Skip to content

Self-hosted AI workspace.

Python

fix(runtime): restrict running effects to launch results and index history

Alexandre Teixeira75243fe0b073
diff --git a/src/agent_runtime/effect_adapters.py b/src/agent_runtime/effect_adapters.py
index 34f1fbfc7..16b1593e6 100644
--- a/src/agent_runtime/effect_adapters.py
+++ b/src/agent_runtime/effect_adapters.py
@@ -191,9 +191,12 @@ def _execution(result: Any, facts: ProducerFacts) -> ExecutionOutcome:
return ExecutionOutcome.INTERRUPTED
if facts.timed_out:
return ExecutionOutcome.TIMED_OUT
+ # Only launch-shaped results mean this operation's own work continues:
+ # the native detached launch, or a bridge's explicit detachment. A listing
+ # that merely reports some other thing as "running" is not.
if isinstance(result.get("bg_job_id"), str) and facts.exit_code == 0:
return ExecutionOutcome.RUNNING
- if result.get("detached") is True or result.get("status") == "running" or result.get("running") is True:
+ if result.get("detached") is True:
return ExecutionOutcome.RUNNING
denied = bool(result.get("blocked") or result.get("approval_required")
or facts.failure_kind.endswith("_denied"))
diff --git a/src/agent_runtime/effects.py b/src/agent_runtime/effects.py
index 994557645..59da3bc44 100644
--- a/src/agent_runtime/effects.py
+++ b/src/agent_runtime/effects.py
@@ -642,14 +642,21 @@ class EffectHistory:
raise ValueError("A settled effect outcome cannot be replaced")
if outcome.execution is not ExecutionOutcome.RUNNING:
settled.add(outcome.effect_id)
+ # Derived indexes (not fields): outcomes per effect in sequence order.
+ by_effect: dict[str, list[EffectOutcome]] = {}
+ for outcome in sorted(self.outcomes, key=lambda o: o.sequence):
+ by_effect.setdefault(outcome.effect_id, []).append(outcome)
+ object.__setattr__(self, "_outcomes_by_effect", by_effect)
+ object.__setattr__(self, "_claims_by_id", {c.effect_id: c for c in self.claims})
def claim(self, effect_id: str) -> EffectClaim | None:
- return next((c for c in self.claims if c.effect_id == effect_id), None)
+ return self._claims_by_id.get(effect_id)
def latest_outcome(self, effect_id: str, before: int | None = None) -> EffectOutcome | None:
- matching = [o for o in self.outcomes if o.effect_id == effect_id
- and (before is None or o.sequence < before)]
- return max(matching, key=lambda o: o.sequence) if matching else None
+ for outcome in reversed(self._outcomes_by_effect.get(effect_id, ())):
+ if before is None or outcome.sequence < before:
+ return outcome
+ return None
def execution(self, effect_id: str, before: int | None = None) -> ExecutionOutcome:
outcome = self.latest_outcome(effect_id, before)
diff --git a/tests/test_effect_resource_bindings.py b/tests/test_effect_resource_bindings.py
index 23a378577..39503fccb 100644
--- a/tests/test_effect_resource_bindings.py
+++ b/tests/test_effect_resource_bindings.py
@@ -33,7 +33,7 @@ def run(ws, tmp_path):
journal = ActionJournal(workspace=str(ws), observed_artifacts=("a.txt",))
journal.effects = EffectLog(journal.run_id, directory=tmp_path / "fx")
authority = RequestAuthority("request", "alice", "thread", str(ws), tuple(
- OperationGrant(tool) for tool in ("write_file", "read_file", "edit_file", "apply_patch", "ls")))
+ OperationGrant(tool) for tool in ("write_file", "read_file", "edit_file", "apply_patch", "ls", "private_browser")))
async def call(tool, args):
content = args if isinstance(args, str) else json.dumps(args)
@@ -218,6 +218,20 @@ def test_listing_is_partial_and_does_not_verify_content(run):
assert verdicts(run.journal) == [fx.EffectVerdict.UNVERIFIED]
+ {"action": "click", "page": "t1", "selector": "#buy"},
+ {"action": "open", "url": "https://example.com"},
+ {"action": "snapshot", "page": "t1"},
+ {"action": "evaluate", "page": "t1", "script": "1"},
+])
+def test_browser_page_operations_stay_fail_closed_with_effects(run, args):
+ description, result = run("private_browser", args)
+ assert "UNSUPPORTED" in description
+ assert result["failure_kind"] == "browser_page_authority_unavailable" and result["executed"] is False
+ assert run.journal.effects.history().claims == ()
+ assert run.journal.actions[0].execution_id is None
+
+
def test_ordinary_read_only_turn_completes_normally(run, ws):
(ws / "a.txt").write_text("existing\n")
run("read_file", {"path": "a.txt"})
diff --git a/tests/test_effect_verification_adapters.py b/tests/test_effect_verification_adapters.py
index 8af537f81..0376fbbd3 100644
--- a/tests/test_effect_verification_adapters.py
+++ b/tests/test_effect_verification_adapters.py
@@ -339,6 +339,40 @@ def test_child_effects_share_lineage_order_and_invalidate_parent_evidence(tmp_pa
assert fx.freshness(history.observations[0], history) is fx.Freshness.STALE
+def test_listing_that_reports_other_work_running_is_not_a_running_effect(store, monkeypatch):
+ journal = journal_for(store)
+ act(journal, monkeypatch, adapters.DispatchCapture(), "list_downloads",
+ result={"output": "1 download", "exit_code": 0, "status": "running", "running": True})
+ assert journal.effects.assessments()[0].execution is fx.ExecutionOutcome.REPORTED_SUCCESS
+
+
+def test_scheduler_trigger_is_admission_not_completed_work(store, monkeypatch):
+ journal = journal_for(store)
+ act(journal, monkeypatch, adapters.DispatchCapture(), "manage_tasks",
+ content=json.dumps({"action": "run", "task_id": "t1"}),
+ result={"output": "Task t1 triggered; it completed successfully.", "exit_code": 0})
+ claim = journal.effects.history().claims[0]
+ assessment = journal.effects.assessments()[0]
+ # Unbound task control may change anything; its reply verifies nothing.
+ assert claim.unknown_scope and assessment.verdict is fx.EffectVerdict.UNVERIFIED
+
+
+def test_assessment_scales_to_long_lineages(store):
+ from time import perf_counter
+ log = EffectLog("f" * 32, directory=store, durable=False)
+ owned = [fx.resource_ref(OwnedResource("notes", "u", "t", "notes", f"n{i}", "r"), "record") for i in range(600)]
+ for i, ref in enumerate(owned):
+ log.claim(effect_id=f"e{i}", action_id=f"a{i}", operation=fx.OperationRef("manage_notes", "", "0" * 64),
+ impact_scope=(ref,), obligations=(fx.Postcondition(ref, fx.Predicate.EXISTS),))
+ log.outcome(effect_id=f"e{i}", execution=fx.ExecutionOutcome.REPORTED_SUCCESS, impact=fx.Impact.POSSIBLE)
+ log.observe(observation_id=f"o{i}", resource=ref, mechanism=fx.ObservationMechanism.OWNED_RECORD_READ,
+ coverage=fx.Coverage.PARTIAL, source_action_id=f"r{i}", exists=True)
+ started = perf_counter()
+ assessments = log.assessments()
+ assert perf_counter() - started < 10
+ assert {a.verdict for a in assessments} == {fx.EffectVerdict.VERIFIED}
+
+
def test_classification_failure_claims_unknown_scope(store, monkeypatch):
journal = journal_for(store)
monkeypatch.setattr(adapters, "classify", lambda capture: (_ for _ in ()).throw(KeyError("bug")))