feat: improved wording and heuristic detection for sisyphus suite of agents
CI / All (ubuntu-latest) (push) Failing after 25s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled

This commit is contained in:
2026-08-10 15:37:53 -06:00
parent 91dbaf5533
commit 2b45e3a9b8
9 changed files with 136 additions and 34 deletions
+6
View File
@@ -439,6 +439,12 @@ nodes:
staleness report, gate decisions, and fix loop history. Downstream
plan updates come from the sweep results.
VERIFICATION HONESTY: evidence marked "GATE NOT RUN" means that gate
is UNVERIFIED — record it as not run; never paraphrase a skipped gate
as covered, passing, or handled elsewhere. A handoff that admits an
unverified gate is correct; one that dresses it up as verified poisons
every downstream reader.
Then append durable, step-independent facts (if any) to {{notes_path}}
- create the file if missing, never rewrite existing entries.
@@ -13,6 +13,7 @@ else
fi
project_dir=$(echo "$state" | jq -r '.project_dir // "."')
project_dir=$(resolve_gate_dir "$project_dir")
if [[ -n "${BUILD_CMD:-}" ]]; then
cmd="$BUILD_CMD"
@@ -24,7 +25,7 @@ fi
if [[ -z "$cmd" || "$cmd" == "null" ]]; then
jq -nc '{
"build_ok": true,
"build_output": "(no build/check command available for this project type)",
"build_output": "(GATE NOT RUN: no build/check command configured or detected. This is NOT evidence that the build passed — set BUILD_CMD, and never report the build as verified.)",
"_next": "verify_tests"
}'
exit 0
@@ -13,19 +13,18 @@ else
fi
project_dir=$(echo "$state" | jq -r '.project_dir // "."')
project_type=$(detect_project "$project_dir" | jq -r '.type // "unknown"')
project_dir=$(resolve_gate_dir "$project_dir")
project_info=$(detect_project "$project_dir")
project_type=$(echo "$project_info" | jq -r '.type // "unknown"')
format_cmd="${FORMAT_CMD:-}"
if [[ -z "$format_cmd" ]]; then
case "$project_type" in
rust) format_cmd="cargo fmt" ;;
go) format_cmd="gofmt -w ." ;;
python) command -v ruff &>/dev/null && format_cmd="ruff format ." ;;
esac
format_cmd=$(echo "$project_info" | jq -r '.fmt // ""')
fi
if [[ "$format_cmd" == "null" ]]; then format_cmd=""; fi
if [[ -z "$format_cmd" ]]; then
format_output="(no format command configured for project type '$project_type'; skipped. Set FORMAT_CMD to enable.)"
format_output="(GATE NOT RUN: no format command configured or detected for project type '$project_type'. This is NOT evidence that formatting is clean. Set FORMAT_CMD to enable.)"
else
fmt_rc=0
fmt_out=$(cd "$project_dir" && eval "$format_cmd" 2>&1) || fmt_rc=$?
@@ -37,12 +36,18 @@ fi
lint_cmd="${LINT_CMD:-}"
if [[ -z "$lint_cmd" ]]; then
lint_cmd=$(echo "$project_info" | jq -r '.lint // ""')
fi
# The skip message must read as a WARNING, never a reassurance: the previous
# wording ("linting is covered by the build/check command") was quoted
# verbatim by workers as false evidence that linting passed
if [[ -z "$lint_cmd" || "$lint_cmd" == "null" ]]; then
jq -nc \
--arg fo "$format_output" \
'{
"format_output": $fo,
"lint_ok": true,
"lint_output": "(no LINT_CMD configured; linting is covered by the build/check command)",
"lint_output": "(GATE NOT RUN: no lint command configured or detected. This is NOT evidence that linting passed — set LINT_CMD or add a Taskfile lint target, and never report linting as covered.)",
"_next": "verify_build"
}'
exit 0
@@ -13,6 +13,7 @@ else
fi
project_dir=$(echo "$state" | jq -r '.project_dir // "."')
project_dir=$(resolve_gate_dir "$project_dir")
if [[ -n "${TEST_CMD:-}" ]]; then
cmd="$TEST_CMD"
@@ -24,7 +25,7 @@ fi
if [[ -z "$cmd" || "$cmd" == "null" ]]; then
jq -nc '{
"tests_ok": true,
"tests_output": "(no test command available for this project type)",
"tests_output": "(GATE NOT RUN: no test command configured or detected. This is NOT evidence that tests passed — set TEST_CMD, and never report the suite as green.)",
"_next": "edge_case_sweep"
}'
exit 0