atogumo 4e5d67df35 fix(gateway): accept Claude Code max_tokens=1 probes for any model ...

The claude_code_only probe exemption only fired for models containing
"haiku". Claude Code also sends max_tokens=1 requests without a system
prompt to the model currently in use, e.g. when switching models or
refreshing the context usage, so on sonnet/opus groups those requests failed
the system-prompt check and were rejected as non-Claude-Code clients.

Recognise the probe from the request body itself (max_tokens == 1) once the
User-Agent check has passed, regardless of model, and carry max_tokens into
the ParsedRequest projection so the hot path sees it too. The haiku context
flag and the local haiku interception are unchanged; non-haiku probes reach
the pool as ordinary one-token requests. One output token offers nothing to
a client that already forges the CLI User-Agent, so this widens no attack
surface.

Fixes #6591

2026-09-08 19:12:37 +08:00

..

cmd

chore: sync VERSION to 0.2.3 [skip ci]

2026-09-08 02:35:11 +00:00

dev-docs

fix(ops): close proxy attribution gaps and bound queued upstream events

2026-09-03 15:11:36 +08:00

ent

feat(groups)!: enforce model allowlists across gateway endpoints

2026-09-05 16:05:17 +08:00

internal

fix(gateway): accept Claude Code max_tokens=1 probes for any model

2026-09-08 19:12:37 +08:00

migrations

fix(db): converge groups.model_allowlist on upgrade

2026-09-08 09:15:23 +08:00

pkg/pluginapi

…

resources/model-pricing

…

scripts

…

.dockerignore

…

.golangci.yml

…

Dockerfile

…

go.mod

…

go.sum

…

Makefile

…