mirror of
https://github.com/jxxghp/MoviePilot.git
synced 2026-09-07 00:16:57 +08:00
feat(agent): 合并同批次整理失败的agent重试调用，避免重复浪费token
同一download_hash或同一源目录下的失败记录在5分钟缓冲期内合并为一次agent调用， 批量处理时只识别一次媒体信息后复用到所有文件。
This commit is contained in:
jxxghp
@@ -1,12 +1,13 @@
|
||||
---
|
||||
name: transfer-failed-retry
|
||||
description: Use this skill when you need to retry a failed file transfer/organization. Given a failed transfer history record ID, this skill guides you through querying the failure details, deleting the old record, and re-identifying and re-organizing the file. This skill is automatically triggered when the system detects a transfer failure and the AI agent retry feature is enabled.
|
||||
version: 1
|
||||
description: Use this skill when you need to retry failed file transfers/organizations. Given one or more failed transfer history record IDs, this skill guides you through querying the failure details, deleting the old records, and re-identifying and re-organizing the files. Supports batch processing of multiple files from the same media (e.g., multiple episodes of a TV show). This skill is automatically triggered when the system detects transfer failures and the AI agent retry feature is enabled.
|
||||
allowed-tools: query_transfer_history delete_transfer_history recognize_media transfer_file search_media
|
||||
---
|
||||
|
||||
# Transfer Failed Retry (整理失败重试)
|
||||
|
||||
This skill handles retrying failed file transfers/organizations. When a file transfer fails, you can use this skill to analyze the failure, remove the stale history record, and attempt to re-identify and re-organize the file.
|
||||
This skill handles retrying failed file transfers/organizations. When file transfers fail, you can use this skill to analyze the failures, remove stale history records, and attempt to re-identify and re-organize the files. It supports both single-file and batch retry scenarios.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
@@ -21,15 +22,15 @@ You need the following tools:
|
||||
|
||||
### Step 1: Query the Failed Transfer History
|
||||
|
||||
Use `query_transfer_history` to get details about the failed record. Filter by status `failed` to find the specific record.
|
||||
Use `query_transfer_history` to get details about the failed record(s). Filter by status `failed` to find the specific records.
|
||||
|
||||
If you are given a specific history record ID, query with that ID to understand the failure context:
|
||||
If you are given a specific history record ID (or multiple IDs), query with those IDs to understand the failure context:
|
||||
|
||||
```
|
||||
query_transfer_history(status="failed")
|
||||
```
|
||||
|
||||
From the record, extract the following key information:
|
||||
From each record, extract the following key information:
|
||||
- **id**: The history record ID
|
||||
- **src**: Source file path
|
||||
- **title**: The recognized title (may be incorrect)
|
||||
@@ -53,9 +54,9 @@ Common failure reasons and how to handle them:
|
||||
| 未找到有效的集数信息 | Episode number not recognized | Use `recognize_media` with the file path to get better metadata, or specify season/episode in `transfer_file` |
|
||||
| 未获取到转移目录设置 | No transfer directory configured for this media type | Cannot auto-fix - notify user about directory configuration |
|
||||
|
||||
### Step 3: Delete the Failed History Record
|
||||
### Step 3: Delete the Failed History Record(s)
|
||||
|
||||
Before retrying, you **must** delete the old failed history record. The system skips files that already have a transfer history entry (even failed ones).
|
||||
Before retrying, you **must** delete the old failed history record(s). The system skips files that already have a transfer history entry (even failed ones).
|
||||
|
||||
```
|
||||
delete_transfer_history(history_id=<record_id>)
|
||||
@@ -101,8 +102,54 @@ For TV shows where episode info couldn't be determined:
|
||||
### Step 5: Report Result
|
||||
|
||||
After the retry attempt, report the result:
|
||||
- If successful: Confirm the file has been organized correctly
|
||||
- If successful: Confirm the file(s) have been organized correctly
|
||||
- If failed again: Report the new error and suggest manual intervention
|
||||
- For batch operations: Report a summary (e.g., "成功 8/10，失败 2/10")
|
||||
|
||||
## Batch Processing (批量处理)
|
||||
|
||||
When multiple files from the same source fail simultaneously (e.g., 10 episodes of the same TV show all fail with the same error), the system groups them and triggers a single batch retry.
|
||||
|
||||
### Key Optimization Rules for Batch Processing:
|
||||
|
||||
1. **Identify media ONCE, apply to ALL files**: Since batch files typically belong to the same media, perform media recognition (`recognize_media`) or search (`search_media`) only ONCE using the first file, then reuse the result (tmdbid, media_type) for all subsequent files.
|
||||
|
||||
2. **Process each file individually for delete + transfer**: Even though the media identity is shared, you must still:
|
||||
- Delete each failed history record individually
|
||||
- Transfer each file individually (they have different source paths)
|
||||
|
||||
3. **Stop early if root cause is unfixable**: If the first file fails due to an unfixable issue (e.g., missing directory configuration), skip all remaining files with the same error rather than retrying each one.
|
||||
|
||||
4. **Process in order**: Handle files sequentially to avoid race conditions.
|
||||
|
||||
### Batch Example Flow:
|
||||
|
||||
```
|
||||
# Given failed records: IDs = [42, 43, 44, 45] (4 episodes of the same show)
|
||||
# All have errmsg="未识别到媒体信息"
|
||||
|
||||
# 1. Query all failed records
|
||||
query_transfer_history(status="failed")
|
||||
|
||||
# 2. Identify media ONCE using the first file
|
||||
recognize_media(path="/downloads/Show.Name.S01E01.1080p.mkv")
|
||||
# Found: tmdb_id=789, media_type="tv"
|
||||
|
||||
# 3. For each record: delete history, then re-transfer
|
||||
delete_transfer_history(history_id=42)
|
||||
transfer_file(file_path="/downloads/Show.Name.S01E01.1080p.mkv", tmdbid=789, media_type="tv")
|
||||
|
||||
delete_transfer_history(history_id=43)
|
||||
transfer_file(file_path="/downloads/Show.Name.S01E02.1080p.mkv", tmdbid=789, media_type="tv")
|
||||
|
||||
delete_transfer_history(history_id=44)
|
||||
transfer_file(file_path="/downloads/Show.Name.S01E03.1080p.mkv", tmdbid=789, media_type="tv")
|
||||
|
||||
delete_transfer_history(history_id=45)
|
||||
transfer_file(file_path="/downloads/Show.Name.S01E04.1080p.mkv", tmdbid=789, media_type="tv")
|
||||
|
||||
# 4. Report summary: "重试完成：4/4 成功"
|
||||
```
|
||||
|
||||
## Important Notes
|
||||
|
||||
@@ -111,9 +158,10 @@ After the retry attempt, report the result:
|
||||
- **Do not retry** if the error is about missing directory configuration - this requires user intervention.
|
||||
- **For unrecognized media**, always try `recognize_media` with the file path first before falling back to `search_media`.
|
||||
- **Be cautious with TV shows** - ensure the correct season and episode information is used.
|
||||
- When this skill is triggered automatically by the system, it provides the `history_id` directly. Start from Step 1 with that specific ID.
|
||||
- **For batch processing**, always reuse media identification results across all files to save time and resources.
|
||||
- When this skill is triggered automatically by the system, it provides the `history_id`(s) directly. Start from Step 1 with those specific IDs.
|
||||
|
||||
## Example: Complete Retry Flow
|
||||
## Example: Single File Retry Flow
|
||||
|
||||
```
|
||||
# 1. Query the failed record
|
||||
|
||||
Reference in New Issue
Block a user