Re-tab only — no logic changes. Follows the repo's tab-based formatting
for these files, matching the CommandCode executor/translator style.
Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
Per-provider textarea (one pattern per line: plain text or /regex/flags)
saved via /api/settings as streamErrorPatterns. Mirrors the existing
providerTimeouts load/save pattern.
- new open-sse/utils/streamErrorPeek.js: bounded peek of the first bytes of a
200 stream; configured pattern match → 502 so account/combo fallback can run
before any byte reaches the client (streaming included). Re-emits RAW bytes
so split multi-byte UTF-8 sequences survive the peek (never re-encode
decoded text — TextDecoder flush corrupts a lone leading byte to U+FFFD).
- chatCore: run the peek after executor.execute when the provider has
streamErrorPatterns configured; chat.js passes the settings through.
- commandcode executor: same raw-bytes fix in peekForUpstreamError + regression
test that fails against the old flush-based re-encode.
Upstream emits AI SDK v5 {"type":"error"} events inside an HTTP 200 stream.
The translator turned them into fake success content ([CommandCode error: ...]
+ finish_reason stop), so account/model fallback never fired and logs showed
Status: success.
- translator: error events now emit an OpenAI-shaped error chunk (chunk.error)
instead of content; parseSSEToOpenAIResponse already detects chunk?.error
- executor: peek the first events before committing the response; an early
error event returns 502 so fallback runs before any byte reaches the client
- Add CommandCode usage handler mirroring the official CLI /usage
(whoami → credits/subscriptions → summary) with 5h/weekly/monthly
quota rows, registered in services/usage.js and registry config
- Parse commandcode quota rows in ProviderLimits (remainingPercentage + $ unit)
- Match official CLI request shape: x-command-code-version 1.10.0,
User-Agent cli, and config.environment '${platform}-${arch}, Node.js ${version}'
- Fix connect timeout unit confusion: both profile and provider pages
now use ms with a 1s minimum guard (prevents 60ms footgun)
- Fix fetchT0 ReferenceError in base.js error path and log fetch
diagnostics only on upstream failure
- Quota Tracker defaults to the Active account filter
- Ignore .commandcode/ CLI local state
Map OpenAI image_url / Claude-style image blocks to the {type:"image",
image:"<data URI|url>"} shape the command-code CLI sends to /alpha/generate
instead of dropping them to "[image omitted]". Handles data URIs, raw base64
(with media_type / image/png fallback), and remote URLs.
- Promote bugs-gemini-cursor-commandcode "image content is preserved" from
it.fails to a real assertion (bug fixed)
- Add vision unit tests to openai-to-commandcode.test.js
- Add test-commandcode-vision.sh curl helper for live verification
Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
The provider lastUsed overlay loop referenced histRows before its const
declaration (temporal dead zone), throwing ReferenceError for 7d/30d/60d/all
which use the usageDaily summary path — leaving the overview cards and tables
empty regardless of the selected period. Merged the provider overlay into the
existing histRows loop.
- provider detail: Test All Models button runs every model (built-in + custom)
with an optional connection selector; failed models can be disabled in bulk
- bulk selected-model test now runs all connections in parallel (Promise.all)
- usage overview: new 'Usage by Provider' table view (default) and a Provider
column in Recent Requests; byProvider now tracks lastUsed
- combos: per-combo enable/disable toggle; disabled combos are skipped by the
routing engine (getComboModels/getComboModelsFromData) and model listing
- settings: 'Only show combo models' toggle filters ModelSelectModal and the
/v1/models response to models present in enabled combos
Remove "Ported from OmniRoute" and cockpit-tools attribution comments.
User-Agent strings and README/landing credits are left intact.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
openrouter, nvidia, gemini lack authModes, so dualAuthTypes on the
providers page defaulted to "oauth" and their apikey connections showed
as "No connections" on the freeTier card.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adds Poolside (inference.poolside.ai) as an API-key provider using the default OpenAI transport. Registers three Laguna models with reasoning capabilities (262K context, 32K max output).
Free-tier cards (e.g. kimchi, oauth-only) hardcoded "apikey" for stats and
toggle, so oauth connections were invisible on /dashboard/providers despite
showing on the detail page. Use dualAuthTypes per provider instead.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Vertex rejects orphan {} left when $ref/$defs are removed from function declarations. Promote empty nodes to object+reason placeholder in addPlaceholders.
Emit SSE error frame for unsupported Cursor AgentService IDE tools
instead of assistant content, and drop frames after the turn finishes
to avoid double-closing the stream controller.
Replace the fixed-table quota layout with flex rows that shrink cleanly,
keep the hidden-quota chip row from overflowing, and use thin mac-like
scrollbars app-wide.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Add a context-window selector on ClaudeToolCard that writes
CLAUDE_CODE_MAX_CONTEXT_TOKENS into settings.json (nudged 2K under the
labeled cap), and clear it on reset/default.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Update model lists and context lengths across free/apikey providers,
move bazaarlink, kilo-gateway, and kimchi into freeTier, demote llm7 to
apikey, and hide bluesminds, sambanova, zed, and mimo-free.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Default to the full agent with built-in tools, expose client function
tools as an MCP server, surface tool calls as OpenAI tool_use, resolve
workspace cwd from the request, and bump context windows.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Exchange Personal Access Tokens for short-lived job tokens, close the
SSE stream on terminal frames so non-streaming clients do not hang,
re-enable OAuth plus API-key auth modes, and replace the model catalog
with the current Qoder aliases.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Decode GetGrokCreditsConfig frames when REST billing returns empty
caps, so SuperGrok weekly quota shows in the usage dashboard.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Wire /v1/usages for Kimi (OAuth + API key) and balance API for DeepSeek,
flag both providers with usage/usageApikey, and normalize their quotas
in the dashboard ProviderLimits parser.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Use w-full instead of min-w-0/flex-1 + overflow-x-auto so the hidden
quota chips wrap cleanly instead of stretching the row.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Wire Devin CLI as a routed provider that spawns the local `devin acp`
binary. Add the DevinCliExecutor, register it in the executor map, expose
its status through the cli-tools batch endpoint and devin-settings route,
and document setup in cliTools constants.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Register 9 new upstream providers with logos and update the auto-generated
registry index. Refresh providers/alias baselines and extend the alias
token allowlist so verify-alias stays green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Rotating-RT providers (xAI/grok-cli) issue a new refresh_token on every
refresh; mutate credentials in-place so refreshWithRetry reuses the fresh
RT instead of the already-consumed one.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Add gemini-3.6-flash tiered (high/medium/low) for Antigravity routing
via upstreamModelId "gemini-3.6-flash-tiered(level)" + thinkingLevel,
plus gemini-3.6-flash and gemini-3.5-flash-lite direct API models.
- getModelUpstreamId: split (level) suffix before lookup, re-append after
- Antigravity executor: preserve transformed body.model
- MITM extractModel: parse thinkingLevel for tiered model (default medium)
- Isolate Cloud Code endpoints: discovery (loadCodeAssist/onboardUser/
quota) on PROD cloudcode-pa, chat transport on daily-cloudcode-pa
to bypass prod 429
Clear stale provider error code and account lock after a successful web
fetch (the core fetch handler never consumed the onRequestSuccess
callback), switch Jina Reader to its documented JSON POST request, and
parse the Title: metadata line before falling back to a Markdown heading.
Strip the generic dashboard model(level) suffix before resolving Kiro
synthetic -thinking/-agentic variants so the upstream request no longer
carries an invalid parenthesized model id. Map explicit levels to native
Kiro effort fields only for supported Claude/GPT model families, and stop
advertising native levels for unsupported legacy Kiro models. Applies to
both OpenAI→Kiro and direct Claude→Kiro routes.
Make PID cleanup conditional on the exiting child still owning the PID file so a stale exit cannot erase a replacement tunnel's PID. Only null the in-memory process when the exiting child is current. Explicit disable keeps unconditional cleanup.
Initialize initConsoleLogCapture() via Next.js instrumentation register()
hook so logs are captured from startup in headless/Docker deployments, and
add X-Accel-Buffering/Cache-Control headers to the SSE stream route to
prevent reverse proxies from buffering the initial payload.
Real Cursor IDE now uses AgentService at agent.api5.cursor.sh (HTTP/2-only)
while 9router still spoke the retired ChatService at api2.cursor.sh with
outdated headers, producing HTTP 429 "Update Required". Add an executeAgent
path that builds an agent.v1.RunRequest Connect RPC over a raw http2 stream
and fetches the account-specific usable model catalog via GetUsableModels.
Also implement MCP tool calling over AgentService: encode OpenAI tools as
AgentRunRequest.mcp_tools (McpToolDefinition with google.protobuf.Value
input_schema), decode McpArgs tool calls, and forward them to the client as
OpenAI tool_calls so the client runs the tool and resumes in the next turn.
Reply to request_context_args with a non-empty RequestContext, to server
heartbeats with client_heartbeat, and to KV blob get/set with empty results,
so action queries no longer stall the stream. Fold the client system prompt
into the user message (custom_system_prompt makes the server return an empty
turn). Bump clientVersion to 3.12.17 and add the x-cursor-client-commit
header so the gateway identifies as a current Cursor IDE release.
