mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-16 04:29:31 +00:00
aa0279e0a2
* feat(anthropic): generate auto mode safeguard_results with a classifier model on the /v1/messages chat bridge * fix(anthropic): check caller limits for the safeguards classifier, mark truncated tool calls, and keep pre-compaction context * fix(anthropic): log classifier spend under the caller's key hash and read list-shaped classifier replies * feat(anthropic): generate safeguard_results on the Responses bridge and native non-Claude /v1/messages providers * fix(messages): keep safeguards requests on Python under the Rust opt-in * fix(anthropic): keep non-ASCII text unescaped in the safeguards classifier prompt * test(anthropic): build the text-parts classifier reply without openai's construct path Message.model_construct goes through openai's construct_type, which caches discriminated unions in a weak-key map. On Python 3.12 a PEP 604 union cannot be weak-referenced, so the fixture raised inside the fake classifier and the test read an unavailable verdict. model_copy sets the list content without that path. * fix(anthropic): scan only new bytes for SSE frame ends on safeguarded native streams * fix(anthropic): answer safeguards on web search short circuits and widen the classifier reply cap * fix(anthropic): answer unsupported when the proxy serves no deployment for the safeguards classifier * fix(anthropic): keep a backend's stream verdicts and join split SSE data lines before stamping * fix(anthropic): map only the router's no-healthy-deployments refusal to unsupported * fix(anthropic): answer unavailable for the turn on a transient caller denial and let the classifier deployment's timeout apply * fix(anthropic): keep the user's whole opening message in the classifier transcript past its budget * fix(anthropic): run the proxy's own access checks for the safeguards classifier call The classifier and compaction sub-calls now pass through the same model access checks as the parent request (key, team, team member, user, project, end user, managed agent grants), with budgets left to the per-model budget check so nothing is reserved. They also carry the parent's logging params and headers, so a redaction header or per-request callback params apply to their own rows. Only per-model RPM limits count against a sub-call now, since a key-wide or team-wide RPM window is already spent by the parent request. The MCP auto-execute loop classifies only its final response, a chat-bridge stream without safeguards yields frames directly, and a classifier provider failure logs one warning line instead of a traceback * fix(anthropic): keep safeguards sub-calls off the parent's session routing and carry a body trace id The classifier and compaction summary calls no longer get the parent's proxy_server_request, so a Claude Code session bound to a router no longer pulls them off their configured model. Redaction still reads the headers carried in metadata. Their access checks now use the parent's resolved litellm_trace_id when the parent metadata has no trace_id, so a team that requires a trace id accepts a sub-call whose parent sent it in the body. * fix(anthropic): keep the disable-callbacks header on safeguards sub-calls * fix(proxy): charge per-model budgets from litellm_metadata when metadata holds only routing keys * test(integration): add safeguard_results cells for the bridges, native routes, caller checks, and classifier failures * fix(proxy): check the caller's budgets on the classifier call and keep failed access reads retryable --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| actors.py | ||
| agentic_probe.py | ||
| anthropic_sse.py | ||
| anthropic_thinking.py | ||
| asgi.py | ||
| async_server.py | ||
| aws_control_plane.py | ||
| bedrock_discovery.py | ||
| bedrock_runtime_peer.py | ||
| browser_state.py | ||
| budget.py | ||
| claude_code.py | ||
| client.py | ||
| codex_vendor.py | ||
| daily_activity.py | ||
| daily_spend_rows.py | ||
| database.py | ||
| database_relay.py | ||
| device_login.py | ||
| forward_proxy.py | ||
| generation.py | ||
| interception_vendor.py | ||
| mail.py | ||
| manifest.py | ||
| mcp.py | ||
| mcp_e2e_upstream_server.py | ||
| mcp_grants.py | ||
| mcp_stdio_peer.py | ||
| oauth_server.py | ||
| openai_wire.py | ||
| ordering.py | ||
| otlp_sink.py | ||
| pdf_document.py | ||
| prisma_clients.py | ||
| process.py | ||
| prometheus_series.py | ||
| prompt_cache_breakpoint.py | ||
| provider.py | ||
| proxy.py | ||
| redaction_probe.py | ||
| redis_process.py | ||
| responses_stream.py | ||
| responses_vendor.py | ||
| routing.py | ||
| runtime.py | ||
| safeguards_rig.py | ||
| sagemaker_embedding.py | ||
| sharding.py | ||
| sigv4.py | ||
| timing.py | ||
| tls.py | ||
| tool_rows.py | ||
| upstream.py | ||
| vertex.py | ||
| wire.py | ||
| worker_readiness.py | ||
| workers.py | ||