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
docs: fix dead contact links in issue templates and troubleshooting guide (#910)
Focused Instability7ced77b6e74a
diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.ymlindex 171b37791..c86795a37 100644--- a/.github/ISSUE_TEMPLATE/config.yml+++ b/.github/ISSUE_TEMPLATE/config.yml@@ -1,8 +1,8 @@blank_issues_enabled: truecontact_links:- name: Questions & Discussions- url: https://github.com/headroom-sdk/headroom/discussions+ url: https://github.com/chopratejas/headroom/discussionsabout: Ask questions and discuss ideas in GitHub Discussions- name: Documentation- url: https://headroom.dev/docs+ url: https://headroom-docs.vercel.app/docsabout: Check out the documentation for guides and API referencediff --git a/docs/content/docs/troubleshooting.mdx b/docs/content/docs/troubleshooting.mdxindex 0cfb613e5..8a577275f 100644--- a/docs/content/docs/troubleshooting.mdx+++ b/docs/content/docs/troubleshooting.mdx@@ -421,4 +421,4 @@ print(f"Tokens: {result.tokens_before} -> {result.tokens_after}")1. Enable debug logging and check the output2. Use `simulate()` to see what transforms would apply3. Run `validate_setup()` for configuration issues-4. File an issue at [github.com/headroom-sdk/headroom](https://github.com/headroom-sdk/headroom/issues) with your Headroom version, Python version, provider, debug log output, and minimal reproduction code+4. File an issue at [github.com/chopratejas/headroom](https://github.com/chopratejas/headroom/issues) with your Headroom version, Python version, provider, debug log output, and minimal reproduction code