bars 2026-09-01 10:40:37 +08:00
ZheFox 9210502e77 Merge pull request #768 from zhefox/main
fix(pool): isolate model quotas and compact account display
2026-09-01 10:20:09 +08:00
ZheFox 2fe2600021 fix(pool): isolate model quotas and compact account display 2026-09-01 10:15:57 +08:00
ZheFox 9b819169d5 Merge pull request #767 from zhefox/fix/provider-key-concurrency-cache-affinity
fix(gateway): improve provider pool concurrency, quotas, and affinity
2026-09-01 08:11:46 +08:00
ZheFox 9631b229b3 fix(gateway): add provider key concurrency and cache affinity modes 2026-09-01 08:06:58 +08:00
ZheFox 9372d6cfa5 Merge pull request #765 from Brisbanehuang/codex/usage-api-template
feat(provider-ops): 新增通用 API Key 用量查询模板
2026-08-29 23:23:06 +08:00
Brisbanehuang 4dbf98163e feat(provider-ops): add generic usage API template 2026-08-29 09:04:05 -04:00
ZheFox 6ec0771297 Merge pull request #764 from zhefox/main
fix(gateway): route Responses compaction only to Responses providers
2026-08-29 12:56:32 +08:00
zhefox 56395945c0 fix(gateway): route Responses compaction only to Responses providers 2026-08-29 12:28:55 +08:00
ZheFox 8032497045 Merge pull request #763 from zhefox/main
Fix response reasoning summaries for Chat
2026-08-29 11:54:15 +08:00
zhefox b35364d7fd fix(antigravity): normalize private search tool name 2026-08-29 11:09:15 +08:00
ZheFox f085fdf918 Merge pull request #762 from zhefox/main
fix(gemini): normalize mixed tools for same-format providers
2026-08-29 08:48:56 +08:00
ZheFox 36daba7a34 fix(antigravity): align tool schema wire fields 2026-08-29 08:45:19 +08:00
ZheFox 9837ce1197 fix(antigravity): use Gemini schema field for tools 2026-08-29 02:50:07 +08:00
ZheFox 1bc2287baa fix(gemini): normalize mixed tools for same-format providers 2026-08-29 01:08:01 +08:00