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
fix(memory/graph): skip a corrupt row instead of aborting a whole graph scan (#3239)
6262c28 Abhay Singh committed 2 months ago
fix(proxy): protect file reads from lossy compression on the Responses API path (Copilot view + HEADROOM_PROTECT_READS) (#3238)
4408e88 Raúl committed 2 months ago
fix(proxy): make output-savings flush atomic and keep it off the event loop (#3231)
b9d7dcc inix committed 2 months ago
fix(wrap): stop concurrent wrap sessions clobbering settings.local.json (#3232)
f27f235 Tejas Chopra committed 2 months ago
fix(kimi): route managed Kimi Code through the proxy (#3223)
701e461 Rod Boev committed 2 months ago
fix(transforms): stop folding datetime-prefixed user messages as search results (#3221)
7784bb1 Raúl committed 2 months ago
fix(cache/semantic): don't semantic-match an empty query across contexts (#3226)
455f4f2 Abhay Singh committed 2 months ago
docs(troubleshooting): note server-managed settings skip custom ANTHROPIC_BASE_URL (#3118)
cc48486 Parideboy committed 2 months ago
fix(codex): detect ChatGPT auth from id_token claims so wrap/init emit requires_openai_auth (#3212)
2f81fa5 Tejas Chopra committed 3 months ago
fix(doctor): report project-scoped Claude routing instead of a false negative (#3213)
8f3e33a Tejas Chopra committed 3 months ago
test: repair three suite failures that are red on main (#3196)
5d25abd Tejas Chopra committed 3 months ago
fix(security): validate caller-supplied upstreams on every resolution path (#3195)
3e3c409 Tejas Chopra committed 3 months ago
fix(proxy/responses): keep the Codex additional_tools carrier on the wire (#3194)
1617f83 Tejas Chopra committed 3 months ago
fix(dashboard): pin MIME types for the vendored static assets (#3193)
b485768 Ayush Kumar Jha committed 3 months ago
fix: skip cross-turn dedup pointers on OpenAI chat streaming (#3191)
9c30b62 Raúl committed 3 months ago
fix(wrap): make the Serena pre-index stall budget configurable (#3183)
202c189 Ayush Kumar Jha committed 3 months ago
fix(proxy/responses): lift Codex >= 0.149.0 additional_tools into top-level tools (#3186)
25ca580 gglucass committed 3 months ago
fix(proxy): count output tokens from the stream's text, not its wire size (#3163)
4006964 Tejas Chopra committed 3 months ago
fix(copilot): bind the minted token to the integration ID we forward (#3164)
397803a Tejas Chopra committed 3 months ago
fix(kompress): accept ccr_original on the remote compressor (#3162)
45cb1b9 Tejas Chopra committed 3 months ago
deps: bump typescript from 5.9.3 to 7.0.2 in /plugins/opencode (#2280)
a382137 dependabot[bot] committed 3 months ago
deps: bump typescript from 5.9.3 to 7.0.2 in /plugins/openclaw (#2279)
85774fc dependabot[bot] committed 3 months ago
deps: bump ai from 6.0.149 to 7.0.59 in /docs (#2277)
f7e5d37 dependabot[bot] committed 3 months ago