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
fix(learn): finish gemini-flash-latest default model sweep (#532)
Evan Alferezd7973665f4e2
diff --git a/headroom/cli/learn.py b/headroom/cli/learn.pyindex f94bdb3bf..ef4ba2b90 100644--- a/headroom/cli/learn.py+++ b/headroom/cli/learn.py@@ -87,7 +87,7 @@ Use 'auto' (default) to scan all detected agents.""""--model",type=str,default=None,- help="LLM model for analysis (e.g., claude-sonnet-4-6, gpt-4o, gemini/gemini-2.0-flash). "+ help="LLM model for analysis (e.g., claude-sonnet-4-6, gpt-4o, gemini/gemini-flash-latest). ""Auto-detected from API keys if not specified.",)@click.option(diff --git a/headroom/learn/analyzer.py b/headroom/learn/analyzer.pyindex 7f9053969..9dc0af325 100644--- a/headroom/learn/analyzer.py+++ b/headroom/learn/analyzer.py@@ -37,7 +37,7 @@ logger = logging.getLogger(__name__)_MODEL_DEFAULTS: list[tuple[str, str]] = [("ANTHROPIC_API_KEY", "claude-sonnet-4-6"),("OPENAI_API_KEY", "gpt-4o"),- ("GEMINI_API_KEY", "gemini/gemini-2.0-flash"),+ ("GEMINI_API_KEY", "gemini/gemini-flash-latest"),]_MAX_DIGEST_TOKENS = 80_000 # Budget for the digest (leave room for prompt + output)@@ -94,7 +94,7 @@ def _detect_default_model() -> str:"No LLM API key found. headroom learn needs one of:\n"" export ANTHROPIC_API_KEY=sk-ant-... → uses claude-sonnet-4-6\n"" export OPENAI_API_KEY=sk-... → uses gpt-4o\n"- " export GEMINI_API_KEY=... → uses gemini-2.0-flash\n"+ " export GEMINI_API_KEY=... → uses gemini-flash-latest\n""Or set HEADROOM_LEARN_CLI to a coding agent CLI (claude, gemini, codex).\n""Or install one of those CLIs for auto-detection.\n""Or specify a model directly: headroom learn --model <litellm-model-name>"diff --git a/tests/test_learn/test_analyzer.py b/tests/test_learn/test_analyzer.pyindex bef73fbd5..b83122cc1 100644--- a/tests/test_learn/test_analyzer.py+++ b/tests/test_learn/test_analyzer.py@@ -466,7 +466,7 @@ class TestDetectDefaultModel:monkeypatch.delenv("ANTHROPIC_API_KEY", raising=False)monkeypatch.delenv("OPENAI_API_KEY", raising=False)monkeypatch.setenv("GEMINI_API_KEY", "test")- assert _detect_default_model() == "gemini/gemini-2.0-flash"+ assert _detect_default_model() == "gemini/gemini-flash-latest"def test_anthropic_preferred_over_openai(self, monkeypatch):monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-test")