Module proxy 

Modules

anthropic

cache_aligner

Cache-aligner (#940 detect, #974 relocate) — Headroom “cache aligner” port.

cache_attribution

Prompt-cache miss attribution (#986, cache-economics telemetry).

cache_breakpoint

Active prompt-cache breakpoint injection (#939, Headroom “cache aligner” adjacent).

cache_policy

Net-cost policy for cache-busting rewrites (#986, cache-economics).

cache_safety

Cache-preservation telemetry for the proxy’s frozen-region prose rewrites (#710).

ccr

Content-addressed recovery (CCR) for the proxy’s lossy rewrites (#482).

chatgpt

chatgpt_cookies

chatgpt_ws

WebSocket passthrough for ChatGPT’s /backend-api rail (#597).

cold_prefix

Big-gap cold-prefix repack prediction (#480).

compress

compress_api

POST /v1/compress — deterministic messages-in / messages-out compression.

cost

Per-model proxy savings accounting.

effort

Cache-safe, cross-provider reasoning-effort control (#834).

forward

google

history_prune

holdout

Deterministic output-savings holdout (#895 Track B).

introspect

metrics

openai

openai_responses

openai_responses_ws

WebSocket bridge for the OpenAI/Codex Responses transport (#440).

output_savings

Output-token savings reporting (#895 Track B).

prose

Frozen-region prose compression for the proxy (#710).

prose_ranker

Cache-safe wire prose squeeze (#895).

tool_kind

Classifies what produced a tool_result so the proxy never lossy-compresses a file/source-code read the model still needs (e.g. mid-refactor).

tool_output

usage

Real provider-reported token usage extraction.

usage_meter

Measured per-model spend meter.

verbosity

Cache-safe wire verbosity steer (#895 Track B).

Structs

ProviderStats

ProxyState

ProxyStats

Functions

start_proxy

start_proxy_with_token