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>
Multiple concurrent requests can receive 429 simultaneously, causing
stop() to be called on an already-stopped limiter. Add .catch() to
prevent unhandled rejection.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a provider returns 429 (rate limit exceeded), the rate limit manager
was setting reservoir=0 and waiting for reservoirRefreshInterval before
releasing queued requests. For providers with long rate limit windows
(e.g. Codex with hours-long resets), this caused all queued requests to
hang indefinitely — they never timed out or returned an error.
This prevented upstream callers (e.g. LiteLLM) from triggering fallback
to alternative providers, effectively making the entire model unavailable
until the rate limit window expired.
Fix: on 429, call limiter.stop({ dropWaitingJobs: true }) to immediately
fail all queued requests, then delete the limiter from the Map so
getLimiter() creates a fresh instance for subsequent requests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add preserveDeveloperRole option and model compat override
- Normalize developer→system in roleNormalizer when not preserving
- Translator runs normalizeRoles for Responses API with option
- UI: ModelCompatPopover with do not preserve developer toggle
- Add ZWS_README_V2 documenting cause and fix
Made-with: Cursor
- fix(budget): BudgetTab sent integer percentage (80) but schema validated
fraction (0-1). Now divides by 100 on POST and multiplies by 100 on GET (#451)
- fix(combos): expose Agent Features UI in combo create/edit modal — fields for
system_message override, tool_filter_regex, and context_cache_protection were
implemented server-side (#399/#401) but missing from the dashboard UI (#454)
- fix(combos): strip <omniModel> tags from messages before forwarding to provider.
The internal cache-pinning tag was being sent to the provider, causing cache
misses as providers treated each tagged request as a new session (#454)
Normalize GitHub Copilot account tiers from the usage payload and hide misleading unlimited buckets so account type and limits render correctly in the dashboard.
Made-with: Cursor
DB Migrations (zero-breaking, ADD COLUMN DEFAULT NULL + new table):
- 005_combo_agent_fields.sql: system_message, tool_filter_regex, context_cache_protection on combos
- 006_detailed_request_logs.sql: ring-buffer table (500 entries) for full pipeline body capture
Features:
- #399 System Message Override + Tool Filter Regex per Combo
- applyComboAgentMiddleware() injected into handleComboChat/handleRoundRobinCombo
- Supports both OpenAI and Anthropic tool name formats
- #401 Context Caching Protection (Stateless)
- injectModelTag() appends <omniModel>provider/model</omniModel> to responses
- extractPinnedModel() reads tag from history and pins model for session
- #320 Auto-Update via Settings
- GET /api/system/version — current vs latest npm
- POST /api/system/update — fire-and-forget npm install + pm2 restart
- #378 Detailed Request Logs
- saveRequestDetailLog() captures bodies at 4 pipeline stages (opt-in toggle)
- GET/POST /api/logs/detail — list logs + enable/disable toggle
- #336 MITM Kiro IDE
- src/mitm/targets/kiro.ts: MitmTarget profile for api.anthropic.com interception
Merged! Excellent contribution @AndersonFirmino 🎉
This PR delivers four major improvements:
- **strict-random** strategy — Fisher-Yates shuffle deck with anti-repeat guarantee and mutex serialization for concurrent safety
- **API key controls** — allowedConnections, is_active, accessSchedule, autoResolve
- **Connection groups** — environment-based grouping view in Limits page with localStorage persistence
- **i18n** — 30 languages fully updated, pt-BR fully translated
655 tests passing. Merged with main (v2.4.4) — no conflicts. Thank you for the exceptional quality!
- New: open-sse/services/apiKeyRotator.ts — round-robin rotation
between primary API key + providerSpecificData.extraApiKeys[]
- Modified: open-sse/executors/base.ts — buildHeaders() rotates key
using getRotatingApiKey() when extraApiKeys configured
- Modified: open-sse/handlers/chatCore.ts — injects connectionId into
credentials to enable per-connection rotation index tracking
- Modified: providers/[id]/page.tsx — 'Extra API Keys' UI section in
EditConnectionModal: add/remove keys, persisted in providerSpecificData
T08 (quota window rolling) and T13 (wildcard model routing) confirmed
already implemented in accountFallback.ts and wildcardRouter.ts.
Fixes race condition in combo strict-random (concurrent requests could
reshuffle simultaneously). Eliminates code duplication between combo.ts
and auth.ts by extracting Fisher-Yates shuffle + deck logic into
src/shared/utils/shuffleDeck.ts with per-namespace mutex serialization.
- Combo layer: strict-random in combo.ts rotates models uniformly
- Credential layer: strict-random in auth.ts rotates connections/accounts
- Anti-repeat guarantee: last of previous cycle ≠ first of next
- Mutex serialization for concurrent request safety
- Independent decks per combo name and per provider
- allowedConnections: restrict which connections a key can use
- autoResolve: per-key toggle for ambiguous model disambiguation
- is_active: enable/disable key instantly (403 on disabled)
- accessSchedule: time-based access control (hours, days, timezone)
- Rename keys via PATCH /api/keys/:id
- Connection restriction badge in API keys table
- Auto-migration for all new columns
- Connection group field on provider connections
- Environment grouping view in Limits page (group by environment)
- Accordion UI with expand/collapse per group
- localStorage persistence for groupBy, autoRefresh, expandedGroups
- Smart default: auto-switches to environment view when groups exist
- Swap SessionsTab above RateLimitStatus
- strict-random option added to combo strategy dropdown (30 languages)
- strategyGuide.strict-random (when/avoid/example)
- pt-BR: translated all strategyRecommendations from English to Portuguese
- en: added API key management strings (accessSchedule, isActive, etc.)
- 11 tests: shuffle deck mechanics (Fisher-Yates, anti-repeat, decks)
- 6 tests: allowedConnections (schema, DB persistence, cache invalidation)
- 12 tests: API key policy (isActive, accessSchedule, autoResolve, budget)
* fix: tool description null sanitization, clipboard HTTP fallback fixes
T10 - Sanitize tool.description null in claude-to-openai translator
- claude-to-openai.ts: tool.description defaults to empty string when null/undefined
- claude-to-openai.ts: filter out tools with empty/missing names
- Prevents 400 validation errors on providers like NVIDIA NIM (issue #276)
T11 - Fix copy buttons to work on HTTP/non-HTTPS deployments
- Add src/shared/utils/clipboard.ts with HTTPS+HTTP (execCommand) dual fallback
- Migrate useCopyToClipboard.ts to use shared utility
- Migrate ConsoleLogViewer.tsx, RequestLoggerV2.tsx to shared utility
- Migrate HomePageClient.tsx, endpoint/page.tsx, GetStarted.tsx
- Migrate DefaultToolCard.tsx to shared utility
- Fixes copy buttons when OmniRoute runs behind HTTP proxy (issue #296)
T02 - Verified SSE [DONE] sentinel handling already correct
- sseParser.ts filters [DONE] on line 13 (no change needed)
- stream.ts uses doneSent flag to prevent duplicate sentinel
- bypassHandler.ts correctly separates streaming/non-streaming responses
Issue triage comments posted to #340, #341, #344
* feat: DB read cache + Accept header stream negotiation (T09/T01)
T09 - In-memory TTL cache for hot DB read paths
- Add src/lib/db/readCache.ts with TTL cache (5s settings/connections, 30s pricing)
- Eliminates redundant SQLite reads on concurrent requests
- Integrate invalidation in settings.ts updateSettings() and updatePricing()
- Integrate invalidation in providers.ts create/update/delete operations
- Export getCachedSettings, getCachedPricing, getCachedProviderConnections,
invalidateDbCache via localDb.ts for consumer migration
- Cache auto-busts on any write, preserving data consistency
T01 - Accept header stream negotiation
- src/sse/handlers/chat.ts: detect Accept: text/event-stream header
- Override body.stream=true when Accept header indicates streaming client
- Enables curl, httpx and SDK clients that use HTTP headers instead of JSON
body field to trigger streaming responses
- Logs Accept override at DEBUG level for observability
* fix: auto-advance quota window on expiry to prevent stale blocking (T08)
T08 - Quota Window Rolling Auto-Advance
- quotaCache.ts: add windowDurationMs field to QuotaCacheEntry interface
(optional field that callers can set when they know the window duration)
- Add advancedWindowResetAt() helper: if entry.nextResetAt is in the past,
eagerly returns { exhausted: false } so requests are unblocked immediately
- isAccountQuotaExhausted() now uses advancedWindowResetAt() instead of
the previous inline date check, and optimistically clears entry.exhausted
flag to avoid re-checking the same stale entry on the next request
Before: exhausted accounts with an expired resetAt would wait up to 5
minutes for the background refresh before accepting new requests.
After: the first request after resetAt passes will be immediately accepted
and will trigger a quota refresh on the next background tick.
* feat: manual OAuth token refresh UI (T12)
T12 - Manual Token Refresh UI
- Add POST /api/providers/[id]/refresh endpoint
- Validates connection exists and is OAuth type
- Calls getAccessToken() (same helper used in auto-refresh)
- Persists new credentials via updateProviderCredentials()
- Returns { success, expiresAt, refreshedAt } on success
- Update providers/[id]/page.tsx
- handleRefreshToken() with loading state (refreshingId)
- Pass onRefreshToken + isRefreshing props to ConnectionRow
- ConnectionRow: add optional onRefreshToken/isRefreshing props
- ConnectionRow: tokenMinsLeft state via lazy init (Date.now() in
getter fn, not in render body - satisfies react-hooks/purity)
- Token expiry badge: red 'expired' | amber '~Xm' (<30min) | hidden
- 'Token' button (amber) next to 'Retest' for OAuth connections
- Add en.json i18n: tokenRefreshed, tokenRefreshFailed
* Initial plan
* feat: integrate wildcardRouter into model alias resolution (T13)
T13 - Wildcard Model Routing
- Import resolveWildcardAlias from wildcardRouter.ts into model.ts
- In getModelInfoCore(), after exact alias check fails, try glob wildcard
alias matching (e.g., 'claude-sonnet-*' alias → 'anthropic/claude-sonnet-4')
- Returns { provider, model, extendedContext, wildcardPattern } on match
- Falls back to MODEL_TO_PROVIDERS lookup and openai default as before
* fix: clipboard cleanup and tool validation
* feat: media page UX + T04 playground uploads + T03 HuggingFace/Vertex AI
Media Page (MediaPageClient.tsx):
- Render images inline (img tags from b64_json or url)
- Show transcription as plain readable text (not raw JSON)
- Amber banner for credential errors with link to /dashboard/providers
- Detect empty transcription result and show credentials hint
- Provider credential hint below selector for non-local providers
- Extended provider/model lists: HuggingFace, Qwen TTS, Inworld, Cartesia, PlayHT, AssemblyAI
T04 - Playground File Uploads (playground/page.tsx):
- Audio file upload panel for transcription endpoint (multipart/form-data)
- Image upload panel for vision models (gpt-4o, claude-3, gemini, pixtral, llava...)
- Auto-detect vision models by name heuristic
- Inject uploaded images as base64 image_url in chat messages
- Inline image rendering for image generation results
- Readable text view for transcription results with copy button
- Preview thumbnails for attached images with individual remove
T03 - HuggingFace + Vertex AI Providers:
- HuggingFace: frontend providers.ts + backend providerRegistry.ts
Uses HuggingFace Router OpenAI-compatible endpoint
- Vertex AI: frontend providers.ts + backend providerRegistry.ts
Uses gemini format with generateContent API (urlBuilder fallback)
T07 - API Key Round-Robin: VERIFIED already implemented in auth.ts
fill-first, round-robin, p2c, random, least-used, cost-optimized strategies
* feat: T05 task-aware routing + fix#302 stream override + fix#73 claude provider fallback
T05 - Task-Aware Smart Routing:
- New open-sse/services/taskAwareRouter.ts:
Detects 7 task types: coding, creative, analysis, vision, summarization,
background, chat from system/user message content and images
Configurable taskModelMap per task type, stats tracking
applyTaskAwareRouting() integrates with existing chat pipeline
- New src/app/api/settings/task-routing/route.ts:
GET/PUT/POST API for task routing config + reset-stats + detect action
Persists config via updateSettings('taskRouting')
- Integration in src/sse/handlers/chat.ts:
applyTaskAwareRouting() called after policy enforcement, before combo resolve
Logs task type detection and model overrides
Fix#302 - OpenAI SDK stream=False drops tool_calls:
- src/sse/handlers/chat.ts T01 Accept header negotiation:
Changed condition from 'body.stream !== true' to 'body.stream === undefined'
OpenAI Python SDK sends 'Accept: application/json, text/event-stream' in every
request, even stream=False — the old code was incorrectly forcing stream=true,
causing tool_calls to be dropped from non-streaming responses
Fix#73 - Claude Haiku routed to OpenAI provider instead of Antigravity:
- open-sse/services/model.ts getModelInfoCore():
Added heuristic prefix detection before the blind 'openai' fallback:
claude-* models → antigravity (Anthropic) provider
gemini-*/gemma-* models → gemini provider
Closes: #73, partially addresses #302
* fix: token counts 0 (#74), model import dup (#180), model route fallback (#73)
fix#74 - Token counts always 0 for Antigravity/Claude streaming:
- open-sse/utils/usageTracking.ts extractUsage():
Add handler for 'message_start' SSE event which carries INPUT tokens in
Antigravity/Claude streaming:
{ type: 'message_start', message: { usage: { input_tokens: N } } }
This event was completely unhandled, causing ALL input token counts to be
dropped for every Antigravity/Claude streaming request
fix#180 - Model import shows duplicates with no visual feedback:
- src/shared/components/ModelSelectModal.tsx:
Added addedModelValues prop (string[]) to receive already-added model values
Models already in the combo now shown with ✓ indicator + green highlight
Makes it visually clear which models are already added vs new
- src/app/(dashboard)/dashboard/combos/page.tsx:
Pass addedModelValues={models.map(m => m.model)} to ModelSelectModal
* Harden clipboard UX and Claude tool normalization (#360)
* Initial plan
* chore: plan updates for clipboard and translator fixes
* fix: clipboard cleanup, copy feedback, and claude tool validation
---------
Co-authored-by: openai-code-agent[bot] <242516109+Codex@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: openai-code-agent[bot] <242516109+Codex@users.noreply.github.com>
