feat: improve worker diagnostics

.env.example

@@ -11,6 +11,7 @@ GITEA_RUNNING_LABEL=ai:running
 GITEA_READY_LABEL=ai:ready
 GITEA_FAILED_LABEL=ai:failed
 POLL_SECONDS=60
+LOG_LEVEL=INFO
 
 AGENT_MODEL=mistral/devstral-latest
 MISTRAL_API_KEY=

README.md

@@ -44,6 +44,10 @@ Start the worker with Docker Compose. Use `lai-agent check` inside the image for
 validation, `lai-agent preflight` for clean-clone setup and tests without a model call, or
 `lai-agent once` for a single polling cycle.
 
+Set `LOG_LEVEL=DEBUG` to include redacted output from setup and test commands. Agent runs always
+log their model, configured limits, call count, cost, exit status, and trajectory path. `INFO` is
+the default for normal operation.
+
 ## Archived implementation
 
 The previous database-polling Aider implementation is preserved unchanged in `old_2026-08-31/`.

docker-compose.yml

@@ -20,6 +20,7 @@ services:
       AGENT_TIMEOUT_SECONDS: ${AGENT_TIMEOUT_SECONDS:-1200}
       AGENT_STEP_LIMIT: ${AGENT_STEP_LIMIT:-50}
       AGENT_COST_LIMIT: ${AGENT_COST_LIMIT:-5}
+      LOG_LEVEL: ${LOG_LEVEL:-INFO}
       AGENT_USER: coder
       MISTRAL_API_KEY: ${MISTRAL_API_KEY:-}
       POLL_SECONDS: ${POLL_SECONDS:-60}

src/lai_automation/agent.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import logging
 from pathlib import Path
 
 from minisweagent.agents.default import DefaultAgent
@@ -9,6 +10,8 @@ from .config import Settings
 from .models import AgentResult, Issue
 from .security import SafeLocalEnvironment
 
+logger = logging.getLogger(__name__)
+
 _SYSTEM_TEMPLATE = """You are a careful coding agent working in one checked-out repository.
 Solve only the supplied issue. Inspect existing code and tests before editing.
 Keep the patch minimal, add or update regression tests, and preserve public APIs
@@ -80,6 +83,17 @@ class MiniSWEAgentRunner:
 		workspace: Path,
 		trajectory_path: Path,
 	) -> AgentResult:
+		logger.info(
+			"Starting agent for issue #%s: model=%s step_limit=%s cost_limit=%.2f "
+			"wall_time_limit=%ss command_timeout=%ss trajectory=%s",
+			issue.number,
+			self.settings.agent_model,
+			self.settings.agent_step_limit,
+			self.settings.agent_cost_limit,
+			self.settings.agent_wall_time_seconds,
+			self.settings.agent_command_timeout_seconds,
+			trajectory_path,
+		)
 		model_kwargs: dict[str, object] = {
 			"timeout": min(self.settings.agent_wall_time_seconds, 600),
 		}
@@ -117,12 +131,22 @@ class MiniSWEAgentRunner:
 			output_path=trajectory_path,
 		)
 		info = agent.run(self._task(issue))
-		return AgentResult(
+		result = AgentResult(
 			exit_status=str(info.get("exit_status") or "unknown"),
 			submission=str(info.get("submission") or ""),
 			model_calls=agent.n_calls,
 			cost=float(agent.cost),
 		)
+		logger.info(
+			"Agent finished for issue #%s: status=%s model_calls=%s cost=%.4f "
+			"trajectory=%s",
+			issue.number,
+			result.exit_status,
+			result.model_calls,
+			result.cost,
+			trajectory_path,
+		)
+		return result
 
 	@staticmethod
 	def _task(issue: Issue) -> str:

src/lai_automation/cli.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import argparse
 import logging
+import os
 
 from .config import Settings
 from .worker import Worker
@@ -15,7 +16,7 @@ def main() -> None:
         nargs="?",
         default="worker",
     )
-    parser.add_argument("--log-level", default="INFO")
+    parser.add_argument("--log-level", default=os.getenv("LOG_LEVEL", "INFO"))
     arguments = parser.parse_args()
     logging.basicConfig(
         level=getattr(logging, arguments.log_level.upper(), logging.INFO),

src/lai_automation/git.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import logging
 import os
 import pwd
 import re
@@ -15,6 +16,8 @@ from .config import Settings
 from .models import ChangeSummary
 from .security import redact
 
+logger = logging.getLogger(__name__)
+
 _TRAILING_WHITESPACE = re.compile(r"^(.*):(\d+): trailing whitespace\.$")
 
 
@@ -65,6 +68,8 @@ class GitWorkspace:
         extra_environment: Mapping[str, str] | None = None,
         timeout: int = 1800,
     ) -> subprocess.CompletedProcess[str]:
+        safe_command = redact(command, 1_000)
+        logger.info("Running trusted command: %s", safe_command)
         environment, identity = self._safe_process_context(extra_environment)
         result = subprocess.run(
             command,
@@ -83,7 +88,15 @@ class GitWorkspace:
                 8_000,
             )
             detail = f":\n{output}" if output else ""
+            logger.error("Trusted command failed: %s%s", safe_command, detail)
             raise RuntimeError(f"Command failed ({command}){detail}")
+        logger.info("Trusted command completed: %s", safe_command)
+        if result.stdout or result.stderr:
+            logger.debug(
+                "Trusted command output (%s):\n%s",
+                safe_command,
+                redact("\n".join(filter(None, (result.stdout, result.stderr))), 8_000),
+            )
         return result
 
     def summary(self) -> ChangeSummary:

src/lai_automation/worker.py

@@ -93,9 +93,14 @@ class Worker:
                 / "trajectories"
                 / f"issue-{issue.number}-{timestamp}.traj.json"
             )
+            started_at = time.monotonic()
             result = self.agent.run(current_issue, workspace.path, trajectory)
+            elapsed = time.monotonic() - started_at
             if result.exit_status != "Submitted":
-                raise RuntimeError(f"Agent stopped with status {result.exit_status}")
+                details = self._agent_failure_details(result, elapsed, trajectory)
+                raise RuntimeError(
+                    f"Agent stopped with status {result.exit_status}: {details}"
+                )
 
             summary = workspace.summary()
             normalized = workspace.normalize_changed_whitespace(summary)
@@ -177,6 +182,27 @@ class Worker:
         finally:
             workspace.cleanup()
 
+    def _agent_failure_details(
+        self,
+        result,
+        elapsed: float,
+        trajectory,
+    ) -> str:
+        limits: list[str] = []
+        if result.model_calls >= self.settings.agent_step_limit:
+            limits.append(f"step limit reached ({self.settings.agent_step_limit})")
+        if self.settings.agent_cost_limit and result.cost >= self.settings.agent_cost_limit:
+            limits.append(f"cost limit reached ({self.settings.agent_cost_limit:.2f})")
+        if elapsed >= self.settings.agent_wall_time_seconds:
+            limits.append(
+                f"wall-time limit reached ({self.settings.agent_wall_time_seconds}s)"
+            )
+        reason = ", ".join(limits) or "limit source not reported by mini-SWE-agent"
+        return (
+            f"{reason}; model_calls={result.model_calls}; cost={result.cost:.4f}; "
+            f"elapsed={elapsed:.1f}s; trajectory={trajectory}"
+        )
+
     def _pull_request_body(
         self,
         issue: Issue,

tests/test_worker.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from pathlib import Path
 from unittest.mock import Mock, call, patch
 
 from lai_automation.models import (
@@ -158,6 +159,22 @@ def test_run_once_returns_false_without_work(settings) -> None:
     assert Worker(settings, gitea, Mock()).run_once() is False
 
 
+def test_agent_failure_details_identify_step_limit(settings) -> None:
+    worker = Worker(settings, Mock(), Mock())
+    result = AgentResult("LimitsExceeded", "", settings.agent_step_limit, 0.2)
+
+    details = worker._agent_failure_details(
+        result,
+        elapsed=180.0,
+        trajectory=Path("/workspaces/trajectories/issue-43.traj.json"),
+    )
+
+    assert f"step limit reached ({settings.agent_step_limit})" in details
+    assert "model_calls=40" in details
+    assert "cost=0.2000" in details
+    assert "issue-43.traj.json" in details
+
+
 @patch("lai_automation.worker.GitWorkspace")
 def test_preflight_runs_setup_and_tests_without_model(
     GitWorkspace,