Commit Graph
10 Commits
Author SHA1 Message Date
Paweł Banaszewski 1a8a153c56 chore: fix flake in TestResponsesInjectedTool (#25630)
Fixes flake in TestResponsesInjectedTool.
See
https://github.com/coder/coder/pull/25630/changes/d9bfeb20092129127ad5e7958c5b8dbf46740527
for reproduction.
Due to AsyncRecorded token usages may be recorded in different order
then expected.

Fixes: https://github.com/coder/internal/issues/1544
2026-05-25 16:41:55 +02:00
Ethan c650aabbef chore: standardize on *_internal_test.go for white-box tests (#25601)
My agent added `//nolint:testpackage` to a test file on one of my PRs.
Again. This PR cleans it up across the entire repo and updates the
in-repo conventions so future agents stop doing it.

The repo already has a precedent for white-box tests that need to touch
unexported symbols: `*_internal_test.go` (145+ existing files). The
`testpackage` linter's default `skip-regexp` exempts that filename
suffix, so the `//nolint:testpackage` directive is unnecessary in every
case where someone reached for it. This PR renames 51 such files to
`*_internal_test.go` via `git mv` so blame and history follow, and
strips the dead directive from 2 files that were already correctly named
(`coderd/oauth2provider/authorize_internal_test.go`,
`coderd/x/chatd/advisor_internal_test.go`).

`.claude/docs/TESTING.md` now documents the rule explicitly under *Test
Package Naming*, which is imported into the root `AGENTS.md` via
`@.claude/docs/TESTING.md`. The rule: prefer `package foo_test`; if you
need internal access, rename the file to `*_internal_test.go` rather
than adding a nolint directive.
2026-05-22 20:24:38 +10:00
Paweł Banaszewski c0b4180206 fix: fix race in setupInjectedToolTest (#25455)
Fixes race condition in `setupInjectedToolTest`.

To reproduce add short sleep to AsyncRecorder.RecordToolUsage method
(inside newly spawned go-routine):
https://github.com/coder/coder/blob/46821525f7d2f7466735463898fb6e054c169f85/aibridge/recorder/recorder.go#L254-L258

Upstream request counter can reach 2 while no recording has been done
since asyncRecorder does it asynchronously:
https://github.com/coder/coder/blob/46821525f7d2f7466735463898fb6e054c169f85/aibridge/internal/integrationtest/setupbridge.go#L242-L244

Added consuming request to `setupInjectedToolTest` so
`newInterceptionProcessor` handler finishes before returning from
`setupInjectedToolTest` which guarantees that all recordings are done:
https://github.com/coder/coder/blob/46821525f7d2f7466735463898fb6e054c169f85/aibridge/bridge.go#L282

Fixes: https://github.com/coder/internal/issues/1526
2026-05-19 09:36:38 +02:00
Marcin Tojek 38772bdb7c refactor: remove cache tokens from ExtraTokenTypes (#25118)
Fixes: https://github.com/coder/aibridge/issues/243

> Generated with [Coder Agents](https://coder.com/agents)
2026-05-18 11:30:19 +02:00
Susana Ferreira b6dacb4a3c feat: add automatic key failover for AI Bridge OpenAI (#24847)
## Description

Adds automatic key failover for centralized OpenAI provider, covering both chat completions and responses APIs. Same shape as the Anthropic PR: each upstream call walks the configured key pool, keys are marked **temporary** on 429 (with cooldown from `Retry-After`) and **permanent** on 401/403. Each agentic-loop iteration gets its own fresh walker so a tool-call continuation can fail over independently of the initial request.

BYOK is unchanged: BYOK requests run as a single attempt with no failover.

## Changes

- `config.OpenAI` carries a `KeyPool`. `Key` remains for BYOK Authorization Bearer set per interception.
- Chat completions blocking interceptor: walks the pool via `newChatCompletionWithKeyFailover`, marks keys on key-specific failures, returns on first success or non-failover error.
- Chat completions streaming interceptor: per-iteration walker. Pre-stream failures fail over to the next key; mid-stream errors are relayed as SSE events.
- Responses blocking interceptor: extracts `newResponseWithKeyFailover` parallel to chatcompletions.
- Responses streaming interceptor: per-iteration walker, retains the existing buffer-then-forward design.

## Related Issues

Related to: https://github.com/coder/internal/issues/1446
Related to: https://linear.app/codercom/issue/AIGOV-197/aibridge-automatic-key-failover-for-bridged-and-passthrough-routes

## Follow-up PRs

- Bedrock multi-key support.
- Refactor provider vs interceptor config separation.
- Record the actually-used key in the interception credential hint after failover.

> [!NOTE]
> Initially generated by Claude Opus 4.7, modified and reviewed by @ssncferreira
2026-05-07 15:35:46 +01:00
Susana Ferreira f1155ac4d7 feat: add automatic key failover for AI Bridge Anthropic (#24836)
## Description

Adds automatic key failover for centralized Anthropic provider. When a key pool is configured, each upstream call walks the pool and tries keys in order until one succeeds or the pool is exhausted. Keys are marked **temporary** on 429 (with cooldown from `Retry-After`) and **permanent** on 401/403. Errors that aren't key-specific don't trigger failover. Each agentic-loop iteration gets its own fresh walker, so a tool-call continuation can fail over independently of the initial request.

BYOK is unchanged: BYOK requests run as a single attempt with no failover.

## Changes

- `config.Anthropic` carries a `KeyPool`. `Key` remains for BYOK X-Api-Key set per interception.
- Blocking interceptor: walks the pool, marks keys on key-specific failures, returns on first success or non-failover error.
- Streaming interceptor: per-iteration walker. Pre-stream failures fail over to the next key; mid-stream errors are relayed as SSE events.
- New `keypool` error types: `TransientExhaustionError` (carries soonest cooldown) and `ErrPermanentExhaustion`. Replace the prior `ErrAllKeysExhausted`.
- Error responses now consistently include the outer `"type": "error"` field.

## Related Issues

Related to: https://github.com/coder/internal/issues/1446
Related to: https://linear.app/codercom/issue/AIGOV-197/aibridge-automatic-key-failover-for-bridged-and-passthrough-routes

## Follow-up PRs

- Bedrock multi-key support.
- Refactor provider vs interceptor config separation.
- Record the actually-used key in the interception credential hint after failover.

> [!NOTE]
> Initially generated by Claude Opus 4.7, modified and reviewed by @ssncferreira
2026-05-07 14:57:44 +01:00
Susana Ferreira dbb50ebaaf feat: remove 429 from aibridge circuit breaker failure conditions (#24701)
## Description

Removes 429 (Too Many Requests) from the circuit breaker failure conditions. Rate limiting is now handled by automatic key failover instead of tripping the circuit breaker.

## Changes

`DefaultIsFailure` no longer treats 429 as a circuit breaker failure. The circuit breaker now only trips on server overload responses (503, 529).

Tests and integration tests updated to use 503 instead of 429 for tripping circuits. Description strings in deployment config updated to reflect the change.

Closes https://github.com/coder/internal/issues/1445

> [!NOTE]
> Initially generated by Coder Agents, modified and reviewed by @ssncferreira
2026-04-30 09:31:32 +01:00
Paweł Banaszewski a24dc19d49 chore: clean up env var usage in aibridge (#24783)
> AI tools where used when creating this PR

This PR removes environment variable parsing from `/aibridge` directory.

Added env variables/flags for dump dir as coder options.
Only added to new indexed provider options
(`CODER_AIBRIDGE_PROVIDER_<N>_*`) not to deprecated legacy env variables
(`CODER_AIBRIDGE_ANTHROPIC_*` and `CODER_AIBRIDGE_OPENAI_KEY_*`).

Reverted adding `MaxRetries` option as it will be removed soon due to
key failover work:
https://github.com/coder/coder/pull/24783#discussion_r3155544808
2026-04-29 18:28:37 +02:00
Paweł Banaszewski b8906c84a1 fix: fixes aibridge integration tests failing on windows (#24665)
Fixes aibridge responses and apidump integration tests in windows CI
job.

example failing job before the fix:
https://github.com/coder/coder/actions/runs/24873191866/job/72823942378
2026-04-24 18:28:22 +02:00
Paweł Banaszewski e00e85765b chore: move aibridge library code into coder repo (#24190)
This PR merges code from `coder/aibridge` repository into `coder/coder`.
It was split into 4 PRs for easier review but stacked PRs will need to
be merged into this PR so all checks pass.

* https://github.com/coder/coder/pull/24190 -> raw code copy (this PR,
before merging PRs on top of it, it was just 1 commit:
https://github.com/coder/coder/commit/70d33f33200c7e77df910957595715f81f9bec24)
* https://github.com/coder/coder/pull/24570 -> update imports in
`coder/coder` to use copied code
* https://github.com/coder/coder/pull/24586 -> linter fixes and CI
integration (also added README.md)
* https://github.com/coder/coder/pull/24571 -> added exclude to
scripts/check_emdash.sh check

Original PR message (before PR squash):
Moves coder/aibridge code into coder/coder repository.

Omitted files:

- `go.mod`, `go.sum`, `.gitignore`, `.github/workflows/ci.yml,`
`Makefile`, `LICENSE`, `README.md` (modified README.md is added later)
- `.github`, `example`, `buildinfo,` `scripts` directories

Simple verification script (will list omitted files)

```
tmp=$(mktemp -d)
echo "$tmp"
git clone --depth=1 https://github.com/coder/aibridge "$tmp/aibridge"
git clone --depth=1 --branch pb/aibridge-code-move https://github.com/coder/coder "$tmp/coder"
diff -rq --exclude=.git "$tmp/aibridge" "$tmp/coder/aibridge"
# rm -rf "$tmp"
```
2026-04-22 17:01:01 +02:00