* test(settings): add unit tests for debugMode and hiddenSidebarItems
Tests cover:
- PATCH debugMode=true/false
- PATCH hiddenSidebarItems with array values
- Combined updates with both fields
* test(e2e): add Playwright tests for settings toggles
Tests cover:
- Debug mode toggle on/off
- Sidebar visibility toggle
- Settings persistence after page reload
* fix(tests): address code review issues
- Unit tests: fix async/await for getSettings, use direct db functions
- E2E tests: remove conditional logic, use Playwright auto-waiting assertions
* feat(logging): unify request log retention and artifacts
* docs: add dashboard settings toggles to CONTRIBUTING
Add section documenting:
- Debug Mode toggle (Settings → Advanced)
- Sidebar Visibility toggle (Settings → General)
* fix(cache): only inject prompt_cache_key for supported providers
Only inject prompt_cache_key for providers that support prompt caching
(Claude, Anthropic, ZAI, Qwen, DeepSeek). This fixes issue #848 where
NVIDIA API rejected the parameter.
* fix(model-sync): log only channel-level model changes
* feat(providers): add 4 free models to opencode-zen
* feat(providers): add explicit contextLength for opencode-zen free models
* feat(providers): add contextLength for all opencode-zen models
* feat: Improve the Chinese translation
* fix: preserve client cache_control for all Claude-protocol providers
Previously, the cache control preservation logic only recognized a
hardcoded list of providers (claude, anthropic, zai, qwen, deepseek).
This caused OmniRoute to inject its own cache_control markers for
Claude-protocol providers not in that list (bailian-coding-plan, glm,
minimax, minimax-cn, etc.), overwriting the client's cache markers.
The fix checks both:
1. Known caching providers list (existing behavior)
2. Whether targetFormat === 'claude' (all Claude-protocol providers)
This ensures all Claude-compatible providers properly preserve client
cache_control headers when appropriate (Claude Code client, deterministic
routing, etc.).
Also removes unused CacheStatsCard from settings/components (duplicate
of the one in cache/ page).
Fixes cache token calculation for GLM, Minimax, and other Claude-compatible providers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: pure passthrough for Claude→Claude when cache_control preserved
The Claude passthrough path round-trips through OpenAI format
(claude→openai→claude) for structural normalization. This strips
cache_control markers from every content block since OpenAI format
has no equivalent, causing ~42k cache creation tokens per request
with zero cache reads.
When preserveCacheControl is true (Claude Code client, "always"
setting, or deterministic combo), skip the round-trip entirely and
forward the body as-is. Claude Code sends well-formed Messages API
payloads — the normalization was only needed for non-Code clients.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: restore CacheStatsCard — was not a duplicate
The first commit incorrectly deleted CacheStatsCard from
settings/components/ as a "duplicate". It's the only copy — both
settings/page.tsx and cache/page.tsx import from this location.
Restored the i18n-ized version from main.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(429): parse long quota reset times from error body
- Parse XhYmZs format from antigravity error messages (e.g., 27h41m36s)
- Dynamic retry-after threshold (60s default) instead of hardcoded 10s
- Add parseRetryFromErrorText() in accountFallback.ts for body parsing
- Fix 403 'verify your account' to trigger permanent deactivation
- Add keyword matching for 'quota will reset', 'exhausted capacity'
- Add unit tests for retry parsing and keyword matching
Fixes#858 (Antigravity 429 handling)
Fixes#832 (Qwen quota 429 - same underlying bug)
* chore: bump version to v3.4.0-dev
* fix(migrations): rename 013 to 014 to avoid collision with v3.3.11
* chore(docs): update CHANGELOG for v3.4.0 integrations
* fix: Claude token refresh, Antigravity quota, and 429 rate-limit handling
- Fix Claude OAuth token refresh to use form-urlencoded format (standard OAuth2)
- Add anthropic-beta header required by Claude OAuth API
- Switch Antigravity quota to use retrieveUserQuota API (same as Gemini CLI)
- Parse quota reset time for all providers (not just Antigravity)
- Add quota reset keywords to error classifier
- Cap maximum retry time at 24 hours to prevent infinite wait
Closes#836, #857, #858, #832
* fix(dashboard): resolve /dashboard/limits hanging UI with 70+ accounts via chunk parallelization (#784)
---------
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
Co-authored-by: R.D. <rogerproself@gmail.com>
Co-authored-by: kang-heewon <heewon.dev@gmail.com>
Co-authored-by: gmw <rorschach1167@qq.com>
Co-authored-by: tombii <github@tombii.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
- Add early return guard for missing accessToken in getGeminiUsage
- Add 10s fetch timeout (AbortSignal.timeout) on retrieveUserQuota calls
- Clamp used value with Math.max(0, ...) for non-negative display
- Use full accessToken as cache key instead of truncated prefix
- Replace catch(err: any) with instanceof Error check in models route
Replace stub getGeminiUsage() with per-model quota fetching from Google
Cloud Code Assist's retrieveUserQuota endpoint (same API the official
Gemini CLI /stats command uses). Fixes OAuth env var name, aligns model
list with official Gemini CLI VALID_GEMINI_MODELS, and makes "Import
from /models" discover new models via the quota endpoint.
Add a providerDiversity module that tracks provider usage distribution
using a rolling time window and calculates Shannon entropy normalized
to [0..1]. This enables the auto-combo scoring engine to factor in
provider diversity — boosting underrepresented providers to reduce
single-point-of-failure risk.
Key features:
- Rolling window with configurable size and TTL
- Shannon entropy calculation normalized to [0..1]
- Per-provider diversity boost for auto-combo integration
- Diversity report for dashboard display
- Full test coverage
Closes#788
Pre-existing any-budget violations in chatCore.ts (6), combo.ts (2), and
embeddings.ts (1 false positive in comment) — none introduced by GLM work.
Replace `as any` with `Record<string, unknown>` casts and reword comment.
Also removes docs/superpowers audit worksheet from git tracking (not part
of GLM Coding provider changes).
- Add missing glm-4.7-flashx variant to provider registry (confirmed in
Z.AI official GLM-4.7 overview docs as one of three variants)
- Remove glm-4.7/glm4.7 from tool calling denylist — official docs
explicitly show GLM-4.7 supporting function calling with tools param
- Add estimated pricing for glm-4.7-flashx ($0.3/$1.1) between free
Flash and standard 4.7 tiers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Models like antigravity/claude-sonnet-4-6 route through Google's internal
Cloud Code API which returns HTTP 400 when thinking/reasoning parameters
are included in the request body.
Changes:
- open-sse/services/modelCapabilities.ts: add supportsReasoning() function
with a denylist of known-unsupported patterns (antigravity/claude-sonnet-*)
and a registry-based lookup hook (supportsReasoning flag per model)
- open-sse/services/thinkingBudget.ts: in applyThinkingBudget(), add early
exit before the mode switch — if model string is present and
supportsReasoning() returns false, call stripThinkingConfig() immediately
regardless of the configured ThinkingMode
This is fully backward-compatible: models not in the denylist are unaffected,
and the supportsReasoning registry flag defaults to null (pass-through).
Fixes: HTTP 400 errors on antigravity provider when client sends requests
with thinking/reasoning budget parameters (e.g. claude-sonnet-4-6 via AG).
Co-authored-by: oyi77 <oyi77@github.com>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
* feat: auto-disable banned accounts setting with UI toggle
Add a configurable setting to automatically disable provider accounts
that return permanent/terminal errors (403 banned, ToS violation, etc.)
Changes:
- open-sse/services/accountFallback.ts: extend ACCOUNT_DEACTIVATED_SIGNALS
with AG-specific ban messages ('verify your account', 'service disabled
for violation')
- src/app/api/settings/auto-disable-accounts/route.ts: new GET/PUT endpoint
for the setting (enabled bool + threshold int)
- src/shared/validation/schemas.ts: updateAutoDisableAccountsSchema
- src/sse/services/auth.ts: in markAccountUnavailable(), capture result.permanent
from checkFallbackError() and — when autoDisableBannedAccounts is enabled and
backoffLevel >= threshold — set isActive=false on the connection
Default: disabled (backward-compatible). Enable via Settings UI or PUT
/api/settings/auto-disable-accounts { "enabled": true, "threshold": 3 }
Fixes: antigravity accounts with 403/Verify-your-account errors being
retried indefinitely in the rotation pool.
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
* fix: address reviewer comments for auto-disable (use getCachedSettings, immediate disable on permanent bans)
---------
Co-authored-by: oyi77 <oyi77@github.com>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
- Add `validateResponseQuality()` to detect empty/invalid 200 responses from
upstream providers in combo routing. Non-streaming responses with empty body,
invalid JSON, or missing content/tool_calls now trigger circuit breaker
failure and fallback to the next model instead of being returned to the client.
- Add missing `breaker._onSuccess()` calls in both priority and round-robin
combo paths. Previously failures accumulated without reset, causing premature
circuit breaker trips on healthy models.
- Update Cursor provider registry with Claude 4.6 model IDs (opus-high,
sonnet-high, haiku, opus + thinking variants). Keep 4.5 IDs for backward
compatibility.
- Update free-stack preset: replace duplicate qw/qwen3-coder-plus with
if/deepseek-v3.2 for better model diversity.
- Add paid-premium combo template for round-robin load distribution across
paid subscription providers (Cursor, Antigravity).
Made-with: Cursor
Non-streaming: Fixed json.messages check to use json.choices[0].message
(OpenAI format). Streaming: inject pin tag before finish_reason chunk for
tool-call-only streams. injectModelTag now appends synthetic assistant
message when content is null/array (tool_calls).
Reviewed and approved via consolidated analysis. GLM-5.1 addition and pricing corrections match official Z.AI pricing page. All 5 files follow existing patterns.
- Add glm-5.1 model to GLM Coding provider with fitness scores
- Update glm-5 pricing to match Z.AI API page ($1/$3.2/$0.2)
- Set glm-5.1 pricing to $1.2/$5/$0.3 per Z.AI
- Remove glm-4-32b (deprecated, returns empty from upstream)
- Rename Z.AI provider display name from "Z.AI (GLM-5)" to "Z.AI"
- Update zai pricing section to match glm pricing
After stripping <antThinking>/<thinking> tags from streaming responses, the
surrounding newlines were left as artifacts (e.g. \n\n\n\n). Now collapses 3+
consecutive newlines to double-newline after any tag removal.
Also fixes PR #625 merge (Provider Limits light mode background).
The sanitize TransformStream (commit 5a8c644) shared the same TextDecoder
instance with the upstream transform stream. This corrupted UTF-8 state
when decoding SSE chunks, producing garbled output that broke clients
like openclaw that parse the stream.
- Use a separate TextDecoder for the sanitize stream
- Always decode→encode in sanitize (don't mix raw passthrough with decoded text)
- Add flush() handler to emit remaining buffered bytes
- Fix double-escaped regex (\\n → \n) for tag stripping
- Replace hardcoded rgba(255,255,255,...) borders/backgrounds with theme-aware
CSS variables (--color-border, --color-bg-subtle) for proper light mode contrast
- Add dark: variants for hover states and progress bar backgrounds
- Fix Claude plan tier: try to extract actual plan from OAuth response instead
of hardcoding "Claude Code"
- Recognize provider names (Claude Code, Kimi Coding, Kiro) as non-plan-tier
values in normalizePlanTier() to avoid showing them as tier badges
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The <omniModel> tag was leaking into user-visible content when
context_cache_protection was enabled on a combo. The tag is an internal
marker for model pinning across conversation turns.
Fix: Add a second TransformStream pass (sanitize) that strips the tag
from SSE chunk content before delivery to the client. The tag is still
injected for round-trip context pinning but cleaned from visible output.
Also adds X-OmniRoute-Model response header as a cleaner metadata channel.
Closes#585
Changed the heuristic fallback for claude-* models from 'antigravity' to 'anthropic'
as the canonical provider. Users without Antigravity credentials were getting
'No credentials for provider: antigravity' errors when sending unprefixed
Claude model names like 'claude-sonnet-4-5'.
Closes#570
- Add contextLength field to RegistryModel interface for per-model overrides
- Add defaultContextLength to RegistryEntry for provider-level defaults
- Set context lengths for major providers:
- Claude: 200k
- Codex: 400k (fixes combo context display)
- Gemini: 1M
- OpenAI: 128k
- GitHub Copilot: 128k
- Kiro/Cursor: 200k
- OpenCode: 200k
- Include context_length in /v1/models API response
- Add context_length field to combo schema for custom combo context
- Update contextManager to use registry defaults and support env overrides
- CONTEXT_LENGTH_<PROVIDER> for per-provider override
- CONTEXT_LENGTH_DEFAULT for global override
This allows clients like OpenClaw to display accurate context windows
for combo models instead of guessing based on model name patterns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Cherry-pick from codex/omniroute-fixes-20260324:
- Replace MCP singleton transport with per-session architecture for Streamable HTTP
- Fix Claude passthrough via OpenAI round-trip normalization
- Add detectFormatFromEndpoint() for endpoint-aware format detection
- Support raw code#state in OAuth modal for Claude Code remote auth
- Expose cloudConfigured/cloudUrl/machineId in settings API
- Switch docker-compose.prod.yml target to runner-cli
- Add 3 new tests for round-trip and detectFormat
PR: #562
T01 (P1): requested_model column in call_logs
- Migration 009_requested_model.sql: ALTER TABLE call_logs ADD COLUMN requested_model
- callLogs.ts: INSERT + SELECT updated to include requestedModel field
T02 (P1): Strip empty text blocks from nested tool_result.content
- New stripEmptyTextBlocks() recursive helper in openai-to-claude.ts
- Applied on tool_result content before forwarding to Anthropic
- Prevents 400 'text content blocks must be non-empty' errors
T03 (P1): Parse x-codex-5h-*/x-codex-7d-* headers for precise quota reset
- parseCodexQuotaHeaders() in codex.ts extracts usage/limit/resetAt
- getCodexResetTime() returns furthest-out reset timestamp for safe unblocking
T04 (P1): X-Session-Id header for external sticky routing
- extractExternalSessionId() in sessionManager.ts reads x-session-id,
x-omniroute-session, session-id headers with 'ext:' prefix to avoid collisions
T06 (P2): account_deactivated permanent expired status on 401
- ACCOUNT_DEACTIVATED_SIGNALS constant + isAccountDeactivated() in accountFallback.ts
- Returns 1-year cooldown (effectively permanent) to prevent retrying dead accounts
T07 (P2): X-Forwarded-For IP validation
- New src/lib/ipUtils.ts with extractClientIp() and getClientIpFromRequest()
- Skips 'unknown'/non-IP entries in X-Forwarded-For chain
T10 (P2): credits_exhausted distinct account status
- CREDITS_EXHAUSTED_SIGNALS + isCreditsExhausted() in accountFallback.ts
- Returns 1h cooldown with creditsExhausted flag, distinct from rate_limit 429
T11 (P1): max reasoning_effort -> budget_tokens: 131072
- EFFORT_BUDGETS and THINKING_LEVEL_MAP updated with max: 131072, xhigh: 131072
- Reverse mapping now returns 'max' for full-budget responses
- Unit test updated to expect 'max' (was 'high')
T12 (P3): Model pricing updates
- MiniMax M2.7 / MiniMax-M2.7 / minimax-m2.7-highspeed pricing added
T15 (P1): Array content normalization for system/tool messages
- normalizeContentToString() helper exported from openai-to-claude.ts
- System messages with array content now correctly collapsed to string
fix(cli-tools): save real API key to CLI config files instead of masked string (#523, #526)
- claude-settings/route.ts: accept keyId, look up real key from DB (getApiKeyById)
- cline-settings/route.ts: same keyId resolution pattern
- openclaw-settings/route.ts: same keyId resolution pattern
- ClaudeToolCard.tsx: store key.id as selected value, send keyId in POST body
The /api/keys endpoint returns masked strings (first8+****+last4) which were being
written verbatim to ~/.claude/settings.json and similar config files, causing auth
failures on CLI tool launch.
fix(combo): update CACHE_TAG_PATTERN to strip surrounding \\n sequences (#531)
- comboAgentMiddleware.ts: non-global regex now matches literal \\n (backslash-n)
and actual newline U+000A that combo.ts injects around the <omniModel> tag.
fix(translator): preserve prompt_cache_key when translating Responses API requests
(#517) — prompt_cache_key is an account-affinity signal used by Codex for
prompt cache routing. Deleting it from the translated request prevented full
cache effectiveness. Removed delete from openai-responses.ts and
responsesApiHelper.ts cleanup blocks.
fix(combo): escape \n in tagContent so injected JSON string is valid (#515)
— omniModel tag content used template literal newlines (U+000A) which produce
unescaped newline chars inside a JSON string value. Replaced with literal \n
escape sequences for valid JSON injection in streaming SSE content chunks.
- #493: Fix custom provider model naming — removed incorrect prefix
stripping in DefaultExecutor.transformRequest() that broke org-scoped
model IDs like 'zai-org/GLM-5-FP8'
- #490: Enable context cache protection for streaming responses using
TransformStream to inject omniModel tag as final SSE content delta
before [DONE] marker
- #452: Add per-API-key request-count limits (max_requests_per_day,
max_requests_per_minute) with in-memory sliding window counter,
schema auto-migration, and Check 5 in enforceApiKeyPolicy()
Address bot review feedback: use .finally() instead of .then()/.catch()
so limiters.delete() runs regardless of whether stop() succeeds or
throws (e.g. already stopped by concurrent 429).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
