Fix streaming tool calls, compressed request bodies, beacon field names; bump to 0.5.13

fix: remove unused imports in test_langgraph.py (ruff F401)

Fix Windows drive letter path decoding in headroom learn (fixes #69)

Merge pull request #60 from gglucass/feat/add-headroom-sdk

feat: add LangGraph compress_tool_messages node for ToolMessage compression

OpenClaw plugin fixes, telemetry fix, cost tracker improvement, tokenBudget support

feat: allow overriding proxy telemetry sdk via HEADROOM_SDK

Add TypeScript SDK (headroom-ai npm package)

Fix CI test, bump to 0.5.7

Fix API integration test: use tool output not user message for tags

Remove LLMLingua: Kompress is the sole text compressor

Protect workflow XML tags from text compression

Diversity-aware SmartCrusher: keep unique items, compress text within

Fix test failures: update hash test for MD5, handle unicode surrogates

test: verify ratelimit headers are forwarded in streaming responses

Fix ruff format for litellm, wrap, test_scanner

Fix ruff lint errors in test files

Merge pull request #52 from gglucass/fix/learn-with-dots-in-paths

fix(bedrock): add EU/AP region support with graceful fallback

Fix tests

.

Add path "." compatibility for headroom learn

fix: close TOIN feedback loop — retrievals now flow back for learning

feat: add live traffic learning + cross-agent memory writers (--learn flag)

.

test: add integration tests for token_headroom mode

feat: add frozen count, apply_cached, update_from_result to CompressionCache

feat: add CompressionCache with LRU eviction for token headroom mode

Add SharedContext for multi-agent, rewrite README, fix proxy cleanup

Enhanced MCP server with compress/stats tools, fix proxy torch crash

Fixing tests

Fix proxy crash when torch not installed (kompress lazy imports)

Add wrap commands for Codex/Cursor/Aider with rtk instructions, fix savings metrics

Commit message:

Slim core dependencies: 2.5GB → 195MB install size

Fix pricing lookup for retired Claude models

Fix proxy backend bugs: env vars, tool forwarding, and provider support

Introducing headroom wrap

Add Kompress: ModernBERT token compressor replacing LLMLingua-2

feat: provider-aware prefix cache tracking and combined savings dashboard

fix: dashboard metrics, TTFB tracking, eager LLMLingua loading, and multi-provider consistency

fix(learn): pass explicit model in tests to avoid API key requirement

feat: add `headroom perf` CLI and rewrite `headroom learn` to use LLM analysis

fix(mcp): fix uninstall symmetry, move subprocess import, add cli-path tests

fix(mcp): use claude mcp add for install and fix startup import

feat(router): adaptive compression with Read lifecycle and context-pressure scaling

feat(code): add semantic symbol importance to CodeAwareCompressor

Add multi-agent support, quality gates, and integration tests for headroom learn

Add headroom learn: offline failure learning for coding agents

Fix LangChain tool_call argument handling for varied message formats