Previously, run_turn_loop was bounded only by max_turns (turn count). If
engine.submit_message stalled — slow provider, hung network, infinite
stream — the loop blocked indefinitely with no cancellation path. Claws
calling run_turn_loop in CI or orchestration had no reliable way to
enforce a deadline; the loop would hang until OS kill or human intervention.
Fix:
- Add timeout_seconds parameter to run_turn_loop (default None = legacy unbounded).
- When set, each submit_message call runs inside a ThreadPoolExecutor and is
bounded by the remaining wall-clock budget (total across all turns, not per-turn).
- On timeout, synthesize a TurnResult with stop_reason='timeout' carrying the
turn's prompt and routed matches so transcripts preserve orchestration context.
- Exhausted/negative budget short-circuits before calling submit_message.
- Legacy path (timeout_seconds=None) bypasses the executor entirely — zero
overhead for callers that don't opt in.
CLI:
- Added --timeout-seconds flag to 'turn-loop' command.
- Exit code 2 when the loop terminated on timeout (vs 0 for completed),
so shell scripts can distinguish 'done' from 'budget exhausted'.
Tests (tests/test_run_turn_loop_timeout.py, 6 tests):
- Legacy unbounded path unchanged (timeout_seconds=None never emits 'timeout')
- Hung submit_message aborted within budget (0.3s budget, 5s mock hang → exit <1.5s)
- Budget is cumulative across turns (0.6s budget, 0.4s per turn, not per-turn)
- timeout_seconds=0 short-circuits first turn without calling submit_message
- Negative timeout treated as exhausted (guard against caller bugs)
- Timeout TurnResult carries correct prompt, matches, UsageSummary shape
Full suite: 49/49 passing, zero regression.
Blocker: none. Closes ROADMAP #161.
- list_sessions(directory=None) -> list[str]: enumerate stored session IDs
- session_exists(session_id, directory=None) -> bool: check existence without FileNotFoundError
- delete_session(session_id, directory=None) -> bool: unlink a session file
- load_session now raises typed SessionNotFoundError (subclass of KeyError) instead of FileNotFoundError
- Claws can now manage session lifecycle without reaching past the module to glob filesystem
Closes ROADMAP #160. Acceptance: claw can call list_sessions(), session_exists(id), delete_session(id) without importing Path or knowing .port_sessions/<id>.json layout.
Constraint: ROADMAP-only dogfood follow-up for 23:30 nudge on rebuilt claw git_sha 6f92e54d
Rejected: implementation change to plugin lifecycle uninstall; request was one concrete follow-up if no backlog item
Confidence: high after repeated bounded samples plus prompt list sanity check
Scope-risk: narrow
Directive: Replaces invalid hang PR #2897 with verified stderr-only JSON-mode gap
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; repeated timeout 8 ./rust/target/debug/claw plugins uninstall does-not-exist --output-format json; timeout 8 ./rust/target/debug/claw plugins list --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 23:00 nudge on rebuilt claw git_sha 5eb1d7d8
Rejected: implementation change to plugin lifecycle update; request was one concrete follow-up if no backlog item
Confidence: high after repeated bounded samples plus prompt list sanity check
Scope-risk: narrow
Directive: Replaces invalid hang PR #2894 with verified stderr-only JSON-mode gap
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; repeated timeout 8 ./rust/target/debug/claw plugins update does-not-exist --output-format json; timeout 8 ./rust/target/debug/claw plugins list --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 22:30 nudge on rebuilt claw git_sha 0f9e8915
Rejected: implementation change to plugin lifecycle mutation; request was one concrete follow-up if no backlog item
Confidence: high after repeated bounded samples plus prompt list sanity check
Scope-risk: narrow
Directive: Replaces invalid hang PR #2891 with verified stderr-only JSON-mode gap
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; repeated timeout 8 ./rust/target/debug/claw plugins disable does-not-exist --output-format json; timeout 8 ./rust/target/debug/claw plugins list --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 22:00 nudge on rebuilt claw git_sha ee44ff98
Rejected: implementation change to plugin lifecycle mutation; request was one concrete follow-up if no backlog item
Confidence: high after repeated bounded samples plus prompt list sanity check
Scope-risk: narrow
Directive: Keep supported lifecycle missing-target hang distinct from #348 list schema and #349 unsupported show action
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; repeated timeout 8 ./rust/target/debug/claw plugins enable does-not-exist --output-format json; timeout 8 ./rust/target/debug/claw plugins list --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 21:30 nudge on rebuilt claw git_sha a2a38df9
Rejected: implementation change to plugin action dispatch; request was one concrete follow-up if no backlog item
Confidence: high after repeated bounded samples
Scope-risk: narrow
Directive: Replaces invalid hang PR #2885 with verified unsupported-action classification gap
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; repeated timeout 8 ./rust/target/debug/claw plugins show does-not-exist --output-format json; timeout 8 ./rust/target/debug/claw plugins list --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 21:00 nudge on rebuilt claw git_sha cca6f682
Rejected: implementation change to plugin list serializer; request was one concrete follow-up if no backlog item
Confidence: high after repeated bounded samples
Scope-risk: narrow
Directive: Keep plugin inventory schema issue distinct from broad help JSON opacity
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; repeated timeout 8 ./rust/target/debug/claw plugins list --output-format json; ./rust/target/debug/claw plugins help --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 20:30 nudge on rebuilt claw git_sha ee41b266
Rejected: implementation change to MCP show status schema; request was one concrete follow-up if no backlog item
Confidence: high after bounded successful repro
Scope-risk: narrow
Directive: Replaces invalid hang/nondeterminism PRs with verified status contract gap
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; ./rust/target/debug/claw mcp show does-not-exist --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 20:00 nudge on rebuilt claw git_sha c6c01bea
Rejected: implementation change to native-agent detail dispatch; request was one concrete follow-up if no backlog item
Confidence: high
Scope-risk: narrow
Directive: Keep agent detail fallback distinct from #328/#329 native-agent source/schema issues; closed invalid hang hypotheses first
Tested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; ./rust/target/debug/claw agents list --output-format json; ./rust/target/debug/claw agents show analyst --output-format json; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 18:30 nudge on rebuilt claw git_sha a510f734
Rejected: implementation change to config slash dispatcher; request was one concrete follow-up if no backlog item
Confidence: high
Scope-risk: narrow
Directive: Keep /config section discovery issue distinct from #342 /commands and #343 /models correction issues
Tested: ./rust/target/debug/claw --resume latest /config help --output-format json; /config list; /config show; bare /config; git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Constraint: ROADMAP-only dogfood follow-up for 16:00 nudge on rebuilt claw git_sha 58569131
Rejected: code change in the command dispatcher | request was specifically to add one ROADMAP.md-only item
Confidence: high
Scope-risk: narrow
Directive: Keep /tasks distinct from #340; this is unsupported command stub JSON, not session help
Tested: git diff --check; scripts/fmt.sh --check
Not-tested: runtime behavior change, because this commit only documents the gap
Capture the dogfood evidence as a roadmap item so the stdout JSON error-envelope contract can be fixed and regression-tested later.\n\nConstraint: User requested exactly one ROADMAP.md-only item #340 from current origin/main.\nConfidence: high\nScope-risk: narrow\nTested: git diff --check; scripts/fmt.sh --check\nNot-tested: Runtime behavior unchanged; documentation-only roadmap entry.
Constraint: ROADMAP.md-only restore of lost #337 from PR #2852 / Jobdori dogfood evidence
Rejected: Renumbering adjacent items | preserving existing #338 and surrounding roadmap entries keeps history stable
Confidence: high
Scope-risk: narrow
Directive: Keep #337 before #338 and do not collapse the dirty-file detail requirement into the broader help/status backlog
Tested: git diff --check; scripts/fmt.sh --check
Not-tested: Product behavior changes; documentation-only change
Constraint: Respond to 14:30 dogfood nudge with one direct claw-code pinpoint.\nEvidence: rebuilt actual debug binary at git_sha 24ccb59b; compared top-level help --output-format json with resume-safe /help --output-format json.\nFinding: same help surface uses message in top-level JSON and text in slash/resume JSON.\nTested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; ./rust/target/debug/claw help --output-format json; ./rust/target/debug/claw --resume latest /help --output-format json; git diff --check; scripts/fmt.sh --check.\nNot-tested: full Rust suite; roadmap-only documentation change.
Constraint: Scope requested ROADMAP.md only with exactly one new #328 pinpoint from direct claw dogfood.\nRejected: Implementing the agents-help fix now | user requested roadmap-only evidence item.\nConfidence: high\nScope-risk: narrow\nDirective: Keep agent help source roots derived from the same loader registry as agents list; do not hand-maintain a divergent root list.\nTested: cargo run --manifest-path rust/Cargo.toml --bin claw -- version --output-format json; ./rust/target/debug/claw version --output-format json; ./rust/target/debug/claw agents help --output-format json; ./rust/target/debug/claw agents --output-format json; git diff --check; scripts/fmt.sh --check\nNot-tested: Full Rust test suite; roadmap-only documentation change.
Constraint: Scope limited to ROADMAP.md and one new pinpoint #327 from actual rebuilt claw dogfood.
Rejected: Code fix in this branch | user requested roadmap-only filing.
Confidence: high
Scope-risk: narrow
Directive: Keep mcp help source lists derived from actual config discovery, not hard-coded partial docs.
Tested: ./rust/target/debug/claw version --output-format json; ./rust/target/debug/claw mcp --help; ./rust/target/debug/claw mcp help --output-format json; temp .claw.json mcp list proof; git diff --check; scripts/fmt.sh --check
Not-tested: Full Rust test suite, documentation-only change.
Document the dogfood gap where help JSON stays parseable but hides command metadata inside a prose message, so future implementation can expose machine-readable command, slash-command, and resume-safety fields.\n\nConstraint: user requested ROADMAP.md-only pinpoint for issue #325 from origin/main d607ff36.\nRejected: implementing the schema now | requested fix shape is roadmap documentation only.\nConfidence: high\nScope-risk: narrow\nDirective: keep message for humans while adding schema/versioned structured help metadata when implementing.\nTested: git diff --check; scripts/fmt.sh --check\nNot-tested: runtime CLI behavior unchanged by docs-only change
