Redeploy f9a0aa1 — run 69's deploy job hit a Kubernetes API timeout
Run 69 built f9a0aa1, but its deploy job failed at 'kubectl create ns' with 'Timeout: request did not complete within requested timeout'. No code change.
An AI member's own chat session routes, budgets and meters as actor AI
Member chat (/api/ai/sessions/**, /ws/ai-chat) routed every member as HUMAN, so an AI member's session (its SP11 workstation browser) reached UNVERIFIED models,...
Member chat uses the Tool Plane with the member's own session; MCP server admin contract fixed
Member and widget chat routed, policy-checked and metered by the router stack
Realtime relay WebSocket with single-use tickets, session cap and metering
Realtime tickets — relay tickets in Redis or OpenAI ephemeral secrets
Ephemeral secrets are minted through the gateway's shared family walk (every dialled mint metered, a rejected key marks the provider, budget alerts after the ti...
Transcription and speech façades metered in audio seconds and characters
E4 POST /api/ai/v1/audio/transcriptions and E5 POST /api/ai/v1/audio/speech, each with its internal twin, on SP01's family adapters. The WAV-header duration wal...
Embeddings on the pinned model and rerank façades
Inputs and documents reach the model in batches it accepts (TEI refuses more than its client batch of 32 with 422; a reranker's maxDocuments); malformed fields ...
POST /api/ai/agent/step with tool use, thinking replay, cache breakpoints and SSE
OpenAI-compatible chat completions with tools, images, structured output and SSE
Internal router resolve endpoint
E1 POST **************** the ordered candidates and exclusions for a capability, 424 no_capability when none, 404 org_not_found for an org that is not live (rea...
Legacy routing, /internal/text and /internal/vision on the router, with provenance
The gate's AI-member path; retire the persona outreach engine
Quiet hours convert the service clock into the contact's zone instead of relabelling it (ruling SP03-T32).
Session/internal caller context, app gate, provenance and the gateway call runtime
Candidate walk with failover, one-shot parameter fallback and metered streaming
Provider credentials never reach the log, the usage row or the rethrown error; a failed provider-health write never costs an answer; an interrupt stops the walk...
Map a Studio config onto job-title charter items
SalesAgentCharterMapper maps a Sales Agent's AgentConfig onto job-title charter items (spec 4.7.8) for the fold-in, and the six Studio templates onto the A9 per...
Compile a charter into an operating brief and a job description
RRuleText words every rule CharterRRule accepts (month-day and monthly weekday lists, an hourly rule's days) and quotes one it cannot read, so a single stored r...
Hugging Face chat sends the tools and returns the tool calls
message.tool_calls, but HuggingFaceAdapter sent no tools (so tool_choice was dropped too) and never read tool_calls. Every HUGGINGFACE model therefore failed th...
The boot backfill counts row-less-by-design models apart
Every AIService start logged 'capability rows written for 21 model(s)' though completions models no capability Kamo uses (ruling SP01-T21), so they stay row-les...
A model list anyone can read no longer passes a wrong key
The Hugging Face router and OpenRouter answer GET /v1/models with 200 for no key and for a wrong key, so Test connection read OK and sync reconciled 140 models ...
Auto routing never picks a row-less model the catalogue says Kamo cannot call
The legacy router let a model with no capability rows through on the name rule legacy-completions *-instruct) get no rows by design, and their names pass the A...
An AI session or the System User holds no platform right in AIService
Master §11 'SP02 final fixes': a session whose intelligenceType is ARTIFICIAL resolves no platform right by any route (owner flag, god window, administrator row...
Family calls speak HTTP/1.1 on cleartext, never an h2c upgrade
The JDK client defaults to HTTP/2 and sends "Upgrade: h2c" with the first request to an http:// host. uvicorn (httptools) refuses the upgrade and drops the requ...
Chat, routing and the model picker run on the registry; capability backfill replaces the pricing backfill
Catalog and coverage, platform console API, internal registration and attestation, health sweep
Model endpoints — manual models, capability edits and verify, price rows, retire-not-delete
A context edit keeps an enabled LONG_CONTEXT in step, so the next capability write no longer restores the old value; a listed capability that needs details is r...
Provider endpoints on the registry — draft test, sync, verify, retire-not-delete, Provided-by-Kamo opt-out
Live capability probes — VERIFIED only from a passing probe; batch verify capped at 200
A chat probe fails on a 200 that is not a completion, names a failure as the connection check does (TLS included), cancels a call that runs out of time, and a 4...
Credentials from env or vault, org/platform visibility, platform-right authz, safe views, internal auth
Capability source precedence, the single capability writer, and the batch capability index
An adapter that denies TEXT_GENERATION speaks for the whole chat family; a switched-off LONG_CONTEXT never overwrites a reported context; remove leaves a tombst...
Deepgram, ElevenLabs, AssemblyAI, Cartesia families and the per-type adapter registry
Beyond the plan: the Perplexity chat check classifies failures as every other check does (spec 4.7.3); ElevenLabs and Cartesia refuse a missing voice and a voic...
Real model discovery for OpenAI-style, Anthropic, Google, Hugging Face, Ollama and catalogue-only vendors
Known-model catalogue (hints + unchanged prices) and name-hint classifier
Like what you see shipping?
All of it arrives in your workspace on its own. Start on the free plan and read this page again in a month.