Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
Commits on main
feat(transforms): pluggable lossless-compaction provider seam (#2433)
a7dcb9e Tejas Chopra committed 4 months ago
fix(copilot): preserve /v1 for the Anthropic /v1/messages endpoint (#2409) (#2414)
c400f90 Abhay Singh committed 4 months ago
fix(proxy/openai): replay incremental events in buffered Responses SSE (#2410) (#2415)
0cbc0e8 Abhay Singh committed 4 months ago
fix(install): carry upstream-routing env overrides into supervised deployments (#2429)
170b04a Abhay Singh committed 4 months ago
fix(proxy/openai): None-guard usage token counts on the chat path (#2431)
313c290 Abhay Singh committed 4 months ago
fix(install): migrate deployments off the retired chopratejas image repo (#2427)
17ff13c Abhay Singh committed 4 months ago
test(pricing): stop asserting DeepSeek pricing freshness on wall-clock time (#2428)
b976378 Abhay Singh committed 4 months ago
feat(wrap): boost Serena — symbol-first guidance, wrap-time pre-index, repo-language scoping (#2425)
fd0e1a8 Tejas Chopra committed 4 months ago
docs(proxy): document Vertex AI backend setup, env vars, aliases, native passthrough (#2422)
45a5a33 Parideboy committed 4 months ago
docs(troubleshooting): explain cache-mode default showing ~0 compression savings on the dashboard (#2248) (#2424)
9cba64d Shubham Srivastava committed 4 months ago
feat(wrap): default code-memory to Serena (dashboard browser off) behind unified --code-memory (#2413)
6e4425a Tejas Chopra committed 4 months ago
feat(transforms): dispatch kompress/text via the compressor registry + forward question (#2411)
446ec26 Tejas Chopra committed 4 months ago
fix(release): publish Windows wheel + sdist (disable PyPI attestations, #112) (#2405)
f9cbdd6 Tejas Chopra committed 4 months ago
test: make copilot-flag fixture tolerate headroom not installed (#2407)
a986d87 Tejas Chopra committed 4 months ago
feat(transforms): dispatch smart_crusher via the compressor registry (defer kompress/text ML boundary) (#2404)
7c7bf43 Tejas Chopra committed 4 months ago
feat(transforms): add compressed signal + dispatch code_aware/html/diff via registry (#2400)
7ebda67 Tejas Chopra committed 4 months ago
fix(ccr): guard empty/malformed OpenAI choices in _extract_assistant_message (#2389)
89319fb Abhay Singh committed 4 months ago
fix(proxy): skip max_tokens rename for backend-routed openai chat (#2401)
d6a1af4 Rod Boev committed 4 months ago
fix(proxy): promote Kompress health after runtime load (#2402)
54526bc Rod Boev committed 4 months ago
refactor(transforms): dispatch simple built-in strategies via the compressor registry (#2399)
fc9c63f Tejas Chopra committed 4 months ago
feat(transforms): make built-in compressors real Compressor implementations (adapters) (#2391)
981616c Tejas Chopra committed 4 months ago
fix(proxy/openai): feed chat/completions traffic into the traffic learner (#2333)
6cdfd3f Abhay Singh committed 4 months ago
feat(proxy): route selected external compressors through the content router (#2388)
e3c7964 Tejas Chopra committed 4 months ago
feat(proxy): label GitHub Copilot traffic as "copilot" in the outcome… (#2377)
d7a8cdb Serge ARADJ committed 4 months ago
feat(rust): add structured prose offload plumbing (#334) (#2378)
9e07785 Rod Boev committed 4 months ago
fix(cache): preserve client cache_control ttl when consolidating breakpoints (#2382)
8906d3a Zhenjia ZHOU committed 4 months ago
fix(wrap): emit bare dotted keys for Codex --config overrides (#2383)
f57e959 Zhenjia ZHOU committed 4 months ago