mlsmaycon e2470985fe [proxy] Split the router's surface dispatch out of Invoke ...

Invoke had grown a branch per API surface, each repeating the same
found/unauthorised/unknown switch. Lift the shared denial arms into decide(),
move the model-less endpoints into their own method, and name the two allow
decorations (non-inference marking, Bedrock namespace stripping) so each
surface reads as the one thing it does differently.

No behaviour change.

2026-08-22 21:14:05 +02:00

..

cost_meter

[proxy] Match dated Anthropic model ids against their undated form

2026-08-22 21:14:05 +02:00

llm_guardrail

[proxy] Mirror LLM denials in the caller's provider error shape

2026-08-22 21:14:05 +02:00

llm_identity_inject

[proxy] Skip OpenAI-shape identity injection on non-OpenAI bodies

2026-08-22 21:14:05 +02:00

llm_limit_check

[proxy] Mirror LLM denials in the caller's provider error shape

2026-08-22 21:14:05 +02:00

llm_limit_record

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

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

llm_request_parser

[proxy] Capture sub-agent ids from LLM request headers

2026-08-22 21:14:05 +02:00

llm_response_parser

[management, proxy] Add prompt-cache token and cost accounting to agent network usage (#6900)

2026-07-26 21:42:41 +02:00

llm_router

[proxy] Split the router's surface dispatch out of Invoke

2026-08-22 21:14:05 +02:00

agentnetwork_chain_integration_test.go

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

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

all_test.go

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

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

builtin.go

[management, proxy] Management-owned LLM pricing: file-backed defaults + (#6965)

2026-07-31 20:52:56 +02:00

cost_calculation_matrix_test.go

[management, proxy] Management-owned LLM pricing: file-backed defaults + (#6965)

2026-07-31 20:52:56 +02:00