Module compress_api 

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

Drop-in parity with library-style compress(messages, model) gateways: the caller sends a chat-style messages array, the proxy rewrites every text payload through the same deterministic funnel used on the wire (super::compress::compress_tool_result), and returns the rewritten messages plus a structured token-savings summary.

Contract

Request: { "messages": [ … ], "model": "…"? } Response: { "messages": [ … ], "stats": { … } }

Both OpenAI (content: "string") and Anthropic (content: [ {type:"text"…}, {type:"tool_result"…} ]) message shapes are accepted. Only text payloads are compressed; images, tool_use blocks, ids and every other field pass through untouched. lean-ctx’s own ctx_* tool results are left verbatim (#479).

Determinism (#498)

Output is a pure function of (messages, model). Compression runs footer-free — savings are reported in stats, never injected into message bodies — so the result stays byte-stable for provider prompt caching.

Structs

CompressRequest

CompressResponse

CompressStats

Functions

compress_messages

Pure, deterministic core: rewrites every text payload in messages and reports aggregate token savings. Same input → same output bytes (#498).

handler

Axum handler. Malformed bodies are rejected by the Json extractor (400).