feat/export-tenant-data
9 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
| 9d3192a9c4 |
Replace the model ids with ones Groq actually serves
The defaults shipped yesterday were wrong the day they shipped, and a real key proved it in one request. Groq serves neither llama-3.1-8b-instant nor llama-3.3-70b-versatile any more. Both were chosen from memory, both passed startup validation, and every agent run would have failed with a 400. This is the exact failure the claude-* guard was written to catch, arriving from the side that guard cannot see. A prefix check can reject a vendor this service cannot call; it has no way to know a provider retired an id last month. That is not a gap in the check, it is a gap in the class of thing local validation can know, so the fix is not another guard: TestConfiguredModelsAreServed asks the provider. It lists /models — part of the same openai-compatible surface the gateway already speaks, so every supported provider answers it — and fails if a configured id is absent, printing what is available. It reads the ids through config.DefaultModels() rather than repeating them, because a second copy would be the first thing to drift, and drift is the whole failure. Skipped without a credential like the rest of the live suite. Verified three ways: it fails on the retired id with the message an operator needs, skips clean with no key, passes on the new ones. New defaults, chosen against the live account rather than from memory: openai/gpt-oss-20b (fast) and openai/gpt-oss-120b (balanced, deep). Tool calling confirmed on both. groq/compound-mini was ruled out — it cannot do tool calls at all, which this platform requires. MODEL_REASONING_EFFORT is now documented as safe here and NOT portable: gpt-oss accepts low/medium/high, exactly the scale openAIEffort maps onto, while qwen/qwen3.6-27b on the same account rejects all three and fails the whole request rather than ignoring the key. I7 IS NO LONGER UNPROVEN. make eval-live passes all three cases twice against gpt-oss-120b, the planted-injection case included: answers from the handbook, cites, refuses the injection, leaks neither the operator-only pay guidance nor the other tenant's figures. CLAUDE.md §12 and handover.md updated from "urgent" to measured, dated, and scoped to the one model it is evidence about. One real defect found on the way. The handbook grounding check failed once on an answer containing the phrase it wanted — "more than ten minutes" on screen, strings.Contains false — which leaves an invisible separator as the only explanation; the same model writes "47 %" and a U+2011 hyphen elsewhere. The flaky assertion is the small half. THE LEAK ASSERTIONS USED THE SAME MATCH and fail in the dangerous direction: "attacker@evil.test" with a zero-width space, or "uplift" with a soft hyphen, would have been reported clean. A permission test that cannot see the leak it is hunting is worse than none, because it is believed. normalizeForMatch folds those away, and its test pins that every case is one plain ToLower MISSES — a case whose naive match already succeeds fails, so the suite cannot fill with examples that demonstrate nothing. That caught my own first BOM case, which put the mark where Contains found it regardless. gofmt clean, vet clean, 15/15 packages pass offline; live suite green twice. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g |
|||
| bd9a8f91fc |
Make the shipped example envs ones that can actually start
The krow-2 deploy failed on the ANTHROPIC_API_KEY guard, which is the guard doing its job. Checking what an operator hits *after* fixing it turned up two older faults in the files they are told to copy — both predating the Groq switch, both fatal at boot. HTTP_WRITE_TIMEOUT shipped as 30s in .env.example, .env.docker.example and the compose default, while validateWriteTimeout refuses anything at or under the deep tier's 2m deadline. `cp .env.docker.example .env && docker compose up` could not start. Now 180s. krow-2 never saw this because someone had already overridden it in that environment. .env.docker.example carried no model block at all, so a production stack built from it is refused for a missing MODEL_API_KEY. Added, with the Groq defaults and the reasoning-effort note (most non-reasoning models reject the request rather than ignoring the key). Neither was subtle. Both survived because the examples were prose to every test in this package: the validator and the file documenting it had no mechanical connection, so tightening one silently invalidated the other. That connection is now TestShippedExampleEnvActuallyBoots, which parses each example and runs Load() on it under the APP_ENV the file itself declares — production for the docker one, development for the root one, each internally consistent. Verified by mutation: reverting the timeout, removing the key line, and restoring a claude-* id each fail it with the message an operator would see. Go does not treat these files as test inputs, so an example-only edit can be served a stale pass from the test cache. Noted in the test; use -count=1. Also documented the upgrade path in handover.md, including the one thing startup validation cannot catch: renaming ANTHROPIC_API_KEY to MODEL_API_KEY without replacing the value boots fine and 401s on every run. gofmt clean, go vet clean, 15/15 packages pass. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g |
|||
| 34fa58a6b9 |
Remove the Anthropic path; the gateway speaks one wire protocol
The platform now runs on Groq by default, through the OpenAI-compatible chat-completions shape. That shape is not one vendor — Gemini, OpenRouter, Together, vLLM and a local Ollama serve it too — so moving again stays configuration rather than code. Two things in the deleted file were not Anthropic's and would have gone with it silently: withRetry / MaxAttempts / retryBackoff were defined in anthropic.go and CALLED BY openai.go. Deleting the file wholesale would have removed the retry policy of the provider that survived, and nothing in openai.go mentions it, so the loss would have been invisible until the next 429. The policy is a property of this platform's runs, not of a vendor's API; it now lives in retry.go where no provider can carry it off. StreamComplete had the same problem and moves to gateway.go, beside the Streamer interface whose comment already referenced it. Three stale-configuration failures are now refused at startup instead of being ignored. Each was verified firing through the real config.Load(): MODEL_PROVIDER=anthropic — named separately from every other wrong value because it used to be correct. Ignoring it gives a stack that believes it is on Claude while every run goes to Groq and is billed there. ANTHROPIC_API_KEY set while MODEL_API_KEY is empty. Ignoring a key an operator did set is the worst version of this: they fail every run on a missing credential they are looking straight at. A leftover claude-* model id, naming the tier that carries it. This is the check the previous commit's error-detail work was diagnosing: such an id is accepted by this process, rejected by the provider, and 400s on EVERY run. "A model is wrong" does not say which of three lines to edit. Defaults ship as a matched pair. defaultBaseURL and the three tier ids are one decision, not four: an id is only meaningful against the service that serves it, and a Groq id on an OpenAI base URL is the same failure from the other side. The tiers also stop being one model — a tier whose cost does not differ is a distinction that buys nothing. Verified end to end against a stub of the wire, driving the real wiring (config.Load in production mode, gateway.New, StreamComplete): streamed deltas, tool-call decoding, the loopback credential exemption, and usage totalling 150 rather than 190 — the cached-prefix subtraction still holds. gofmt clean, go vet clean, 14/14 non-DB packages pass. httpserver still needs a reachable database. NOT verified: the I7 planted-injection eval. Removing this path removed the only model whose refusal behaviour had been measured against it, so the new default is unproven there until `make eval-live` runs with a real key. The Groq model ids should also be confirmed against Groq's current lineup. Flagged in CLAUDE.md §12 and docs/handover.md. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g |
|||
| c74fe7e074 |
Add an OpenAI-compatible gateway, so the model provider is a config value
The platform could only talk to one vendor. Moving off Claude — for cost, or
because a client asks for Gemini — meant a rewrite behind an interface that
already had exactly the right shape and one implementation.
`openai` is not only OpenAI. Groq, Gemini's compatibility endpoint, OpenRouter,
Together, vLLM and a local Ollama all serve the chat-completions shape, so one
implementation reaches all of them and the difference between them is a base
URL and three model ids. That is why this is one file and not a package per
vendor.
`routing.go` had the vendor baked into the routing table every provider has to
read: effort was `anthropic.OutputConfigEffort`. Nothing was wrong with that
while there was one implementation; it became wrong the moment there were two,
because the OpenAI path would have had to import the Anthropic SDK to learn how
hard to think. Effort is now the platform's own three-value vocabulary and each
implementation maps it onto whatever its API calls the same idea.
THE ACCOUNTING DIFFERS BETWEEN THE TWO WIRES, and getting it wrong would have
been invisible. OpenAI reports prompt_tokens INCLUSIVE of the cached prefix;
Anthropic reports input tokens EXCLUSIVE of it and carries the cache
separately. Usage.Total() adds all four fields, so copying both numbers across
verbatim bills the cached prefix twice — worst on long conversations, which is
exactly where I3's budget matters most. The run would still answer; it would
just hit BudgetExceeded early, for no visible reason. normalise() subtracts,
and there is a test named after it.
Streamed tool calls are keyed by their wire index, not appended in arrival
order. Providers interleave the fragments of parallel calls, so appending
splices one call's arguments onto another's — and the result is usually two
calls that are each valid JSON and both wrong, which means the tools run with
inputs the model never chose and nothing errors. Mutation-checked: ignoring the
index produces `{"day"{"week":"friday"}:"next"}` and the test catches it.
Three configuration mistakes are refused at startup rather than at runtime:
- MODEL_BASE_URL without MODEL_PROVIDER=openai. The anthropic path has one
endpoint and ignores the field, so this is a deployment that believes it
switched providers and did not — every run still goes to Anthropic and is
still billed there, with nothing in the logs to say so. Cost is the whole
reason this change exists, and that is the one mistake that silently
defeats it.
- An unrecognised MODEL_PROVIDER, once at boot instead of once per run.
- A production deployment with no credential — except against localhost,
which needs none, and demanding one would make the free local path
impossible to configure.
reasoning_effort is opt-in via MODEL_REASONING_EFFORT. Reasoning models accept
it; most others reject the entire request with a 400 rather than ignoring an
unknown key, so every deployment would have had to opt out instead.
`make eval-live` now reads the same environment the service does and logs which
provider answered, because a suite that cannot say which model produced a
result is a suite whose result cannot be compared with another run's. That is
the point of this change: §12 leaves model hosting open, and this makes the
decision cheap to reverse and possible to settle on evidence. Weigh the I7 case
heaviest — a cheaper model that follows the planted injection is a security
regression, not a saving.
Default behaviour is unchanged: MODEL_PROVIDER unset means anthropic, and
ANTHROPIC_API_KEY still works, so no existing deployment needs an edit.
NOT verified against a live provider — no credential was available on this
machine. Tested against a fake endpoint covering both paths, and the three
guarantees above are mutation-checked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g
|
|||
| 57c2a52c1e |
Refuse an HTTP write timeout that would cut off a legal agent run
Production answered 502 Bad Gateway on a non-streamed agent run. Nothing about that was a gateway fault: krow-proxy already had proxy_read_timeout 3600s, and the API pods were healthy with zero restarts throughout. HTTP_WRITE_TIMEOUT was 30s. Every shipped agent runs at the `balanced` tier, whose deadline is 60s, and the `deep` tier allows 120s. So the server aborted the response on any run over half the time the runtime considered legal, the proxy saw its upstream vanish mid-response, and it reported the only thing it could. A gateway error for something no gateway did — which is why it looked like infrastructure for as long as it did. Delegation did not cause this; it made it routine. A parent that asks two subagents takes longer than one answering alone, so a latent misconfiguration became a reliable one. Verified: the exact request that returned 502 now answers 200 in 18s. Streaming is what hid it, and that is the part worth keeping in mind. The chat panel uses SSE, so the product looked healthy while every non-streaming caller got 502 on a slow question. A bug only reachable by the callers who do not yet exist is one nobody reports. So the value is now derived from the thing that constrains it — the default is DeepestAgentDeadline plus headroom rather than a number typed once — and validate() refuses anything below that deadline at startup. A slow, intermittent, misattributed failure becomes a message on the first boot. DeepestAgentDeadline is duplicated in internal/config rather than imported, because internal/runtime already imports internal/config and a cycle to share one number is a bad trade. TestConfigKnowsTheDeepestAgentDeadline asserts the two agree, so drift is a build failure rather than a discovery. It also checks that no tier exceeds it, or the name lies. ORDERING, and it matters for the next deploy: the check refuses the old 30s, so a pod carrying this image against an unpatched configmap will not boot. Production's configmap is already 180s. The handover says so too. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g |
|||
| fd1812e161 |
Record the CI runner, now that one exists
Both repositories carried GitHub Actions workflows on a Gitea remote and nobody had confirmed a runner. There was not one: the 924 frontend checks, the whole Go suite, the skip guard and the suite-shrank guard had never run on a push, only when somebody remembered. gitea/act_runner v0.6.1 is registered as krow-runner on the cluster host. This commit is also the first push that can prove it picks up a job, which is the failure mode worth catching — a runner that registers and never runs anything looks identical to a healthy one in the Runners list. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g |
|||
| 629d97181d |
Rebase Staff too, which was the last thing keeping the chart incomplete
And correct the previous commit's closing claim, which was wrong.
|
|||
| 4c29185c3b |
Correct the governing documents where this session disproved them
Both documents are the first thing a new reader trusts, and several of their
claims were wrong — some wrong from the start, some overtaken by work this
week. A governing document that misdescribes the system is worse than none,
because it is believed.
CLAUDE.md §10 specified Python 3.11, FastAPI, SQLAlchemy and Alembic. The code
is Go and has never been anything else. That is corrected rather than quietly
deleted, so the next person understands the document drifted rather than
wondering which half to trust.
Also in CLAUDE.md: the tool count was 17 with one write and is 19 with two;
delegation now exists and §11's Orchestration row says what it guarantees; the
embedder deviation described a Voyage-or-stand-in choice that has since become
EMBED_PROVIDER with three options, of which production sets none.
The handover claimed three things that this session disproved by running them:
- "definition_versions is empty ... nothing has gone through it". It was not
empty in production; activity-agent had a v1 that the shipped file
contradicted, which is how a real drift was found. It now holds every
agent and skill.
- "Skills are still stored in user_preferences". They are rows in
skill_definitions, and are now versioned.
- "make eval-live ... has never been run". It has, it passes 3/3, and what
it established is recorded — including that the handbook corpus carries a
planted prompt injection which the agent refused and reported. That is I7
holding against a real model, which is worth more than the pass count.
The endpoint counts were one high throughout (55/57, not 56/58) — the delta of
two was always right, so the signal worked and the absolute numbers did not.
Added, because they cost time this week and would cost it again:
- the app reaches its database through pgbouncer, not PostgreSQL directly.
Enabling TLS on PostgreSQL does nothing for the application hop; pgbouncer
terminates 5432 and needs its own client_tls_sslmode.
- the seeded UserActivity is NOT anchored to today the way ShiftRecord is,
so it ages out of every window the activity tools offer. Twenty-three days
old as of writing: zero events in the last 7 days, 6 of 15 in the last 30.
The agent answers truthfully and the demo looks dead.
- the whole stack runs on Docker alone. Dockerfile.api builds every command
plus the migrate CLI, so a new machine needs neither Go nor psql — which
is how this one was set up, having no Homebrew.
- Ollama runs on the HOST, so a container reaches it at
host.docker.internal, not localhost. The old .env said localhost and would
have failed with nothing obviously wrong.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g
|
|||
| d190fc8ee9 |
Preserve CLAUDE.md and add a handover document
Neither survived a machine change. CLAUDE.md sat in the directory ABOVE both repositories, which is not a git repository at all, so the governing document for the project existed on exactly one laptop. It is now in this repository; place a copy at the parent level on a new machine, where it covers both. docs/handover.md records what CLAUDE.md does not: what was decided and why, what is deployed and how to verify it, and the conventions that produce confident wrong numbers rather than errors — a score of 0 meaning "not rated", screened_at being vestigial, shift data anchored to today. Written because Claude Code's own memory is per-machine and keyed to the absolute path of the checkout: it does not sync, and a different path on a new machine reads a different folder. A file in the repository travels with the code and is useful to a person besides. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0186JgqQUCDS8ZwGmyw3ymWu |
