Maycon Santos bab5572a74 [management, proxy] scope agent-network model allowlist per policy/group and provider (#6905) ...

## Describe your changes

The model-allowlist guardrail was merged into one account-wide union and
enforced flat on every request, ignoring which policy/group/provider
authorised it. With multiple policies — especially a mix of guardrailed
and un-guardrailed ones — this caused:

- **false-allow**: a model allowlisted for one group/provider leaked to
any caller; and
- **false-deny**: an un-guardrailed policy (intended unrestricted) was
blocked by another policy's allowlist.

Enforcement is now policy/group-aware, mirroring `llm_limit_check`:

- **Management (`SelectPolicyForRequest`) is authoritative.** It uses
the request model (already carried in
`CheckLLMPolicyLimitsRequest.model`, previously ignored) to keep only
applicable policies whose guardrails permit the model; no
allowlist-enabled guardrail = unrestricted. Denies
`llm_policy.model_blocked` when policies govern the (provider, groups)
but none permits the model.
- **Proxy `llm_guardrail` becomes a per-provider fail-closed backstop.**
The synthesiser emits an allowlist only for providers every authorising
policy restricts; the middleware keys off the resolved provider id and
keeps unknown-model fail-closed.

2026-07-27 20:43:59 +02:00

..

agentnetwork

[management, proxy] scope agent-network model allowlist per policy/group and provider (#6905)

2026-07-27 20:43:59 +02:00

peers

[management,client] 0.74.5 branch sync (#6769)

2026-07-14 21:22:40 +02:00

reverseproxy

[management,proxy,client] 0.74.0 version (#6563)

2026-07-01 12:45:14 +02:00

zones

[management] enrich context in permissions manager (#6286)

2026-05-29 16:36:38 +02:00