Add LLM-assisted deploy retry

codex_context.yaml

@@ -75,6 +75,9 @@ SESSION_STATE:
     D15: "Extended ./deploy_agent.py with deploy_service(service): generates compose, writes ./deployments/<service[-n]>/docker-compose.yml without overwriting existing directories, runs 'docker compose up -d' via subprocess, returns DEPLOYED or ERROR."
     D16: "Updated ./deploy_agent.py with get_service_status(path), post-deploy 'docker compose ps' verification requiring 'Up', error outputs including ps output when available, and pre-deploy 'docker ps' port-80 check that adds prompt note 'Use a different port than 80'."
     D17: "User requested git commit on 2026-04-22; commit scope includes ./deploy_agent.py and ./codex_context.yaml for deployment status and safety updates."
+    D18: "Git commit created on 2026-04-22: 0abe9cb 'Improve deploy agent safety checks'."
+    D19: "Updated ./deploy_agent.py to use local LLM for one bounded deployment-failure retry: capture service/error/status, request corrected YAML only, replace docker-compose.yml, retry once, then return final error plus last status if still failing."
+    D20: "User requested git commit on 2026-04-22; commit scope includes ./deploy_agent.py and ./codex_context.yaml for one-shot LLM-assisted deployment failure recovery."
   todos:
     T1: "For all future meaningful changes/decisions, update and overwrite ./codex_context.yaml."
     T2: "DONE: Commit current changes."
@@ -89,6 +92,8 @@ SESSION_STATE:
     T11: "DONE: Add docker-compose YAML validation and retry logic."
     T12: "DONE: Add automatic service deployment workflow."
     T13: "DONE: Add deployment status verification and basic port-80 safety check."
+    T14: "DONE: Commit deploy agent safety/status updates."
+    T15: "DONE: Add one-shot LLM-assisted deployment failure recovery."
   issues:
     I1: "Tailscale DNS health warning: configured DNS servers unreachable."
     I2: "Preferred gateway path unavailable: 100.108.208.3:8080 connection failed."

deploy_agent.py

@@ -43,6 +43,30 @@ def generate_compose(service: str) -> str:
     return _generate_compose(service)
 
 
+def _is_valid_compose(compose: str) -> bool:
+    try:
+        parsed = yaml.safe_load(compose)
+    except yaml.YAMLError:
+        return False
+    return isinstance(parsed, dict) and "services" in parsed
+
+
+def _fix_compose(service: str, error: str, status: str) -> str:
+    prompt = (
+        "Deployment failed.\n\n"
+        f"Service: {service}\n\n"
+        f"Error: {error}\n\n"
+        f"Status: {status}\n\n"
+        "Fix the docker-compose YAML. Return ONLY corrected YAML."
+    )
+    response = ask(prompt)
+    if response.startswith("ERROR:"):
+        return response
+    if not _is_valid_compose(response):
+        return "ERROR: invalid docker-compose"
+    return response
+
+
 def get_service_status(path: Path) -> str:
     try:
         result = subprocess.run(
@@ -61,6 +85,23 @@ def get_service_status(path: Path) -> str:
     return output
 
 
+def _run_compose_up(path: Path) -> tuple[bool, str]:
+    try:
+        result = subprocess.run(
+            ["docker", "compose", "up", "-d"],
+            cwd=path,
+            check=False,
+            capture_output=True,
+            text=True,
+        )
+    except Exception as exc:
+        return False, str(exc)
+    if result.returncode != 0:
+        error = result.stderr.strip() or result.stdout.strip() or "docker compose up failed"
+        return False, error
+    return True, result.stdout.strip()
+
+
 def deploy_service(service: str) -> str:
     prompt_extra = ""
     try:
@@ -91,19 +132,21 @@ def deploy_service(service: str) -> str:
     compose_path = target_dir / "docker-compose.yml"
     compose_path.write_text(compose, encoding="utf-8")
 
-    try:
+    ok, error = _run_compose_up(target_dir)
-        subprocess.run(
+    if not ok:
-            ["docker", "compose", "up", "-d"],
+        status = get_service_status(target_dir)
-            cwd=target_dir,
+        fixed_compose = _fix_compose(service, error, status)
-            check=True,
+        if fixed_compose.startswith("ERROR:"):
-            capture_output=True,
+            if status and not status.startswith("ERROR:"):
-            text=True,
+                return f"ERROR: {error}\n{status}"
-        )
+            return f"ERROR: {error}"
-    except subprocess.CalledProcessError as exc:
+        compose_path.write_text(fixed_compose, encoding="utf-8")
-        message = exc.stderr.strip() or exc.stdout.strip() or str(exc)
+        ok, error = _run_compose_up(target_dir)
-        return f"ERROR: {message}"
+        if not ok:
-    except Exception as exc:
+            status = get_service_status(target_dir)
-        return f"ERROR: {exc}"
+            if status and not status.startswith("ERROR:"):
+                return f"ERROR: {error}\n{status}"
+            return f"ERROR: {error}"
 
     status = get_service_status(target_dir)
     if status.startswith("ERROR:"):