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(troubleshooting): explain the frozen ghcr.io/chopratejas/headroom image (#4069)
Radhakrishnan Pachyappan47288d67e91c
diff --git a/docs/content/docs/troubleshooting.mdx b/docs/content/docs/troubleshooting.mdxindex 07620bd50..206d322de 100644--- a/docs/content/docs/troubleshooting.mdx+++ b/docs/content/docs/troubleshooting.mdx@@ -364,6 +364,28 @@ pipx install --python python3.13 "headroom-ai[all]==0.21.4"If you already have Headroom installed under `pipx`, uninstall it first orreinstall it with the supported interpreter.+### Docker image frozen at an old version++**Symptom**: `headroom --version` inside the running container reports an old+release (e.g. `0.27.0`) no matter how recently you pulled the image.++**Cause**: the project moved from the `chopratejas` personal account to the+`headroomlabs-ai` org, and GHCR does not redirect packages across that move.+`ghcr.io/chopratejas/headroom` still exists but stopped receiving pushes at+that point, so it is permanently frozen at the last version built under the+old namespace. A `HEADROOM_DOCKER_IMAGE` override, an install script, or a+tutorial saved from before the move can still point there.++Pull the current image instead:++```bash+docker pull ghcr.io/headroomlabs-ai/headroom:latest+```++If you set `HEADROOM_DOCKER_IMAGE` yourself, check it does not still read+`ghcr.io/chopratejas/headroom`. See [Docker install](/docs/docker-install)+for the current default and the available tags.+### pip install fails with C++ compilation error**Symptom**: `RuntimeError: Unsupported compiler -- at least C++11 support is needed!`