docs: product-facing README; archive CST theory notes (0.9.34)
Rewrite the homepage for day-to-day use, move paper/eval drafts under docs/archive, and add a docs index so theory no longer leads the project. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
@@ -7,7 +7,7 @@
|
||||
# [--model M] [--max-steps N] [--tools minimal|default] [--out DIR]
|
||||
# [--record] [--baseline-only]
|
||||
#
|
||||
# --tools defaults to minimal (the four tools the paper experiments used).
|
||||
# --tools defaults to minimal (read_file / run_shell / write_file / apply_patch).
|
||||
#
|
||||
# Artifacts go to <out>/<fixture>__<protocol>__<model>__<stamp>/:
|
||||
# result.json agent.log session.jsonl metrics.jsonl check.log [sse/]
|
||||
|
||||
@@ -5,4 +5,4 @@ ROOT="$(cd "$(dirname "$0")/.." && pwd)"
|
||||
cd "$ROOT"
|
||||
make check
|
||||
echo
|
||||
echo "See docs/theory_tool_cst.md for the claim under test."
|
||||
echo "Historical note: docs/archive/theory_tool_cst.md (not product docs)."
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
#
|
||||
# -m provider:model pairs (model may be empty: "deepseek:")
|
||||
# -r also record raw SSE streams per run (for replay experiments)
|
||||
# -t tool profile (default minimal, as in the paper runs)
|
||||
# -t tool profile (default minimal)
|
||||
#
|
||||
# Each run is scripts/e2e_fixture.sh; results land in <out>/<run>/ and the
|
||||
# summary in <out>/results.csv and <out>/summary.md.
|
||||
|
||||
Reference in New Issue
Block a user