The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
docs: tighten videodb listener guidance
Affaan Mustafa70449a1cd7e6
diff --git a/skills/videodb/SKILL.md b/skills/videodb/SKILL.mdindex e9195d7da..02c417d9e 100644--- a/skills/videodb/SKILL.md+++ b/skills/videodb/SKILL.md@@ -10,7 +10,7 @@ argument-hint: "[task description]"**Perception + memory + actions for video, live streams, and desktop sessions.**-## When to Use+## When to use### Desktop Perception- Start/stop a **desktop session** capturing **screen, mic, and system audio**@@ -37,7 +37,7 @@ argument-hint: "[task description]"- Connect **RTSP/live feeds**- Run **real-time visual and spoken understanding** and emit **events/alerts** for monitoring workflows-## How It Works+## How it works### Common inputs- Local **file path**, public **URL**, or **RTSP URL**diff --git a/skills/videodb/reference/capture-reference.md b/skills/videodb/reference/capture-reference.mdindex 302e0ef12..125653ea5 100644--- a/skills/videodb/reference/capture-reference.md+++ b/skills/videodb/reference/capture-reference.md@@ -383,8 +383,13 @@ For RTStream methods (indexing, transcription, alerts, batch config), see [rtstr│ active │ ──> Start AI pipelines└───────┬──────────────┐│ │- │ └──────────────┐- │ client.stop_capture() │ unrecoverable capture error+ │ v+ │ ┌───────────────┐ WebSocket: capture_session.failed+ │ │ failed │ ──> Inspect error payload and retry setup+ │ └───────────────┘+ │ unrecoverable capture error+ │+ │ client.stop_capture()v┌───────────────┐ WebSocket: capture_session.stopping│ stopping │ ──> Finalize streams@@ -399,11 +404,4 @@ For RTStream methods (indexing, transcription, alerts, batch config), see [rtstr┌───────────────┐ WebSocket: capture_session.exported│ exported │ ──> Access video_id, stream_url, player_url└───────────────┘-- unrecoverable capture error- │- v- ┌───────────────┐ WebSocket: capture_session.failed- │ failed │ ──> Inspect error payload and retry setup- └───────────────┘```diff --git a/skills/videodb/reference/generative.md b/skills/videodb/reference/generative.mdindex e71f31c23..8b36c524e 100644--- a/skills/videodb/reference/generative.md+++ b/skills/videodb/reference/generative.md@@ -165,7 +165,7 @@ Combine scene extraction with text generation:from videodb import SceneExtractionType# First index scenes-video.index_scenes(+scenes = video.index_scenes(extraction_type=SceneExtractionType.time_based,extraction_config={"time": 10},prompt="Describe the visual content in this scene.",@@ -173,11 +173,21 @@ video.index_scenes(# Get transcript for spoken contexttranscript_text = video.get_transcript_text()+scene_descriptions = []+for scene in scenes:+ if isinstance(scene, dict):+ description = scene.get("description") or scene.get("summary")+ else:+ description = getattr(scene, "description", None) or getattr(scene, "summary", None)+ scene_descriptions.append(description or str(scene))++scenes_text = "\n".join(scene_descriptions)# Analyze with collection LLMresult = coll.generate_text(prompt=(f"Given this video transcript:\n{transcript_text}\n\n"+ f"And these visual scene descriptions:\n{scenes_text}\n\n""Based on the spoken and visual content, describe the main topics covered."),model_name="pro",diff --git a/skills/videodb/scripts/ws_listener.py b/skills/videodb/scripts/ws_listener.pyindex 456bfb203..105aabc77 100644--- a/skills/videodb/scripts/ws_listener.py+++ b/skills/videodb/scripts/ws_listener.py@@ -39,6 +39,7 @@ from dotenv import load_dotenvload_dotenv()import videodb+from videodb.exceptions import AuthenticationError# Retry configMAX_RETRIES = 10@@ -82,6 +83,8 @@ def parse_args() -> tuple[bool, Path]:for arg in args:if arg == "--clear":clear = True+ elif arg.startswith("-"):+ raise SystemExit(f"Unknown flag: {arg}")elif not arg.startswith("-"):output_dir = arg@@ -127,6 +130,17 @@ def cleanup_pid():LOGGER.debug("Failed to remove PID file %s: %s", PID_FILE, exc)+def is_fatal_error(exc: Exception) -> bool:+ """Return True when retrying would hide a permanent configuration error."""+ if isinstance(exc, (AuthenticationError, PermissionError)):+ return True+ status = getattr(exc, "status_code", None)+ if status in {401, 403}:+ return True+ message = str(exc).lower()+ return "401" in message or "403" in message or "auth" in message++async def listen_with_retry():"""Main listen loop with auto-reconnect and exponential backoff."""global _first_connection@@ -143,7 +157,12 @@ async def listen_with_retry():except asyncio.CancelledError:log("Shutdown requested")raise- except RETRYABLE_ERRORS as e:+ except Exception as e:+ if is_fatal_error(e):+ log(f"Fatal configuration error: {e}")+ raise+ if not isinstance(e, RETRYABLE_ERRORS):+ raiseretry_count += 1log(f"Connection error: {e}")@@ -182,7 +201,12 @@ async def listen_with_retry():except asyncio.CancelledError:log("Shutdown requested")raise- except RETRYABLE_ERRORS as e:+ except Exception as e:+ if is_fatal_error(e):+ log(f"Fatal configuration error: {e}")+ raise+ if not isinstance(e, RETRYABLE_ERRORS):+ raiseretry_count += 1log(f"Connection error: {e}")