Skip to content

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.

fix(learn): finish gemini-flash-latest default model sweep (#532)

Evan Alferezd7973665f4e2
diff --git a/headroom/cli/learn.py b/headroom/cli/learn.py
index 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.py
index 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.py
index 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")