Compare commits
16 Commits
v2026.03.0
...
async-cont
| Author | SHA1 | Date | |
|---|---|---|---|
|
cd95b5ff69 | ||
|
|
3210262296 | ||
|
|
37a130993a | ||
|
|
b75fd96e4a | ||
|
|
5dd9d6cc56 | ||
|
|
d569dc3ec9 | ||
|
|
e2426c74e1 | ||
|
|
ae0fa1d39a | ||
|
|
62e78ace5c | ||
|
|
7efb64b16b | ||
|
|
2eee7c5d35 | ||
|
|
9bf31488ae | ||
|
|
ef86a2c3c4 | ||
|
|
b4c6d23dfb | ||
|
|
6102851e55 | ||
|
|
79c1fde217 |
@@ -0,0 +1,27 @@
|
||||
# Async Context Compression Progress Mapping
|
||||
|
||||
> Discovered: 2026-03-10
|
||||
|
||||
## Context
|
||||
Applies to `plugins/filters/async-context-compression/async_context_compression.py` once the inlet has already replaced early history with a synthetic summary message.
|
||||
|
||||
## Finding
|
||||
`compressed_message_count` cannot be recalculated from the visible message list length after compression. Once a summary marker is present, the visible list mixes:
|
||||
- preserved head messages that are still before the saved boundary
|
||||
- one synthetic summary message
|
||||
- tail messages that map to original history starting at the saved boundary
|
||||
|
||||
## Solution / Pattern
|
||||
Store the original-history boundary on the injected summary message metadata, then recover future progress using:
|
||||
- `original_count = covered_until + len(messages_after_summary_marker)`
|
||||
- `target_progress = max(covered_until, original_count - keep_last)`
|
||||
|
||||
When the summary-model window is too small, trim newest atomic groups from the summary input so the saved boundary still matches what the summary actually covers.
|
||||
|
||||
## Gotchas
|
||||
- If you trim from the head of the summary input, the saved progress can overstate coverage and hide messages that were never summarized.
|
||||
- Status previews for the next context must convert the saved original-history boundary back into the current visible view before rebuilding head/summary/tail.
|
||||
- `inlet(body["messages"])` and `outlet(body["messages"])` can both represent the full conversation while using different serializations:
|
||||
- inlet may receive expanded native tool-call chains (`assistant(tool_calls) -> tool -> assistant`)
|
||||
- outlet may receive a compact top-level transcript where tool calls are folded into assistant `<details type="tool_calls">` blocks
|
||||
- These two views do not share a safe `compressed_message_count` coordinate system. If outlet is in the compact assistant/details view, do not persist summary progress derived from its top-level message count.
|
||||
26
.agent/learnings/openwebui-tool-call-context-inflation.md
Normal file
26
.agent/learnings/openwebui-tool-call-context-inflation.md
Normal file
@@ -0,0 +1,26 @@
|
||||
# OpenWebUI Tool Call Context Inflation
|
||||
|
||||
> Discovered: 2026-03-11
|
||||
|
||||
## Context
|
||||
When analyzing why the `async_context_compression` plugin sees different array lengths of `messages` between the `inlet` (e.g. 27 items) and `outlet` (e.g. 8 items) phases, especially when native tool calling (Function Calling) is involved in OpenWebUI.
|
||||
|
||||
## Finding
|
||||
There is a fundamental disparity in how OpenWebUI serializes conversational history at different stages of the request lifecycle:
|
||||
|
||||
1. **Outlet (UI Rendering View)**:
|
||||
After the LLM completes generation and tools have been executed, OpenWebUI's `middleware.py` (and streaming builders) bundles intermediate tool calls and their raw results. It hides them inside an HTML `<details type="tool_calls">...</details>` block within a single `role: assistant` message's `content`.
|
||||
Concurrently, the actual native API tool-calling data is saved in a hidden `output` dict field attached to that message. At this stage, the `messages` array looks short (e.g., 8 items) because tool interactions are visually folded.
|
||||
|
||||
2. **Inlet (LLM Native View)**:
|
||||
When the user sends the *next* message, the request enters `main.py` -> `process_chat_payload` -> `middleware.py:process_messages_with_output()`.
|
||||
Here, OpenWebUI scans historical `assistant` messages for that hidden `output` field. If found, it completely **inflates (unfolds)** the raw data back into an exact sequence of OpenAI-compliant `tool_call` and `tool_result` messages (using `utils/misc.py:convert_output_to_messages`).
|
||||
The HTML `<details>` string is entirely discarded before being sent to the LLM.
|
||||
|
||||
**Conclusion on Token Consumption**:
|
||||
In the next turn, tool context is **NOT** compressed at all. It is fully re-expanded to its original verbose state (e.g., back to 27 items) and consumes the maximum amount of tokens required by the raw JSON arguments and results.
|
||||
|
||||
## Gotchas
|
||||
- Any logic operating in the `outlet` phase (like background tasks) that relies on the `messages` array index will be completely misaligned with the array seen in the `inlet` phase.
|
||||
- Attempting to slice or trim history based on `outlet` array lengths will cause index out-of-bounds errors or destructive cropping of recent messages.
|
||||
- The only safe way to bridge these two views is either to translate the folded view back into the expanded view using `convert_output_to_messages`, or to rely on unique `id` fields (if available) rather than array indices.
|
||||
@@ -73,11 +73,21 @@ Create two versioned release notes files:
|
||||
#### Required Sections
|
||||
|
||||
Each file must include:
|
||||
1. **Title**: `# v{version} Release Notes` (EN) / `# v{version} 版本发布说明` (CN)
|
||||
2. **Overview**: One paragraph summarizing this release
|
||||
3. **New Features** / **新功能**: Bulleted list of features
|
||||
4. **Bug Fixes** / **问题修复**: Bulleted list of fixes
|
||||
5. **Migration Notes** / **迁移说明**: Breaking changes or Valve key renames (omit section if none)
|
||||
0. **Marketplace Badge**: A prominent button linking to the plugin on openwebui.com using shields.io (e.g., `[](URL)`).
|
||||
1. **Overview Header**: Use `## Overview` as the first header.
|
||||
2. **Summary Paragraph**: A paragraph summarizing the release. **NEVER** include the version number as a title.
|
||||
3. **README Link**: Direct link to the plugin's README file on GitHub.
|
||||
4. **New Features** / **新功能**: Bulleted list of features
|
||||
5. **Bug Fixes** / **问题修复**: Bulleted list of fixes
|
||||
6. **Related Issues** / **相关 Issue**: Link to GitHub Issues. **ONLY** include if a specific issue is resolved. **NEVER use placeholders.**
|
||||
7. **Related PRs** / **相关 PR**: Link to the Pull Request. **ONLY** include if the PR is already created and the ID is known. **NEVER use placeholders.**
|
||||
8. **Migration Notes**: Breaking changes or Valve key renames (omit section if none)
|
||||
|
||||
---
|
||||
|
||||
## Language Standard
|
||||
|
||||
- **Release Notes Files**: Use **English ONLY** for the final `.md` files to maintain professional consistency on GitHub. Avoid bilingual content in the release description.
|
||||
6. **Companion Plugins** / **配套插件** (optional): If a companion plugin was updated
|
||||
|
||||
If a release notes file already exists for this version, update it rather than creating a new one.
|
||||
@@ -98,8 +108,10 @@ Generate the commit message following `commit-message.instructions.md` rules:
|
||||
- **Language**: English ONLY
|
||||
- **Format**: `type(scope): subject` + blank line + body bullets
|
||||
- **Scope**: use plugin folder name (e.g., `github-copilot-sdk`)
|
||||
- **Body**: 1-3 bullets summarizing key changes
|
||||
- Explicitly mention "READMEs and docs synced" if version was bumped
|
||||
- **Body**:
|
||||
- 1-3 bullets summarizing key changes
|
||||
- Explicitly mention "READMEs and docs synced" if version was bumped
|
||||
- **MUST** end with `Closes #XX` or `Fixes #XX` if an issue is being resolved.
|
||||
|
||||
Present the full commit message to the user for review before executing.
|
||||
|
||||
|
||||
23
.github/agents/release-prep.agent.md
vendored
23
.github/agents/release-prep.agent.md
vendored
@@ -78,5 +78,28 @@ Plugin: {type}/{name} → v{new_version}
|
||||
### Verification Status
|
||||
{filled-in 9-file checklist for each changed plugin}
|
||||
|
||||
## Post-Release: Batch Plugin Installation
|
||||
|
||||
After release is published, users can quickly install all plugins:
|
||||
|
||||
```bash
|
||||
# Clone the repository
|
||||
git clone https://github.com/Fu-Jie/openwebui-extensions.git
|
||||
cd openwebui-extensions
|
||||
|
||||
# Setup API key and instance URL
|
||||
echo "api_key=sk-your-api-key-here" > scripts/.env
|
||||
echo "url=http://localhost:3000" >> scripts/.env
|
||||
|
||||
# If using remote instance, configure the baseURL:
|
||||
# echo "url=http://192.168.1.10:3000" >> scripts/.env
|
||||
# echo "url=https://openwebui.example.com" >> scripts/.env
|
||||
|
||||
# Install all plugins at once
|
||||
python scripts/install_all_plugins.py
|
||||
```
|
||||
|
||||
See: [Deployment Guide](./scripts/DEPLOYMENT_GUIDE.md)
|
||||
|
||||
---
|
||||
⚠️ **Waiting for user confirmation — no git operations will run until explicitly approved.**
|
||||
|
||||
183
.github/workflows/release.yml
vendored
183
.github/workflows/release.yml
vendored
@@ -5,13 +5,13 @@
|
||||
# Triggers:
|
||||
# - Push to main branch when plugins are modified (auto-release)
|
||||
# - Manual trigger (workflow_dispatch) with custom release notes
|
||||
# - Push of version tags (v*)
|
||||
# - Push of plugin version tags (<plugin>-v*)
|
||||
#
|
||||
# What it does:
|
||||
# 1. Detects plugin version changes compared to the last release
|
||||
# 2. Generates release notes with updated plugin information
|
||||
# 3. Creates a GitHub Release with plugin files as downloadable assets
|
||||
# 4. Supports multiple plugin updates in a single release
|
||||
# 4. Enforces one plugin creation/update per release
|
||||
|
||||
name: Plugin Release
|
||||
|
||||
@@ -28,13 +28,14 @@ on:
|
||||
- 'plugins/**/v*_CN.md'
|
||||
- 'docs/plugins/**/*.md'
|
||||
tags:
|
||||
- '*-v*'
|
||||
- 'v*'
|
||||
|
||||
# Manual trigger with inputs
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Release version (e.g., v1.0.0). Leave empty for auto-generated version.'
|
||||
description: 'Release tag (e.g., markdown-normalizer-v1.2.8). Leave empty for auto-generated tag.'
|
||||
required: false
|
||||
type: string
|
||||
release_title:
|
||||
@@ -65,7 +66,9 @@ jobs:
|
||||
outputs:
|
||||
has_changes: ${{ steps.detect.outputs.has_changes }}
|
||||
changed_plugins: ${{ steps.detect.outputs.changed_plugins }}
|
||||
changed_plugin_titles: ${{ steps.detect.outputs.changed_plugin_titles }}
|
||||
changed_plugin_title: ${{ steps.detect.outputs.changed_plugin_title }}
|
||||
changed_plugin_slug: ${{ steps.detect.outputs.changed_plugin_slug }}
|
||||
changed_plugin_version: ${{ steps.detect.outputs.changed_plugin_version }}
|
||||
changed_plugin_count: ${{ steps.detect.outputs.changed_plugin_count }}
|
||||
release_notes: ${{ steps.detect.outputs.release_notes }}
|
||||
has_doc_changes: ${{ steps.detect.outputs.has_doc_changes }}
|
||||
@@ -95,12 +98,12 @@ jobs:
|
||||
run: |
|
||||
# Always compare against the most recent previously released version.
|
||||
CURRENT_TAG=""
|
||||
if [[ "${GITHUB_REF}" == refs/tags/v* ]]; then
|
||||
if [[ "${GITHUB_REF}" == refs/tags/* ]]; then
|
||||
CURRENT_TAG="${GITHUB_REF#refs/tags/}"
|
||||
echo "Current tag event detected: $CURRENT_TAG"
|
||||
fi
|
||||
|
||||
PREVIOUS_RELEASE_TAG=$(git tag --sort=-creatordate | grep -E '^v' | grep -Fxv "$CURRENT_TAG" | head -n1 || true)
|
||||
PREVIOUS_RELEASE_TAG=$(git tag --sort=-creatordate | grep -Fxv "$CURRENT_TAG" | head -n1 || true)
|
||||
|
||||
if [ -n "$PREVIOUS_RELEASE_TAG" ]; then
|
||||
echo "Comparing with previous release tag: $PREVIOUS_RELEASE_TAG"
|
||||
@@ -162,22 +165,80 @@ jobs:
|
||||
# Only trigger release if there are actual version changes, not just doc changes
|
||||
echo "has_changes=false" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugins=" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_titles=" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_title=" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_slug=" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_version=" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_count=0" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "has_changes=true" >> $GITHUB_OUTPUT
|
||||
|
||||
# Extract changed plugin file paths and titles using Python
|
||||
python3 -c "import json; data = json.load(open('changes.json', 'r')); get_title = lambda plugin: ((plugin.get('data', {}).get('function', {}).get('meta', {}).get('manifest', {}).get('title')) or plugin.get('title') or '').strip(); files = []; [files.append(plugin['file_path']) for plugin in data.get('added', []) if plugin.get('file_path')]; [files.append(update['current']['file_path']) for update in data.get('updated', []) if update.get('current', {}).get('file_path')]; print('\\n'.join(files))" > changed_files.txt
|
||||
|
||||
python3 -c "import json; data = json.load(open('changes.json', 'r')); get_title = lambda plugin: ((plugin.get('data', {}).get('function', {}).get('meta', {}).get('manifest', {}).get('title')) or plugin.get('title') or '').strip(); titles = []; [titles.append(title) for plugin in data.get('added', []) for title in [get_title(plugin)] if title and title not in titles]; [titles.append(title) for update in data.get('updated', []) for title in [get_title(update.get('current', {}))] if title and title not in titles]; print(', '.join(titles)); open('changed_plugin_count.txt', 'w').write(str(len(titles)))" > changed_plugin_titles.txt
|
||||
# Extract changed plugin metadata and enforce a single-plugin release.
|
||||
python3 <<'PY'
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
data = json.load(open('changes.json', 'r', encoding='utf-8'))
|
||||
|
||||
def get_plugin_meta(plugin):
|
||||
manifest = plugin.get('data', {}).get('function', {}).get('meta', {}).get('manifest', {})
|
||||
title = (manifest.get('title') or plugin.get('title') or '').strip()
|
||||
version = (manifest.get('version') or plugin.get('version') or '').strip()
|
||||
file_path = (plugin.get('file_path') or '').strip()
|
||||
slug = Path(file_path).parent.name.replace('_', '-').strip() if file_path else ''
|
||||
return {
|
||||
'title': title,
|
||||
'slug': slug,
|
||||
'version': version,
|
||||
'file_path': file_path,
|
||||
}
|
||||
|
||||
plugins = []
|
||||
seen_keys = set()
|
||||
|
||||
for plugin in data.get('added', []):
|
||||
meta = get_plugin_meta(plugin)
|
||||
key = meta['file_path'] or meta['title']
|
||||
if key and key not in seen_keys:
|
||||
plugins.append(meta)
|
||||
seen_keys.add(key)
|
||||
|
||||
for update in data.get('updated', []):
|
||||
meta = get_plugin_meta(update.get('current', {}))
|
||||
key = meta['file_path'] or meta['title']
|
||||
if key and key not in seen_keys:
|
||||
plugins.append(meta)
|
||||
seen_keys.add(key)
|
||||
|
||||
Path('changed_files.txt').write_text(
|
||||
'\n'.join(meta['file_path'] for meta in plugins if meta['file_path']),
|
||||
encoding='utf-8',
|
||||
)
|
||||
Path('changed_plugin_count.txt').write_text(str(len(plugins)), encoding='utf-8')
|
||||
|
||||
if len(plugins) > 1:
|
||||
print('Error: release workflow only supports one plugin creation/update per release.', file=sys.stderr)
|
||||
for meta in plugins:
|
||||
print(
|
||||
f"- {meta['title'] or 'Unknown'} v{meta['version'] or '?'} ({meta['file_path'] or 'unknown path'})",
|
||||
file=sys.stderr,
|
||||
)
|
||||
sys.exit(1)
|
||||
|
||||
selected = plugins[0] if plugins else {'title': '', 'slug': '', 'version': ''}
|
||||
Path('changed_plugin_title.txt').write_text(selected['title'], encoding='utf-8')
|
||||
Path('changed_plugin_slug.txt').write_text(selected['slug'], encoding='utf-8')
|
||||
Path('changed_plugin_version.txt').write_text(selected['version'], encoding='utf-8')
|
||||
PY
|
||||
|
||||
echo "changed_plugins<<EOF" >> $GITHUB_OUTPUT
|
||||
cat changed_files.txt >> $GITHUB_OUTPUT
|
||||
echo "" >> $GITHUB_OUTPUT
|
||||
echo "EOF" >> $GITHUB_OUTPUT
|
||||
|
||||
echo "changed_plugin_titles=$(cat changed_plugin_titles.txt)" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_title=$(cat changed_plugin_title.txt)" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_slug=$(cat changed_plugin_slug.txt)" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_version=$(cat changed_plugin_version.txt)" >> $GITHUB_OUTPUT
|
||||
echo "changed_plugin_count=$(cat changed_plugin_count.txt)" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
|
||||
@@ -191,7 +252,7 @@ jobs:
|
||||
|
||||
release:
|
||||
needs: check-changes
|
||||
if: needs.check-changes.outputs.has_changes == 'true' || github.event_name == 'workflow_dispatch' || startsWith(github.ref, 'refs/tags/v')
|
||||
if: needs.check-changes.outputs.has_changes == 'true' || github.event_name == 'workflow_dispatch' || startsWith(github.ref, 'refs/tags/')
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
LANG: en_US.UTF-8
|
||||
@@ -219,53 +280,34 @@ jobs:
|
||||
id: version
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
CHANGED_PLUGIN_SLUG: ${{ needs.check-changes.outputs.changed_plugin_slug }}
|
||||
CHANGED_PLUGIN_VERSION: ${{ needs.check-changes.outputs.changed_plugin_version }}
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" = "workflow_dispatch" ] && [ -n "${{ github.event.inputs.version }}" ]; then
|
||||
VERSION="${{ github.event.inputs.version }}"
|
||||
elif [[ "${{ github.ref }}" == refs/tags/v* ]]; then
|
||||
elif [[ "${{ github.ref }}" == refs/tags/* ]]; then
|
||||
VERSION="${GITHUB_REF#refs/tags/}"
|
||||
elif [ -n "$CHANGED_PLUGIN_SLUG" ] && [ -n "$CHANGED_PLUGIN_VERSION" ]; then
|
||||
VERSION="${CHANGED_PLUGIN_SLUG}-v${CHANGED_PLUGIN_VERSION}"
|
||||
else
|
||||
# Auto-generate version based on date and daily release count
|
||||
TODAY=$(date +'%Y.%m.%d')
|
||||
TODAY_PREFIX="v${TODAY}-"
|
||||
|
||||
# Count existing releases with today's date prefix
|
||||
# grep -c returns 1 if count is 0, so we use || true to avoid script failure
|
||||
EXISTING_COUNT=$(gh release list --limit 100 2>/dev/null | grep -c "^${TODAY_PREFIX}" || true)
|
||||
|
||||
# Clean up output (handle potential newlines or fallback issues)
|
||||
EXISTING_COUNT=$(echo "$EXISTING_COUNT" | tr -cd '0-9')
|
||||
if [ -z "$EXISTING_COUNT" ]; then EXISTING_COUNT=0; fi
|
||||
|
||||
NEXT_NUM=$((EXISTING_COUNT + 1))
|
||||
|
||||
VERSION="${TODAY_PREFIX}${NEXT_NUM}"
|
||||
|
||||
# Final fallback to ensure VERSION is never empty
|
||||
if [ -z "$VERSION" ]; then
|
||||
VERSION="v$(date +'%Y.%m.%d-%H%M%S')"
|
||||
fi
|
||||
echo "Error: failed to determine plugin-scoped release tag." >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
echo "Release version: $VERSION"
|
||||
echo "Release tag: $VERSION"
|
||||
|
||||
- name: Build release metadata
|
||||
id: meta
|
||||
env:
|
||||
VERSION: ${{ steps.version.outputs.version }}
|
||||
INPUT_TITLE: ${{ github.event.inputs.release_title }}
|
||||
CHANGED_PLUGIN_TITLES: ${{ needs.check-changes.outputs.changed_plugin_titles }}
|
||||
CHANGED_PLUGIN_COUNT: ${{ needs.check-changes.outputs.changed_plugin_count }}
|
||||
CHANGED_PLUGIN_TITLE: ${{ needs.check-changes.outputs.changed_plugin_title }}
|
||||
CHANGED_PLUGIN_VERSION: ${{ needs.check-changes.outputs.changed_plugin_version }}
|
||||
run: |
|
||||
if [ -n "$INPUT_TITLE" ]; then
|
||||
RELEASE_NAME="$INPUT_TITLE"
|
||||
elif [ "$CHANGED_PLUGIN_COUNT" = "1" ] && [ -n "$CHANGED_PLUGIN_TITLES" ]; then
|
||||
RELEASE_NAME="$CHANGED_PLUGIN_TITLES $VERSION"
|
||||
elif [ -n "$CHANGED_PLUGIN_TITLES" ] && [ "$CHANGED_PLUGIN_COUNT" = "2" ]; then
|
||||
RELEASE_NAME="$VERSION - $CHANGED_PLUGIN_TITLES"
|
||||
elif [ -n "$CHANGED_PLUGIN_TITLES" ] && [ "${CHANGED_PLUGIN_COUNT:-0}" -gt 2 ]; then
|
||||
FIRST_PLUGIN=$(echo "$CHANGED_PLUGIN_TITLES" | cut -d',' -f1 | xargs)
|
||||
RELEASE_NAME="$VERSION - $FIRST_PLUGIN and $CHANGED_PLUGIN_COUNT plugin updates"
|
||||
elif [ -n "$CHANGED_PLUGIN_TITLE" ] && [ -n "$CHANGED_PLUGIN_VERSION" ]; then
|
||||
RELEASE_NAME="$CHANGED_PLUGIN_TITLE v$CHANGED_PLUGIN_VERSION"
|
||||
else
|
||||
RELEASE_NAME="$VERSION"
|
||||
fi
|
||||
@@ -391,47 +433,37 @@ jobs:
|
||||
VERSION: ${{ steps.version.outputs.version }}
|
||||
TITLE: ${{ github.event.inputs.release_title }}
|
||||
NOTES: ${{ github.event.inputs.release_notes }}
|
||||
CHANGED_PLUGIN_TITLE: ${{ needs.check-changes.outputs.changed_plugin_title }}
|
||||
CHANGED_PLUGIN_VERSION: ${{ needs.check-changes.outputs.changed_plugin_version }}
|
||||
DETECTED_CHANGES: ${{ needs.check-changes.outputs.release_notes }}
|
||||
COMMITS: ${{ steps.commits.outputs.commits }}
|
||||
DOC_FILES: ${{ needs.check-changes.outputs.changed_doc_files }}
|
||||
run: |
|
||||
> release_notes.md
|
||||
|
||||
# 1. Release notes from v*.md files (highest priority, shown first)
|
||||
# 1. Primary content from v*.md files (highest priority)
|
||||
if [ -n "$DOC_FILES" ]; then
|
||||
RELEASE_NOTE_FILES=$(echo "$DOC_FILES" | grep -E '^plugins/.*/v[^/]*\.md$' | grep -v '_CN\.md$' || true)
|
||||
if [ -n "$RELEASE_NOTE_FILES" ]; then
|
||||
while IFS= read -r file; do
|
||||
[ -z "$file" ] && continue
|
||||
if [ -f "$file" ]; then
|
||||
python3 -c "import json, pathlib, re; file_path = pathlib.Path(r'''$file'''); plugin_versions_path = pathlib.Path('plugin_versions.json'); text = file_path.read_text(encoding='utf-8'); plugin_dir = file_path.parent.as_posix(); plugins = json.loads(plugin_versions_path.read_text(encoding='utf-8')) if plugin_versions_path.exists() else []; plugin_title = next((plugin.get('title', '').strip() for plugin in plugins if plugin.get('file_path', '').startswith(plugin_dir + '/')), ''); text = re.sub(r'^#\\s+(v[0-9][^\\n]*Release Notes)\\s*$', '# ' + plugin_title + ' ' + r'\\1', text, count=1, flags=re.MULTILINE) if plugin_title else text; print(text.rstrip())" >> release_notes.md
|
||||
# Extract content, removing any H1 title from the file to avoid duplication
|
||||
python3 -c "import pathlib, re; file_path = pathlib.Path(r'''$file'''); text = file_path.read_text(encoding='utf-8'); text = re.sub(r'^#\s+.+?(?:\r?\n)+', '', text, count=1, flags=re.MULTILINE); print(text.lstrip().rstrip())" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
fi
|
||||
done <<< "$RELEASE_NOTE_FILES"
|
||||
fi
|
||||
fi
|
||||
|
||||
# 2. Plugin version changes detected by script
|
||||
if [ -n "$TITLE" ]; then
|
||||
echo "## $TITLE" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
fi
|
||||
|
||||
# 2. Automated plugin version change summary
|
||||
if [ -n "$DETECTED_CHANGES" ] && ! echo "$DETECTED_CHANGES" | grep -q "No changes detected"; then
|
||||
echo "## What's Changed" >> release_notes.md
|
||||
echo "## Version Changes" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "$DETECTED_CHANGES" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
fi
|
||||
|
||||
# 3. Commits (Conventional Commits format with body)
|
||||
if [ -n "$COMMITS" ]; then
|
||||
echo "## Commits" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "$COMMITS" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
fi
|
||||
|
||||
# 3. Manual additional notes from workflow dispatch
|
||||
if [ -n "$NOTES" ]; then
|
||||
echo "## Additional Notes" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
@@ -441,35 +473,20 @@ jobs:
|
||||
|
||||
cat >> release_notes.md << 'EOF'
|
||||
|
||||
## Download
|
||||
|
||||
📦 **Download the updated plugin files below**
|
||||
|
||||
### Installation
|
||||
|
||||
#### From OpenWebUI Community
|
||||
1. Open OpenWebUI Admin Panel
|
||||
2. Navigate to Functions/Tools
|
||||
3. Search for the plugin name
|
||||
4. Click Install
|
||||
|
||||
#### Manual Installation
|
||||
1. Download the plugin file (`.py`) from the assets below
|
||||
2. Open OpenWebUI Admin Panel → Functions
|
||||
3. Click "Create Function" → Import
|
||||
4. Paste the plugin code
|
||||
|
||||
---
|
||||
|
||||
📚 [Documentation](https://fu-jie.github.io/openwebui-extensions/)
|
||||
📚 [Documentation Portal](https://fu-jie.github.io/openwebui-extensions/)
|
||||
🐛 [Report Issues](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
EOF
|
||||
|
||||
|
||||
echo "=== Final Release Notes ==="
|
||||
cat release_notes.md
|
||||
|
||||
echo "=== Release Notes ==="
|
||||
cat release_notes.md
|
||||
|
||||
- name: Create Git Tag
|
||||
if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
|
||||
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
|
||||
run: |
|
||||
VERSION="${{ steps.version.outputs.version }}"
|
||||
|
||||
|
||||
75
CHANGELOG.md
75
CHANGELOG.md
@@ -1,75 +0,0 @@
|
||||
# Changelog / 更新日志
|
||||
|
||||
All notable changes to this project will be documented in this file.
|
||||
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
|
||||
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
|
||||
本项目的所有重要更改都将记录在此文件中。
|
||||
格式基于 [Keep a Changelog](https://keepachangelog.com/zh-CN/1.1.0/)，
|
||||
本项目遵循 [语义化版本](https://semver.org/lang/zh-CN/)。
|
||||
|
||||
---
|
||||
|
||||
## [Unreleased] / 未发布
|
||||
|
||||
### Added / 新增
|
||||
- 插件发布工作流 (Plugin release workflow)
|
||||
|
||||
### Changed / 变更
|
||||
|
||||
### Fixed / 修复
|
||||
|
||||
### Removed / 移除
|
||||
|
||||
---
|
||||
|
||||
## Plugin Versions / 插件版本
|
||||
|
||||
### Actions
|
||||
|
||||
| Plugin / 插件 | Version / 版本 |
|
||||
|---------------|----------------|
|
||||
| Smart Mind Map / 思维导图 | 0.8.0 |
|
||||
| Flash Card / 闪记卡 | 0.2.1 |
|
||||
| Export to Word / 导出为 Word | 0.1.0 |
|
||||
| Export to Excel / 导出为 Excel | 0.3.3 |
|
||||
| Deep Reading & Summary / 精读 | 0.1.0 / 2.0.0 |
|
||||
| Smart Infographic / 智能信息图 | 1.3.0 |
|
||||
|
||||
### Filters
|
||||
|
||||
| Plugin / 插件 | Version / 版本 |
|
||||
|---------------|----------------|
|
||||
| Async Context Compression / 异步上下文压缩 | 1.1.0 |
|
||||
| Context & Model Enhancement Filter | 0.2 |
|
||||
| Gemini Manifold Companion | 1.7.0 |
|
||||
| Gemini 多模态过滤器 | 0.3.2 |
|
||||
|
||||
### Pipes
|
||||
|
||||
| Plugin / 插件 | Version / 版本 |
|
||||
|---------------|----------------|
|
||||
| Gemini Manifold google_genai | 1.26.0 |
|
||||
|
||||
---
|
||||
|
||||
<!--
|
||||
Release Template / 发布模板:
|
||||
|
||||
## [x.x.x] - YYYY-MM-DD
|
||||
|
||||
### Added / 新增
|
||||
- New feature description
|
||||
|
||||
### Changed / 变更
|
||||
- Change description
|
||||
|
||||
### Fixed / 修复
|
||||
- Bug fix description
|
||||
|
||||
### Plugin Updates / 插件更新
|
||||
- `plugin_name`: v0.x.0 -> v0.y.0
|
||||
- Feature 1
|
||||
- Feature 2
|
||||
-->
|
||||
26
README.md
26
README.md
@@ -9,6 +9,7 @@ A collection of enhancements, plugins, and prompts for [open-webui](https://gith
|
||||
|
||||
<!-- STATS_START -->
|
||||
## 📊 Community Stats
|
||||
>
|
||||
> 
|
||||
|
||||
| 👤 Author | 👥 Followers | ⭐ Points | 🏆 Contributions |
|
||||
@@ -19,18 +20,19 @@ A collection of enhancements, plugins, and prompts for [open-webui](https://gith
|
||||
| :---: | :---: | :---: | :---: | :---: |
|
||||
|  |  |  |  |  |
|
||||
|
||||
|
||||
### 🔥 Top 6 Popular Plugins
|
||||
|
||||
| Rank | Plugin | Version | Downloads | Views | 📅 Updated |
|
||||
| :---: | :--- | :---: | :---: | :---: | :---: |
|
||||
| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) |  |  |  |  |
|
||||
| 🥈 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) |  |  |  |  |
|
||||
| 🥉 | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) |  |  |  |  |
|
||||
| 4️⃣ | [Export to Word Enhanced](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) |  |  |  |  |
|
||||
| 5️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) |  |  |  |  |
|
||||
| 5️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) |  |  |  |  |
|
||||
| 6️⃣ | [AI Task Instruction Generator](https://openwebui.com/posts/ai_task_instruction_generator_9bab8b37) |  |  |  |  |
|
||||
|
||||
### 📈 Total Downloads Trend
|
||||
|
||||
|
||||
|
||||
*See full stats and charts in [Community Stats Report](./docs/community-stats.md)*
|
||||
@@ -163,13 +165,6 @@ For code examples, please check the `docs/examples/` directory.
|
||||
|
||||
This project is a collection of resources and does not require a Python environment. Simply download the files you need and import them into your OpenWebUI instance.
|
||||
|
||||
### Using Prompts
|
||||
|
||||
1. Browse the `/prompts` directory and select a prompt file (`.md`).
|
||||
2. Copy the file content.
|
||||
3. In the OpenWebUI chat interface, click the "Prompt" button above the input box.
|
||||
4. Paste the content and save.
|
||||
|
||||
### Using Plugins
|
||||
|
||||
1. **Install from OpenWebUI Community (Recommended)**:
|
||||
@@ -177,11 +172,14 @@ This project is a collection of resources and does not require a Python environm
|
||||
- Browse the plugins and select the one you like.
|
||||
- Click "Get" to import it directly into your OpenWebUI instance.
|
||||
|
||||
2. **Manual Installation**:
|
||||
- Browse the `/plugins` directory and download the plugin file (`.py`) you need.
|
||||
- Go to OpenWebUI **Admin Panel** -> **Settings** -> **Plugins**.
|
||||
- Click the upload button and select the `.py` file you just downloaded.
|
||||
- Once uploaded, refresh the page to enable the plugin in your chat settings or toolbar.
|
||||
2. **Quick Install All Plugins**: To install all plugins to your local OpenWebUI instance at once, clone this repo and run `python scripts/install_all_plugins.py` after configuring your API key in `.env` — see [Deployment Guide](./scripts/DEPLOYMENT_GUIDE.md) for details.
|
||||
|
||||
### Using Prompts
|
||||
|
||||
1. Browse the `/prompts` directory and select a prompt file (`.md`).
|
||||
2. Copy the file content.
|
||||
3. In the OpenWebUI chat interface, click the "Prompt" button above the input box.
|
||||
4. Paste the content and save.
|
||||
|
||||
### Contributing
|
||||
|
||||
|
||||
22
README_CN.md
22
README_CN.md
@@ -6,6 +6,7 @@ OpenWebUI 增强功能集合。包含个人开发与收集的插件、提示词
|
||||
|
||||
<!-- STATS_START -->
|
||||
## 📊 社区统计
|
||||
>
|
||||
> 
|
||||
|
||||
| 👤 作者 | 👥 粉丝 | ⭐ 积分 | 🏆 贡献 |
|
||||
@@ -16,18 +17,19 @@ OpenWebUI 增强功能集合。包含个人开发与收集的插件、提示词
|
||||
| :---: | :---: | :---: | :---: | :---: |
|
||||
|  |  |  |  |  |
|
||||
|
||||
|
||||
### 🔥 热门插件 Top 6
|
||||
|
||||
| 排名 | 插件 | 版本 | 下载 | 浏览 | 📅 更新 |
|
||||
| :---: | :--- | :---: | :---: | :---: | :---: |
|
||||
| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) |  |  |  |  |
|
||||
| 🥈 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) |  |  |  |  |
|
||||
| 🥉 | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) |  |  |  |  |
|
||||
| 4️⃣ | [Export to Word Enhanced](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) |  |  |  |  |
|
||||
| 5️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) |  |  |  |  |
|
||||
| 5️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) |  |  |  |  |
|
||||
| 6️⃣ | [AI Task Instruction Generator](https://openwebui.com/posts/ai_task_instruction_generator_9bab8b37) |  |  |  |  |
|
||||
|
||||
### 📈 总下载量累计趋势
|
||||
|
||||
|
||||
|
||||
*完整统计与趋势图请查看 [社区统计报告](./docs/community-stats.zh.md)*
|
||||
@@ -166,4 +168,20 @@ Open WebUI 的前端增强扩展：
|
||||
|
||||
本项目是一个资源集合，无需安装 Python 环境。你只需要下载对应的文件并导入到你的 OpenWebUI 实例中即可。
|
||||
|
||||
### 使用插件
|
||||
|
||||
1. **从官方社区安装（推荐）**：
|
||||
- 访问我的主页：[Fu-Jie 的个人页面](https://openwebui.com/u/Fu-Jie)
|
||||
- 浏览插件并选择你喜欢的
|
||||
- 点击"Get"按钮直接导入到你的 OpenWebUI 实例
|
||||
|
||||
2. **快速安装所有插件**：如果想一次性安装此项目中的所有插件到本地 OpenWebUI 实例，克隆此仓库后运行 `python scripts/install_all_plugins.py`，并在 `.env` 中配置好 API 密钥，详见 [部署指南](./scripts/DEPLOYMENT_GUIDE.md)。
|
||||
|
||||
### 使用提示词
|
||||
|
||||
1. 浏览 `/prompts` 目录并选择一个提示词文件（`.md`）。
|
||||
2. 复制文件内容。
|
||||
3. 在 OpenWebUI 聊天界面中，点击输入框上方的"提示词"按钮。
|
||||
4. 粘贴内容并保存。
|
||||
|
||||
[贡献指南](./CONTRIBUTING_CN.md) | [更新日志](./CHANGELOG.md)
|
||||
|
||||
124
docs/development/fix-role-tool-error.md
Normal file
124
docs/development/fix-role-tool-error.md
Normal file
@@ -0,0 +1,124 @@
|
||||
# Fix: OpenAI API Error "messages with role 'tool' must be a response to a preceding message with 'tool_calls'"
|
||||
|
||||
## Problem Description
|
||||
In the `async-context-compression` filter, chat history can be trimmed or summarized when the conversation grows. If the retained tail starts in the middle of a native tool-calling sequence, the next request may begin with a `tool` message whose triggering `assistant` message is no longer present.
|
||||
|
||||
That produces the OpenAI API error:
|
||||
`"messages with role 'tool' must be a response to a preceding message with 'tool_calls'"`
|
||||
|
||||
## Root Cause
|
||||
History compression boundaries were not fully aware of atomic tool-call chains. A valid chain may include:
|
||||
|
||||
1. An `assistant` message with `tool_calls`
|
||||
2. One or more `tool` messages
|
||||
3. An optional assistant follow-up that consumes the tool results
|
||||
|
||||
If truncation happens inside that chain, the request sent to the model becomes invalid.
|
||||
|
||||
## Solution: Atomic Boundary Alignment
|
||||
The fix groups tool-call sequences into atomic units and aligns trim boundaries to those groups.
|
||||
|
||||
### 1. `_get_atomic_groups()`
|
||||
This helper groups message indices into units that must be kept or dropped together. It explicitly recognizes native tool-calling patterns such as:
|
||||
|
||||
- `assistant(tool_calls)`
|
||||
- `tool`
|
||||
- assistant follow-up response
|
||||
|
||||
Conceptually, it treats the whole sequence as one atomic block instead of independent messages.
|
||||
|
||||
```python
|
||||
def _get_atomic_groups(self, messages: List[Dict]) -> List[List[int]]:
|
||||
groups = []
|
||||
current_group = []
|
||||
|
||||
for i, msg in enumerate(messages):
|
||||
role = msg.get("role")
|
||||
has_tool_calls = bool(msg.get("tool_calls"))
|
||||
|
||||
if role == "assistant" and has_tool_calls:
|
||||
if current_group:
|
||||
groups.append(current_group)
|
||||
current_group = [i]
|
||||
elif role == "tool":
|
||||
if not current_group:
|
||||
groups.append([i])
|
||||
else:
|
||||
current_group.append(i)
|
||||
elif (
|
||||
role == "assistant"
|
||||
and current_group
|
||||
and messages[current_group[-1]].get("role") == "tool"
|
||||
):
|
||||
current_group.append(i)
|
||||
groups.append(current_group)
|
||||
current_group = []
|
||||
else:
|
||||
if current_group:
|
||||
groups.append(current_group)
|
||||
current_group = []
|
||||
groups.append([i])
|
||||
|
||||
if current_group:
|
||||
groups.append(current_group)
|
||||
|
||||
return groups
|
||||
```
|
||||
|
||||
### 2. `_align_tail_start_to_atomic_boundary()`
|
||||
This helper checks whether a proposed trim point falls inside one of those atomic groups. If it does, the start index is moved backward to the beginning of that group.
|
||||
|
||||
```python
|
||||
def _align_tail_start_to_atomic_boundary(
|
||||
self, messages: List[Dict], raw_start_index: int, protected_prefix: int
|
||||
) -> int:
|
||||
aligned_start = max(raw_start_index, protected_prefix)
|
||||
|
||||
if aligned_start <= protected_prefix or aligned_start >= len(messages):
|
||||
return aligned_start
|
||||
|
||||
trimmable = messages[protected_prefix:]
|
||||
local_start = aligned_start - protected_prefix
|
||||
|
||||
for group in self._get_atomic_groups(trimmable):
|
||||
group_start = group[0]
|
||||
group_end = group[-1] + 1
|
||||
|
||||
if local_start == group_start:
|
||||
return aligned_start
|
||||
|
||||
if group_start < local_start < group_end:
|
||||
return protected_prefix + group_start
|
||||
|
||||
return aligned_start
|
||||
```
|
||||
|
||||
### 3. Applied to Tail Retention and Summary Progress
|
||||
The aligned boundary is now used when rebuilding the retained tail and when calculating how much history can be summarized safely.
|
||||
|
||||
Example from the current implementation:
|
||||
|
||||
```python
|
||||
raw_start_index = max(compressed_count, effective_keep_first)
|
||||
start_index = self._align_tail_start_to_atomic_boundary(
|
||||
messages, raw_start_index, effective_keep_first
|
||||
)
|
||||
tail_messages = messages[start_index:]
|
||||
```
|
||||
|
||||
And during summary progress calculation:
|
||||
|
||||
```python
|
||||
raw_target_compressed_count = max(0, len(messages) - self.valves.keep_last)
|
||||
target_compressed_count = self._align_tail_start_to_atomic_boundary(
|
||||
messages, raw_target_compressed_count, effective_keep_first
|
||||
)
|
||||
```
|
||||
|
||||
## Verification Results
|
||||
- **First compression boundary**: When history first crosses the compression threshold, the retained tail no longer starts inside a tool-call block.
|
||||
- **Complex sessions**: Real-world testing with 30+ messages, multiple tool calls, and failed calls remained stable during background summarization.
|
||||
- **Regression behavior**: The filter now prefers a valid boundary even if that means retaining slightly more context than a naive raw slice would allow.
|
||||
|
||||
## Conclusion
|
||||
The fix prevents orphaned `tool` messages by making history trimming and summary progress aware of atomic tool-call groups. This eliminates the 400 error during long conversations and background compression.
|
||||
126
docs/development/fix-role-tool-error.zh.md
Normal file
126
docs/development/fix-role-tool-error.zh.md
Normal file
@@ -0,0 +1,126 @@
|
||||
# 修复：OpenAI API 错误 "messages with role 'tool' must be a response to a preceding message with 'tool_calls'"
|
||||
|
||||
## 问题描述
|
||||
在 `async-context-compression` 过滤器中，当对话历史变长时，系统会对消息进行裁剪或摘要。如果保留下来的尾部历史恰好从一个原生工具调用序列的中间开始，那么下一次请求就可能以一条 `tool` 消息开头，而触发它的 `assistant` 消息已经被裁掉。
|
||||
|
||||
这就会触发 OpenAI API 的错误：
|
||||
`"messages with role 'tool' must be a response to a preceding message with 'tool_calls'"`
|
||||
|
||||
## 根本原因
|
||||
|
||||
真正的缺陷在于历史压缩边界没有完整识别工具调用链的“原子性”。一个合法的工具调用链通常包括：
|
||||
|
||||
1. 一条带有 `tool_calls` 的 `assistant` 消息
|
||||
2. 一条或多条 `tool` 消息
|
||||
3. 一条可选的 assistant 跟进回复，用于消费工具结果
|
||||
|
||||
如果裁剪点落在这段链条内部，发给模型的消息序列就会变成非法格式。
|
||||
|
||||
## 解决方案：对齐原子边界
|
||||
修复通过把工具调用序列分组为原子单元，并使裁剪边界对齐到这些单元。
|
||||
|
||||
### 1. `_get_atomic_groups()`
|
||||
这个辅助函数会把消息索引分组为“必须一起保留或一起丢弃”的原子单元。它显式识别以下原生工具调用模式：
|
||||
|
||||
- `assistant(tool_calls)`
|
||||
- `tool`
|
||||
- assistant 跟进回复
|
||||
|
||||
也就是说，它不再把这些消息看成彼此独立的单条消息，而是把整段序列视为一个原子块。
|
||||
|
||||
```python
|
||||
def _get_atomic_groups(self, messages: List[Dict]) -> List[List[int]]:
|
||||
groups = []
|
||||
current_group = []
|
||||
|
||||
for i, msg in enumerate(messages):
|
||||
role = msg.get("role")
|
||||
has_tool_calls = bool(msg.get("tool_calls"))
|
||||
|
||||
if role == "assistant" and has_tool_calls:
|
||||
if current_group:
|
||||
groups.append(current_group)
|
||||
current_group = [i]
|
||||
elif role == "tool":
|
||||
if not current_group:
|
||||
groups.append([i])
|
||||
else:
|
||||
current_group.append(i)
|
||||
elif (
|
||||
role == "assistant"
|
||||
and current_group
|
||||
and messages[current_group[-1]].get("role") == "tool"
|
||||
):
|
||||
current_group.append(i)
|
||||
groups.append(current_group)
|
||||
current_group = []
|
||||
else:
|
||||
if current_group:
|
||||
groups.append(current_group)
|
||||
current_group = []
|
||||
groups.append([i])
|
||||
|
||||
if current_group:
|
||||
groups.append(current_group)
|
||||
|
||||
return groups
|
||||
```
|
||||
|
||||
### 2. `_align_tail_start_to_atomic_boundary()`
|
||||
这个辅助函数会检查一个拟定的裁剪起点是否落在某个原子块内部。如果是，它会把起点向前回退到该原子块的开头位置。
|
||||
|
||||
```python
|
||||
def _align_tail_start_to_atomic_boundary(
|
||||
self, messages: List[Dict], raw_start_index: int, protected_prefix: int
|
||||
) -> int:
|
||||
aligned_start = max(raw_start_index, protected_prefix)
|
||||
|
||||
if aligned_start <= protected_prefix or aligned_start >= len(messages):
|
||||
return aligned_start
|
||||
|
||||
trimmable = messages[protected_prefix:]
|
||||
local_start = aligned_start - protected_prefix
|
||||
|
||||
for group in self._get_atomic_groups(trimmable):
|
||||
group_start = group[0]
|
||||
group_end = group[-1] + 1
|
||||
|
||||
if local_start == group_start:
|
||||
return aligned_start
|
||||
|
||||
if group_start < local_start < group_end:
|
||||
return protected_prefix + group_start
|
||||
|
||||
return aligned_start
|
||||
```
|
||||
|
||||
### 3. 应用于尾部保留和摘要进度计算
|
||||
这个对齐后的边界现在被用于重建保留尾部消息，以及计算可以安全摘要的历史范围。
|
||||
|
||||
当前实现中的示例：
|
||||
|
||||
```python
|
||||
raw_start_index = max(compressed_count, effective_keep_first)
|
||||
start_index = self._align_tail_start_to_atomic_boundary(
|
||||
messages, raw_start_index, effective_keep_first
|
||||
)
|
||||
tail_messages = messages[start_index:]
|
||||
```
|
||||
|
||||
在摘要进度计算中同样如此：
|
||||
|
||||
```python
|
||||
raw_target_compressed_count = max(0, len(messages) - self.valves.keep_last)
|
||||
target_compressed_count = self._align_tail_start_to_atomic_boundary(
|
||||
messages, raw_target_compressed_count, effective_keep_first
|
||||
)
|
||||
```
|
||||
|
||||
## 验证结果
|
||||
|
||||
- **首次压缩边界**：当历史第一次越过压缩阈值时，保留尾部不再从工具调用块中间开始。
|
||||
- **复杂会话验证**：在 30+ 条消息、多个工具调用和失败调用的真实场景下，后台摘要过程保持稳定。
|
||||
- **回归行为更安全**：过滤器现在会优先选择合法边界，即使这意味着比原始的朴素切片稍微多保留一点上下文。
|
||||
|
||||
## 结论
|
||||
通过让历史裁剪与摘要进度计算具备"工具调用原子块感知"能力，避免孤立的 `tool` 消息出现，消除长对话与后台压缩期间的 400 错误。
|
||||
@@ -103,13 +103,6 @@ hide:
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Using Prompts
|
||||
|
||||
1. Browse the [Prompt Library](prompts/library.md) and select a prompt
|
||||
2. Click the **Copy** button to copy the prompt to your clipboard
|
||||
3. In OpenWebUI, click the "Prompt" button above the input box
|
||||
4. Paste the content and save
|
||||
|
||||
### Using Plugins
|
||||
|
||||
1. **Install from OpenWebUI Community (Recommended)**:
|
||||
@@ -117,11 +110,14 @@ hide:
|
||||
- Browse the plugins and select the one you like.
|
||||
- Click "Get" to import it directly into your OpenWebUI instance.
|
||||
|
||||
2. **Manual Installation**:
|
||||
- Browse the [Plugin Center](plugins/index.md) and download the plugin file (`.py`)
|
||||
- Open OpenWebUI **Admin Panel** → **Settings** → **Plugins**
|
||||
- Click the upload button and select the `.py` file
|
||||
- Refresh the page and enable the plugin in your chat settings
|
||||
2. **Quick Install All Plugins**: To install all plugins to your local OpenWebUI instance at once, clone this repo and run `python scripts/install_all_plugins.py` after configuring your API key in `.env` — see [Deployment Guide](https://github.com/Fu-Jie/openwebui-extensions/blob/main/scripts/DEPLOYMENT_GUIDE.md) for details.
|
||||
|
||||
### Using Prompts
|
||||
|
||||
1. Browse the [Prompt Library](prompts/library.md) and select a prompt
|
||||
2. Click the **Copy** button to copy the prompt to your clipboard
|
||||
3. In OpenWebUI, click the "Prompt" button above the input box
|
||||
4. Paste the content and save
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -103,13 +103,6 @@ hide:
|
||||
|
||||
## 快速入门
|
||||
|
||||
### 使用提示词
|
||||
|
||||
1. 浏览[提示词库](prompts/library.md)并选择一个提示词
|
||||
2. 点击**复制**按钮将提示词复制到剪贴板
|
||||
3. 在 OpenWebUI 中，点击输入框上方的"提示词"按钮
|
||||
4. 粘贴内容并保存
|
||||
|
||||
### 使用插件
|
||||
|
||||
1. **从 OpenWebUI 社区安装 (推荐)**:
|
||||
@@ -117,11 +110,14 @@ hide:
|
||||
- 浏览插件列表，选择你喜欢的插件。
|
||||
- 点击 "Get" 按钮，将其直接导入到你的 OpenWebUI 实例中。
|
||||
|
||||
2. **手动安装**:
|
||||
- 浏览[插件中心](plugins/index.md)并下载插件文件（`.py`）
|
||||
- 打开 OpenWebUI **管理面板** → **设置** → **插件**
|
||||
- 点击上传按钮并选择 `.py` 文件
|
||||
- 刷新页面并在聊天设置中启用插件
|
||||
2. **快速安装全部插件**：想要一次性安装此项目中的所有插件到本地 OpenWebUI 实例，克隆此仓库后运行 `python scripts/install_all_plugins.py`，并在 `.env` 中配置好 API 密钥，详见[部署指南](https://github.com/Fu-Jie/openwebui-extensions/blob/main/scripts/DEPLOYMENT_GUIDE.md)。
|
||||
|
||||
### 使用提示词
|
||||
|
||||
1. 浏览[提示词库](prompts/library.md)并选择一个提示词
|
||||
2. 点击**复制**按钮将提示词复制到剪贴板
|
||||
3. 在 OpenWebUI 中，点击输入框上方的"提示词"按钮
|
||||
4. 粘贴内容并保存
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,16 +1,13 @@
|
||||
# Async Context Compression Filter
|
||||
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.3.0 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.4.1 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
|
||||
This filter reduces token consumption in long conversations through intelligent summarization and message compression while keeping conversations coherent.
|
||||
|
||||
## What's new in 1.3.0
|
||||
## What's new in 1.4.1
|
||||
|
||||
- **Internationalization (i18n)**: Complete localization of user-facing messages across 9 languages (English, Chinese, Japanese, Korean, French, German, Spanish, Italian).
|
||||
- **Smart Status Display**: Added `token_usage_status_threshold` valve (default 80%) to intelligently control when token usage status is shown.
|
||||
- **Improved Performance**: Frontend language detection and logging are optimized to be completely non-blocking, maintaining lightning-fast TTFB.
|
||||
- **Copilot SDK Integration**: Automatically detects and skips compression for copilot_sdk based models to prevent conflicts.
|
||||
- **Configuration**: `debug_mode` is now set to `false` by default for a quieter production experience.
|
||||
- **Reverse-Unfolding Mechanism**: Accurately reconstructs the expanded native tool-calling sequence during the outlet phase to permanently fix coordinate drift and missing summaries for long tool-based conversations.
|
||||
- **Safer Tool Trimming**: Refactored `enable_tool_output_trimming` to strictly use atomic block groups for safe trimming, completely preventing JSON payload corruption.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,18 +1,15 @@
|
||||
# 异步上下文压缩过滤器
|
||||
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 1.3.0 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 1.4.1 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
|
||||
> **重要提示**：为了确保所有过滤器的可维护性和易用性，每个过滤器都应附带清晰、完整的文档，以确保其功能、配置和使用方法得到充分说明。
|
||||
|
||||
本过滤器通过智能摘要和消息压缩技术，在保持对话连贯性的同时，显著降低长对话的 Token 消耗。
|
||||
|
||||
## 1.3.0 版本更新
|
||||
## 1.4.1 版本更新
|
||||
|
||||
- **国际化 (i18n) 支持**: 完成了所有用户可见消息的本地化，现已原生支持 9 种语言（含中、英、日、韩及欧洲主要语言）。
|
||||
- **智能状态显示**: 新增 `token_usage_status_threshold` 阀门（默认 80%），可以智能控制何时显示 Token 用量状态，减少不必要的打扰。
|
||||
- **性能大幅优化**: 对前端语言检测和日志处理流程进行了非阻塞重构，完全不影响首字节响应时间（TTFB），保持毫秒级极速推流。
|
||||
- **Copilot SDK 兼容**: 自动检测并跳过基于 `copilot_sdk` 模型的上下文压缩，避免冲突。
|
||||
- **配置项调整**: 为了提供更安静的生产环境体验，`debug_mode` 现已默认设置为 `false`。
|
||||
- **逆向展开机制**: 引入 `_unfold_messages` 机制以在 `outlet` 阶段精确对齐坐标系，彻底解决了由于前端视图折叠导致长轮次工具调用对话出现进度漂移或跳过生成摘要的问题。
|
||||
- **更安全的工具内容裁剪**: 重构了 `enable_tool_output_trimming`，现在严格使用原子级分组进行安全的原生工具内容裁剪，替代了激进的正则表达式匹配，防止 JSON 载荷损坏。
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ Filters act as middleware in the message pipeline:
|
||||
|
||||
Reduces token consumption in long conversations through intelligent summarization while maintaining coherence.
|
||||
|
||||
**Version:** 1.3.0
|
||||
**Version:** 1.4.1
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](async-context-compression.md)
|
||||
|
||||
@@ -52,7 +52,7 @@ Filters act as middleware in the message pipeline:
|
||||
|
||||
Fixes common Markdown formatting issues in LLM outputs, including Mermaid syntax, code blocks, and LaTeX formulas.
|
||||
|
||||
**Version:** 1.2.7
|
||||
**Version:** 1.2.8
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](markdown_normalizer.md)
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ Filter 充当消息管线中的中间件：
|
||||
|
||||
通过智能总结减少长对话的 token 消耗，同时保持连贯性。
|
||||
|
||||
**版本：** 1.3.0
|
||||
**版本：** 1.4.1
|
||||
|
||||
[:octicons-arrow-right-24: 查看文档](async-context-compression.md)
|
||||
|
||||
@@ -52,7 +52,7 @@ Filter 充当消息管线中的中间件：
|
||||
|
||||
修复 LLM 输出中常见的 Markdown 格式问题，包括 Mermaid 语法、代码块和 LaTeX 公式。
|
||||
|
||||
**版本：** 1.2.7
|
||||
**版本：** 1.2.8
|
||||
|
||||
[:octicons-arrow-right-24: 查看文档](markdown_normalizer.zh.md)
|
||||
|
||||
|
||||
@@ -1,81 +1,90 @@
|
||||
# Markdown Normalizer Filter
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.2.8 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.2.7 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
A powerful, context-aware content normalizer filter for Open WebUI designed to fix common Markdown formatting issues in LLM outputs. It ensures that code blocks, LaTeX formulas, Mermaid diagrams, and other structural Markdown elements are rendered flawlessly, without destroying valid technical content.
|
||||
|
||||
A content normalizer filter for Open WebUI that fixes common Markdown formatting issues in LLM outputs. It ensures that code blocks, LaTeX formulas, Mermaid diagrams, and other Markdown elements are rendered correctly.
|
||||
> 🏆 **Featured by OpenWebUI Official** — This plugin was recommended in the official OpenWebUI Community Newsletter: [January 28, 2026](https://openwebui.com/blog/newsletter-january-28-2026)
|
||||
|
||||
> 🏆 **Featured by OpenWebUI Official** — Recommended in the official OpenWebUI Community Newsletter: [January 28, 2026](https://openwebui.com/blog/newsletter-january-28-2026)
|
||||
[English](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README.md) | [简体中文](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README_CN.md)
|
||||
|
||||
## 🔥 What's New in v1.2.7
|
||||
---
|
||||
|
||||
* **LaTeX Formula Protection**: Enhanced escape character cleaning to protect LaTeX commands like `\times`, `\nu`, and `\theta` from being corrupted.
|
||||
* **Expanded i18n Support**: Now supports 12 languages with automatic detection and fallback.
|
||||
* **Valves Optimization**: Optimized configuration descriptions to be English-only for better consistency.
|
||||
* **Bug Fixes**:
|
||||
* Resolved [Issue #49](https://github.com/Fu-Jie/openwebui-extensions/issues/49): Fixed a bug where consecutive bold parts on the same line caused spaces between them to be removed.
|
||||
* Fixed a `NameError` in the plugin code that caused test collection failures.
|
||||
## 🔥 What's New in v1.2.8
|
||||
* **Safe-by-Default Strategy**: The `enable_escape_fix` feature is now **disabled by default**. This prevents unwanted modifications to valid technical text like Windows file paths (`C:\new\test`) or complex LaTeX formulas.
|
||||
* **LaTeX Parsing Fix**: Improved the logic for identifying display math (`$$ ... $$`). Fixed a bug where LaTeX commands starting with `\n` (like `\nabla`) were incorrectly treated as newlines.
|
||||
* **Reliability Enhancement**: Complete error fallback mechanism. Guarantees 0% data loss during processing.
|
||||
* **Inline Code Protection**: Upgraded escaping logic to protect inline code blocks (`` `...` ``).
|
||||
* **Code Block Escaping Control**: The `enable_escape_fix_in_code_blocks` Valve now correctly targets broken newlines inside code blocks (perfect for fixing flat SQL queries) when enabled.
|
||||
* **Privacy Optimization**: `show_debug_log` now defaults to `False` to prevent console noise.
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Why do you need this plugin? (What does it do?)
|
||||
|
||||
Language Models (LLMs) often generate malformed Markdown due to tokenization artifacts, aggressive escaping, or hallucinated formatting. If you've ever seen:
|
||||
- A `mermaid` diagram fail to render because of missing quotes around labels.
|
||||
- A SQL block stuck on a single line because `\n` was output literally instead of a real newline.
|
||||
- A `<details>` block break the entire chat rendering because of missing newlines.
|
||||
- A LaTeX formula fail because the LLM used `\[` instead of `$$`.
|
||||
|
||||
**This plugin automatically intercepts the LLM's raw output, analyzes its structure, and surgically repairs these formatting errors in real-time before they reach your browser.**
|
||||
|
||||
## ✨ Comprehensive Feature List
|
||||
|
||||
### 1. Advanced Structural Protections (Context-Aware)
|
||||
Before making any changes, the plugin builds a semantic map of the text to protect your technical content:
|
||||
- **Code Block Protection**: Skips formatting inside ` ``` ` code blocks by default to protect code logic.
|
||||
- **Inline Code Protection**: Recognizes `` `code` `` snippets and protects regular expressions and file paths (e.g., `C:\Windows`) from being incorrectly unescaped.
|
||||
- **LaTeX Protection**: Identifies inline (`$`) and block (`$$`) formulas to prevent modifying critical math commands like `\times`, `\theta`, or `\nu`.
|
||||
|
||||
### 2. Auto-Healing Transformations
|
||||
- **Details Tag Normalization**: `<details>` blocks (often used for Chain of Thought) require strict spacing to render correctly. The plugin automatically injects blank lines after `</details>` and self-closing `<details />` tags.
|
||||
- **Mermaid Syntax Fixer**: One of the most common LLM errors is omitting quotes in Mermaid diagrams (e.g., `A --> B(Some text)`). This plugin parses the Mermaid syntax and auto-quotes labels and citations to guarantee the graph renders.
|
||||
- **Emphasis Spacing Fix**: Fixes formatting-breaking extra spaces inside bold/italic markers (e.g., `** text **` becomes `**text**`) while cleverly ignoring math expressions like `2 * 3 * 4`.
|
||||
- **Intelligent Escape Character Cleanup**: Removes excessive literal `\n` and `\t` generated by some models and converts them to actual structural newlines (only in safe text areas).
|
||||
- **LaTeX Standardization**: Automatically upgrades old-school LaTeX delimiters (`\[...\]` and `\(...\)`) to modern Markdown standards (`$$...$$` and `$ ... $`).
|
||||
- **Thought Tag Unification**: Standardizes various model thought outputs (`<think>`, `<thinking>`) into a unified `<thought>` tag.
|
||||
- **Broken Code Block Repair**: Fixes indentation issues, repairs mangled language prefixes (e.g., ` ```python`), and automatically closes unclosed code blocks if a generation was cut off.
|
||||
- **List & Table Formatting**: Injects missing newlines to repair broken numbered lists and adds missing closing pipes (`|`) to tables.
|
||||
- **XML Artifact Cleanup**: Silently removes leftover `<antArtifact>` or `<antThinking>` tags often leaked by Claude models.
|
||||
|
||||
### 3. Reliability & Safety
|
||||
- **100% Rollback Guarantee**: If any normalization logic fails or crashes, the plugin catches the error and silently returns the exact original text, ensuring your chat never breaks.
|
||||
|
||||
## 🌐 Multilingual Support
|
||||
|
||||
Supports automatic interface and status switching for the following languages:
|
||||
The plugin UI and status notifications automatically switch based on your language:
|
||||
`English`, `简体中文`, `繁體中文 (香港)`, `繁體中文 (台灣)`, `한국어`, `日本語`, `Français`, `Deutsch`, `Español`, `Italiano`, `Tiếng Việt`, `Bahasa Indonesia`.
|
||||
|
||||
## ✨ Core Features
|
||||
|
||||
* **Details Tag Normalization**: Ensures proper spacing for `<details>` tags (used for thought chains). Adds a blank line after `</details>` and ensures a newline after self-closing `<details />` tags to prevent rendering issues.
|
||||
* **Emphasis Spacing Fix**: Fixes extra spaces inside emphasis markers (e.g., `** text **` -> `**text**`) which can cause rendering failures. Includes safeguards to protect math expressions (e.g., `2 * 3 * 4`) and list variables.
|
||||
* **Mermaid Syntax Fix**: Automatically fixes common Mermaid syntax errors, such as unquoted node labels (including multi-line labels and citations) and unclosed subgraphs. **New in v1.1.2**: Comprehensive protection for edge labels (text on connecting lines) across all link types (solid, dotted, thick).
|
||||
* **Frontend Console Debugging**: Supports printing structured debug logs directly to the browser console (F12) for easier troubleshooting.
|
||||
* **Code Block Formatting**: Fixes broken code block prefixes, suffixes, and indentation.
|
||||
* **LaTeX Normalization**: Standardizes LaTeX formula delimiters (`\[` -> `$$`, `\(` -> `$`).
|
||||
* **Thought Tag Normalization**: Unifies thought tags (`<think>`, `<thinking>` -> `<thought>`).
|
||||
* **Escape Character Fix**: Cleans up excessive escape characters (`\\n`, `\\t`).
|
||||
* **List Formatting**: Ensures proper newlines in list items.
|
||||
* **Heading Fix**: Adds missing spaces in headings (`#Heading` -> `# Heading`).
|
||||
* **Table Fix**: Adds missing closing pipes in tables.
|
||||
* **XML Cleanup**: Removes leftover XML artifacts.
|
||||
|
||||
## How to Use 🛠️
|
||||
|
||||
1. Install the plugin in Open WebUI.
|
||||
2. Enable the filter globally or for specific models.
|
||||
3. Configure the enabled fixes in the **Valves** settings.
|
||||
4. (Optional) **Show Debug Log** is enabled by default in Valves. This prints structured logs to the browser console (F12).
|
||||
> [!WARNING]
|
||||
> As this is an initial version, some "negative fixes" might occur (e.g., breaking valid Markdown). If you encounter issues, please check the console logs, copy the "Original" vs "Normalized" content, and submit an issue.
|
||||
2. Enable the filter globally or assign it to specific models (highly recommended for models with poor formatting).
|
||||
3. Tune the specific fixes you want via the **Valves** settings.
|
||||
|
||||
## Configuration (Valves) ⚙️
|
||||
|
||||
| Parameter | Default | Description |
|
||||
| :--- | :--- | :--- |
|
||||
| `priority` | `50` | Filter priority. Higher runs later (recommended after other filters). |
|
||||
| `enable_escape_fix` | `True` | Fix excessive escape characters (`\n`, `\t`, etc.). |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | Apply escape fix inside code blocks (may affect valid code). |
|
||||
| `enable_thought_tag_fix` | `True` | Normalize thought tags (`</thought>`). |
|
||||
| `enable_details_tag_fix` | `True` | Normalize `<details>` tags and add safe spacing. |
|
||||
| `enable_code_block_fix` | `True` | Fix code block formatting (indentation/newlines). |
|
||||
| `enable_latex_fix` | `True` | Normalize LaTeX delimiters (`\[` -> `$$`, `\(` -> `$`). |
|
||||
| `priority` | `50` | Filter priority. Higher runs later (recommended to run this after all other content filters). |
|
||||
| `enable_escape_fix` | `False` | Convert excessive literal escape characters (`\n`, `\t`) to real spacing. (Default: False for safety). |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | **Pro-tip**: Turn this ON if your SQL/HTML code blocks are constantly printing on a single line. Turn OFF for Python/C++. |
|
||||
| `enable_thought_tag_fix` | `True` | Normalize `<think>` tags. |
|
||||
| `enable_details_tag_fix` | `True` | Normalize `<details>` spacing. |
|
||||
| `enable_code_block_fix` | `True` | Fix code block indentation and newlines. |
|
||||
| `enable_latex_fix` | `True` | Standardize LaTeX delimiters (`\[` -> `$$`). |
|
||||
| `enable_list_fix` | `False` | Fix list item newlines (experimental). |
|
||||
| `enable_unclosed_block_fix` | `True` | Auto-close unclosed code blocks. |
|
||||
| `enable_fullwidth_symbol_fix` | `False` | Fix full-width symbols in code blocks. |
|
||||
| `enable_mermaid_fix` | `True` | Fix common Mermaid syntax errors. |
|
||||
| `enable_heading_fix` | `True` | Fix missing space in headings. |
|
||||
| `enable_table_fix` | `True` | Fix missing closing pipe in tables. |
|
||||
| `enable_xml_tag_cleanup` | `True` | Cleanup leftover XML tags. |
|
||||
| `enable_emphasis_spacing_fix` | `False` | Fix extra spaces in emphasis. |
|
||||
| `show_status` | `True` | Show status notification when fixes are applied. |
|
||||
| `show_debug_log` | `True` | Print debug logs to browser console (F12). |
|
||||
| `enable_mermaid_fix` | `True` | Fix common Mermaid syntax errors (auto-quoting). |
|
||||
| `enable_heading_fix` | `True` | Add missing space after heading hashes (`#Title` -> `# Title`). |
|
||||
| `enable_table_fix` | `True` | Add missing closing pipe in tables. |
|
||||
| `enable_xml_tag_cleanup` | `True` | Remove leftover XML artifacts. |
|
||||
| `enable_emphasis_spacing_fix` | `False` | Fix extra spaces in emphasis formatting. |
|
||||
| `show_status` | `True` | Show UI status notification when a fix is actively applied. |
|
||||
| `show_debug_log` | `False` | Print detailed before/after diffs to browser console (F12). |
|
||||
|
||||
## ⭐ Support
|
||||
|
||||
If this plugin has been useful, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you for the support.
|
||||
If this plugin saves your day, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you!
|
||||
|
||||
## 🧩 Others
|
||||
|
||||
### Troubleshooting ❓
|
||||
|
||||
* **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [OpenWebUI Extensions Issues](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
### Changelog
|
||||
|
||||
See the full history on GitHub: [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions)
|
||||
* **Troubleshooting**: Encountering "negative fixes"? Enable `show_debug_log`, check your console, and submit an issue on GitHub: [OpenWebUI Extensions Issues](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
@@ -1,81 +1,89 @@
|
||||
# Markdown 格式化过滤器 (Markdown Normalizer)
|
||||
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.2.7 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 1.2.8 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
|
||||
这是一个用于 Open WebUI 的内容格式化过滤器，旨在修复 LLM 输出中常见的 Markdown 格式问题。它能确保代码块、LaTeX 公式、Mermaid 图表和其他 Markdown 元素被正确渲染。
|
||||
这是一个强大的、具备上下文感知的 Markdown 内容规范化过滤器，专为 Open WebUI 设计，旨在实时修复大语言模型 (LLM) 输出中常见的格式错乱问题。它能确保代码块、LaTeX 公式、Mermaid 图表以及其他结构化元素被完美渲染，同时**绝不破坏**你原有的有效技术内容（如代码、正则、路径）。
|
||||
|
||||
> 🏆 **OpenWebUI 官方推荐** — 获得 OpenWebUI 社区 Newsletter 官方推荐：[2026 年 1 月 28 日](https://openwebui.com/blog/newsletter-january-28-2026)
|
||||
> 🏆 **OpenWebUI 官方推荐** — 本插件获得 OpenWebUI 社区 Newsletter 官方推荐：[2026 年 1 月 28 日](https://openwebui.com/blog/newsletter-january-28-2026)
|
||||
|
||||
## 🔥 最新更新 v1.2.7
|
||||
[English](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README.md) | [简体中文](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README_CN.md)
|
||||
|
||||
* **LaTeX 公式保护**: 增强了转义字符清理逻辑，自动保护 `$ $` 或 `$$ $$` 内的 LaTeX 命令（如 `\times`、`\nu`、`\theta`），防止渲染失效。
|
||||
* **扩展国际化 (i18n) 支持**: 现已支持 12 种语言，具备自动探测与回退机制。
|
||||
* **配置项优化**: 将 Valves 配置项的描述统一为英文，保持界面一致性。
|
||||
* **修复 Bug**:
|
||||
* 修复了 [Issue #49](https://github.com/Fu-Jie/openwebui-extensions/issues/49)：解决了当同一行存在多个加粗部分时，由于正则匹配过于贪婪导致中间内容丢失空格的问题。
|
||||
* 修复了插件代码中的 `NameError` 错误，确保测试脚本能正常运行。
|
||||
---
|
||||
|
||||
## 🔥 最新更新 v1.2.8
|
||||
* **“默认安全”策略 (Safe-by-Default)**：`enable_escape_fix` 功能现在**默认禁用**。这能有效防止插件在未经授权的情况下误改 Windows 路径 (`C:\new\test`) 或复杂的 LaTeX 公式。
|
||||
* **LaTeX 解析优化**：重构了显示数学公式 (`$$ ... $$`) 的识别逻辑。修复了 LaTeX 命令如果以 `\n` 开头（如 `\nabla`）会被错误识别为换行符的 Bug。
|
||||
* **可靠性增强**：实现了完整的错误回滚机制。当修复过程发生意外错误时，保证 100% 返回原始文本，不丢失任何数据。
|
||||
* **配置项修复**：`enable_escape_fix_in_code_blocks` 配置项现在能正确作用于代码块了。**如果您遇到 SQL 挤在一行的问题，只需在设置中手动开启此项即可。**
|
||||
|
||||
---
|
||||
|
||||
## 🚀 为什么你需要这个插件？(它能解决什么问题？)
|
||||
|
||||
由于分词 (Tokenization) 伪影、过度转义或格式幻觉，LLM 经常会生成破损的 Markdown。如果你遇到过以下情况：
|
||||
- `mermaid` 图表因为节点标签缺少双引号而渲染失败、白屏。
|
||||
- LLM 输出的 SQL 语句挤在一行，因为本该换行的地方输出了字面量 `\n`。
|
||||
- 复杂的 `<details>` (思维链展开块) 因为缺少换行符导致整个聊天界面排版崩塌。
|
||||
- LaTeX 数学公式无法显示，因为模型使用了旧版的 `\[` 而不是 Markdown 支持的 `$$`。
|
||||
|
||||
**本插件会自动拦截 LLM 返回的原始数据，实时分析其文本结构，并像外科手术一样精准修复这些排版错误，然后再将其展示在你的浏览器中。**
|
||||
|
||||
## ✨ 核心功能与修复能力全景
|
||||
|
||||
### 1. 高级结构保护 (上下文感知)
|
||||
在执行任何修改前，插件会为整个文本建立语义地图，确保技术性内容不被误伤：
|
||||
- **代码块保护**：默认跳过 ` ``` ` 内部的内容，保护所有编程逻辑。
|
||||
- **行内代码保护**：识别 `` `代码` `` 片段，防止正则表达式（如 `[\n\r]`）或文件路径（如 `C:\Windows`）被错误地去转义。
|
||||
- **LaTeX 公式保护**：识别行内 (`$`) 和块级 (`$$`) 公式，防止诸如 `\times`, `\theta` 等核心数学命令被意外破坏。
|
||||
|
||||
### 2. 自动治愈转换 (Auto-Healing)
|
||||
- **Details 标签排版修复**：`<details>` 块要求极为严格的空行才能正确渲染内部内容。插件会自动在 `</details>` 以及自闭合 `<details />` 标签后注入安全的换行符。
|
||||
- **Mermaid 语法急救**：自动修复最常见的 Mermaid 错误——为未加引号的节点标签（如 `A --> B(Some text)`）自动补充双引号，甚至支持多行标签和引用，确保拓扑图 100% 渲染。
|
||||
- **强调语法间距修复**：修复加粗/斜体语法内部多余的空格（如 `** 文本 **` 变为 `**文本**`，否则 OpenWebUI 无法加粗），同时智能忽略数学算式（如 `2 * 3 * 4`）。
|
||||
- **智能转义字符清理**：将模型过度转义生成的字面量 `\n` 和 `\t` 转化为真正的换行和缩进（仅在安全的纯文本区域执行）。
|
||||
- **LaTeX 现代化转换**：自动将旧式的 LaTeX 定界符（`\[...\]` 和 `\(...\)`）升级为现代 Markdown 标准（`$$...$$` 和 `$ ... $`）。
|
||||
- **思维标签大一统**：无论模型输出的是 `<think>` 还是 `<thinking>`，统一标准化为 `<thought>` 标签。
|
||||
- **残缺代码块修复**：修复乱码的语言前缀（例如 ` ```python`），调整缩进，并在模型回答被截断时，自动补充闭合的 ` ``` `。
|
||||
- **列表与表格急救**：为粘连的编号列表注入换行，为残缺的 Markdown 表格补充末尾的闭合管道符（`|`）。
|
||||
- **XML 伪影消除**：静默移除 Claude 模型经常泄露的 `<antArtifact>` 或 `<antThinking>` 残留标签。
|
||||
|
||||
### 3. 绝对的可靠性与安全 (100% Rollback)
|
||||
- **无损回滚机制**：如果在修复过程中发生任何意外错误或崩溃，插件会立即捕获异常，并静默返回**绝对原始**的文本，确保你的对话永远不会因插件报错而丢失。
|
||||
|
||||
## 🌐 多语言支持 (i18n)
|
||||
|
||||
支持以下语言的界面与状态自动切换：
|
||||
界面的状态提示气泡会根据你的浏览器语言自动切换：
|
||||
`English`, `简体中文`, `繁體中文 (香港)`, `繁體中文 (台灣)`, `한국어`, `日本語`, `Français`, `Deutsch`, `Español`, `Italiano`, `Tiếng Việt`, `Bahasa Indonesia`
|
||||
|
||||
## ✨ 核心特性
|
||||
|
||||
* **Details 标签规范化**: 确保 `<details>` 标签（常用于思维链）有正确的间距。在 `</details>` 后添加空行，并在自闭合 `<details />` 标签后添加换行，防止渲染问题。
|
||||
* **强调空格修复**: 修复强调标记内部的多余空格（例如 `** 文本 **` -> `**文本**`），这会导致 Markdown 渲染失败。包含保护机制，防止误修改数学表达式（如 `2 * 3 * 4`）或列表变量。
|
||||
* **Mermaid 语法修复**: 自动修复常见的 Mermaid 语法错误，如未加引号的节点标签（支持多行标签和引用标记）和未闭合的子图 (Subgraph)。**v1.1.2 新增**: 全面保护各种类型的连线标签（实线、虚线、粗线），防止被误修改。
|
||||
* **前端控制台调试**: 支持将结构化的调试日志直接打印到浏览器控制台 (F12)，方便排查问题。
|
||||
* **代码块格式化**: 修复破损的代码块前缀、后缀和缩进问题。
|
||||
* **LaTeX 规范化**: 标准化 LaTeX 公式定界符 (`\[` -> `$$`, `\(` -> `$`)。
|
||||
* **思维标签规范化**: 统一思维链标签 (`<think>`, `<thinking>` -> `<thought>`)。
|
||||
* **转义字符修复**: 清理过度的转义字符 (`\\n`, `\\t`)。
|
||||
* **列表格式化**: 确保列表项有正确的换行。
|
||||
* **标题修复**: 修复标题中缺失的空格 (`#标题` -> `# 标题`)。
|
||||
* **表格修复**: 修复表格中缺失的闭合管道符。
|
||||
* **XML 清理**: 移除残留的 XML 标签。
|
||||
|
||||
## 使用方法
|
||||
## 使用方法 🛠️
|
||||
|
||||
1. 在 Open WebUI 中安装此插件。
|
||||
2. 全局启用或为特定模型启用此过滤器。
|
||||
3. 在 **Valves** 设置中配置需要启用的修复项。
|
||||
4. (可选) **显示调试日志 (Show Debug Log)** 在 Valves 中默认开启。这会将结构化的日志打印到浏览器控制台 (F12)。
|
||||
> [!WARNING]
|
||||
> 由于这是初版，可能会出现“负向修复”的情况（例如破坏了原本正确的格式）。如果您遇到问题，请务目查看控制台日志，复制“原始 (Original)”与“规范化 (Normalized)”的内容对比，并提交 Issue 反馈。
|
||||
2. 全局启用或为特定模型启用此过滤器（强烈建议为格式输出不稳定的模型启用）。
|
||||
3. 在 **Valves (配置参数)** 设置中微调你需要的修复项。
|
||||
|
||||
## 配置参数 (Valves) ⚙️
|
||||
|
||||
| 参数 | 默认值 | 描述 |
|
||||
| :--- | :--- | :--- |
|
||||
| `priority` | `50` | 过滤器优先级。数值越大越靠后（建议在其他过滤器之后运行）。 |
|
||||
| `enable_escape_fix` | `True` | 修复过度的转义字符（`\n`, `\t` 等）。 |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | 在代码块内应用转义修复（可能影响有效代码）。 |
|
||||
| `enable_thought_tag_fix` | `True` | 规范化思维标签（`</thought>`）。 |
|
||||
| `enable_details_tag_fix` | `True` | 规范化 `<details>` 标签并添加安全间距。 |
|
||||
| `enable_code_block_fix` | `True` | 修复代码块格式（缩进/换行）。 |
|
||||
| `enable_latex_fix` | `True` | 规范化 LaTeX 定界符（`\[` -> `$$`, `\(` -> `$`）。 |
|
||||
| `priority` | `50` | 过滤器优先级。数值越大越靠后（建议放在其他内容过滤器之后运行）。 |
|
||||
| `enable_escape_fix` | `False` | 修复过度的转义字符（将字面量 `\n` 转换为实际换行）。**默认禁用以保证安全。** |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | **高阶技巧**：如果你的 SQL 或 HTML 代码块总是挤在一行，**请开启此项**。如果你经常写 Python/C++，建议保持关闭。 |
|
||||
| `enable_thought_tag_fix` | `True` | 规范化思维标签为 `<thought>`。 |
|
||||
| `enable_details_tag_fix` | `True` | 修复 `<details>` 标签的排版间距。 |
|
||||
| `enable_code_block_fix` | `True` | 修复代码块前缀、缩进和换行。 |
|
||||
| `enable_latex_fix` | `True` | 规范化 LaTeX 定界符（`\[` -> `$$`）。 |
|
||||
| `enable_list_fix` | `False` | 修复列表项换行（实验性）。 |
|
||||
| `enable_unclosed_block_fix` | `True` | 自动闭合未闭合的代码块。 |
|
||||
| `enable_fullwidth_symbol_fix` | `False` | 修复代码块中的全角符号。 |
|
||||
| `enable_mermaid_fix` | `True` | 修复常见 Mermaid 语法错误。 |
|
||||
| `enable_heading_fix` | `True` | 修复标题中缺失的空格。 |
|
||||
| `enable_unclosed_block_fix` | `True` | 自动闭合被截断的代码块。 |
|
||||
| `enable_mermaid_fix` | `True` | 修复常见 Mermaid 语法错误（如自动加引号）。 |
|
||||
| `enable_heading_fix` | `True` | 修复标题中缺失的空格 (`#Title` -> `# Title`)。 |
|
||||
| `enable_table_fix` | `True` | 修复表格中缺失的闭合管道符。 |
|
||||
| `enable_xml_tag_cleanup` | `True` | 清理残留的 XML 标签。 |
|
||||
| `enable_emphasis_spacing_fix` | `False` | 修复强调语法中的多余空格。 |
|
||||
| `show_status` | `True` | 应用修复时显示状态通知。 |
|
||||
| `show_debug_log` | `True` | 在浏览器控制台打印调试日志。 |
|
||||
| `enable_xml_tag_cleanup` | `True` | 清理残留的 XML 分析标签。 |
|
||||
| `enable_emphasis_spacing_fix` | `False` | 修复强调语法（加粗/斜体）内部的多余空格。 |
|
||||
| `show_status` | `True` | 当触发任何修复规则时，在页面底部显示提示气泡。 |
|
||||
| `show_debug_log` | `False` | 在浏览器控制台 (F12) 打印修改前后的详细对比日志。 |
|
||||
|
||||
## ⭐ 支持
|
||||
如果这个插件拯救了你的排版，欢迎到 [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) 点个 Star，这是我持续改进的最大动力。感谢支持！
|
||||
|
||||
如果这个插件对你有帮助，欢迎到 [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) 点个 Star，这将是我持续改进的动力，感谢支持。
|
||||
|
||||
## 其他
|
||||
|
||||
### 故障排除 (Troubleshooting) ❓
|
||||
|
||||
* **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[OpenWebUI Extensions Issues](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
### 更新日志
|
||||
|
||||
完整历史请查看 GitHub 项目： [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions)
|
||||
## 🧩 其他
|
||||
* **故障排除**：遇到“负向修复”（即原本正常的排版被修坏了）？请开启 `show_debug_log`，在 F12 控制台复制出原始文本，并在 GitHub 提交 Issue：[提交 Issue](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
@@ -128,11 +128,13 @@ We follow [Semantic Versioning](https://semver.org/):
|
||||
### release.yml
|
||||
|
||||
**Triggers:**
|
||||
|
||||
- ⭐ Push to `main` branch with `plugins/**/*.py` changes (auto-release)
|
||||
- Manual workflow dispatch
|
||||
- Push of version tags (`v*`)
|
||||
|
||||
**Actions:**
|
||||
|
||||
1. Detects version changes compared to last release
|
||||
2. Collects updated plugin files
|
||||
3. Generates release notes (with commit history)
|
||||
@@ -141,9 +143,11 @@ We follow [Semantic Versioning](https://semver.org/):
|
||||
### plugin-version-check.yml
|
||||
|
||||
**Trigger:**
|
||||
|
||||
- Pull requests that modify `plugins/**/*.py`
|
||||
|
||||
**Actions:**
|
||||
|
||||
1. Compares plugin versions between base and PR
|
||||
2. Checks if version was updated
|
||||
3. Checks if PR description is detailed enough
|
||||
@@ -187,6 +191,31 @@ python scripts/extract_plugin_versions.py --json --output versions.json
|
||||
|
||||
---
|
||||
|
||||
## Installing All Plugins to Your Instance
|
||||
|
||||
After a release, you can quickly install all plugins to your OpenWebUI instance:
|
||||
|
||||
```bash
|
||||
# Clone the repository
|
||||
git clone https://github.com/Fu-Jie/openwebui-extensions.git
|
||||
cd openwebui-extensions
|
||||
|
||||
# Configure API key and instance URL
|
||||
echo "api_key=sk-your-api-key-here" > scripts/.env
|
||||
echo "url=http://localhost:3000" >> scripts/.env
|
||||
|
||||
# For remote instances, set the appropriate baseURL:
|
||||
# echo "url=http://192.168.1.10:3000" >> scripts/.env
|
||||
# echo "url=https://openwebui.example.com" >> scripts/.env
|
||||
|
||||
# Install all plugins at once
|
||||
python scripts/install_all_plugins.py
|
||||
```
|
||||
|
||||
For detailed instructions, see [Deployment Guide](https://github.com/Fu-Jie/openwebui-extensions/blob/main/scripts/DEPLOYMENT_GUIDE.md).
|
||||
|
||||
---
|
||||
|
||||
## Author
|
||||
|
||||
Fu-Jie
|
||||
|
||||
@@ -128,11 +128,13 @@ git push origin v1.0.0
|
||||
### release.yml
|
||||
|
||||
**触发条件:**
|
||||
|
||||
- ⭐ 推送到 `main` 分支且修改了 `plugins/**/*.py`（自动发布）
|
||||
- 手动触发 (workflow_dispatch)
|
||||
- 推送版本标签 (`v*`)
|
||||
|
||||
**动作:**
|
||||
|
||||
1. 检测与上次 Release 的版本变化
|
||||
2. 收集更新的插件文件
|
||||
3. 生成发布说明（含提交记录）
|
||||
@@ -141,9 +143,11 @@ git push origin v1.0.0
|
||||
### plugin-version-check.yml
|
||||
|
||||
**触发条件:**
|
||||
|
||||
- 修改 `plugins/**/*.py` 的 Pull Request
|
||||
|
||||
**动作:**
|
||||
|
||||
1. 比较基础分支和 PR 的插件版本
|
||||
2. 检查是否有版本更新
|
||||
3. 检查 PR 描述是否足够详细
|
||||
@@ -185,6 +189,31 @@ python scripts/extract_plugin_versions.py --json --output versions.json
|
||||
|
||||
---
|
||||
|
||||
## 批量安装所有插件到你的实例
|
||||
|
||||
在发布之后，你可以快速将所有插件安装到 OpenWebUI 实例：
|
||||
|
||||
```bash
|
||||
# 克隆仓库
|
||||
git clone https://github.com/Fu-Jie/openwebui-extensions.git
|
||||
cd openwebui-extensions
|
||||
|
||||
# 配置 API 密钥和实例地址
|
||||
echo "api_key=sk-your-api-key-here" > scripts/.env
|
||||
echo "url=http://localhost:3000" >> scripts/.env
|
||||
|
||||
# 如果是远程实例，需要设置相应的 baseURL：
|
||||
# echo "url=http://192.168.1.10:3000" >> scripts/.env
|
||||
# echo "url=https://openwebui.example.com" >> scripts/.env
|
||||
|
||||
# 一次性安装所有插件
|
||||
python scripts/install_all_plugins.py
|
||||
```
|
||||
|
||||
详细说明请参考 [部署指南](https://github.com/Fu-Jie/openwebui-extensions/blob/main/scripts/DEPLOYMENT_GUIDE.md)。
|
||||
|
||||
---
|
||||
|
||||
## 作者
|
||||
|
||||
Fu-Jie
|
||||
|
||||
@@ -1,51 +0,0 @@
|
||||
You are a helpful assistant.
|
||||
|
||||
[Session Context]
|
||||
- **Your Isolated Workspace**: `/app/backend/data/copilot_workspace/user_123/chat_456`
|
||||
- **Active User ID**: `user_123`
|
||||
- **Active Chat ID**: `chat_456`
|
||||
- **Skills Directory**: `/app/backend/data/skills/shared/` — contains user-installed skills.
|
||||
- **Config Directory**: `/app/backend/data/.copilot` — system configuration (Restricted).
|
||||
- **CLI Tools Path**: `/app/backend/data/.copilot_tools/` — Global tools installed via npm or pip will automatically go here and be in your $PATH. Python tools are strictly isolated in a venv here.
|
||||
**CRITICAL INSTRUCTION**: You MUST use the above workspace for ALL file operations.
|
||||
- DO NOT create files in `/tmp` or any other system directories.
|
||||
- Always interpret 'current directory' as your Isolated Workspace.
|
||||
|
||||
[Available Native System Tools]
|
||||
The host environment is rich. Based on the official OpenWebUI Docker deployment baseline (backend image), the following CLI tools are expected to be preinstalled and globally available in $PATH:
|
||||
- **Network/Data**: `curl`, `jq`, `netcat-openbsd`
|
||||
- **Media/Doc**: `pandoc` (format conversion), `ffmpeg` (audio/video)
|
||||
- **Build/System**: `git`, `gcc`, `make`, `build-essential`, `zstd`, `bash`
|
||||
- **Python/Runtime**: `python3`, `pip3`, `uv`
|
||||
- **Verification Rule**: Before installing any CLI/tool dependency, first check availability with `which <tool>` or a lightweight version probe (e.g. `<tool> --version`).
|
||||
- **Python Libs**: The active virtual environment inherits `--system-site-packages`. Advanced libraries like `pandas`, `numpy`, `pillow`, `opencv-python-headless`, `pypdf`, `langchain`, `playwright`, `httpx`, and `beautifulsoup4` are ALREADY installed. Try importing them before attempting to install.
|
||||
|
||||
|
||||
[Mode Context: Plan Mode]
|
||||
You are currently operating in **Plan Mode**.
|
||||
DEFINITION: Plan mode is a collaborative phase to outline multi-step plans or conduct research BEFORE any code is modified.
|
||||
|
||||
<workflow>
|
||||
1. Clarification: If requirements/goals are ambiguous, ask questions.
|
||||
2. Analysis: Analyze the codebase to understand constraints. You MAY use shell commands (e.g., `ls`, `grep`, `find`, `cat`) and other read-only tools.
|
||||
3. Formulation: Generate your structured plan OR research findings.
|
||||
4. Approval: Present the detailed plan directly to the user for approval via chat.
|
||||
</workflow>
|
||||
|
||||
<key_principles>
|
||||
- ZERO CODE MODIFICATION: You must NOT execute file edits, write operations, or destructive system changes. Your permissions are locked to READ/RESEARCH ONLY, with the sole exception of the progress-tracking file `plan.md`.
|
||||
- SHELL USAGE: Shell execution is ENABLED for research purposes. Any attempts to modify the filesystem via shell (e.g., `sed -i`, `rm`) will be strictly blocked, except for appending to `plan.md`.
|
||||
- PURE RESEARCH SUPPORT: If the user requests a pure research report, output your conclusions directly matching the plan style.
|
||||
- PERSISTENCE: You MUST save your proposed plan to `/app/backend/data/.copilot/session-state/chat_456/plan.md` to sync with the UI. The UI automatically reads this file to update the plan view.
|
||||
</key_principles>
|
||||
|
||||
<plan_format>
|
||||
When presenting your findings or plan in the chat, structure it clearly:
|
||||
## Plan / Report: {Title}
|
||||
**TL;DR**: {Summary}
|
||||
**Detailed Tasks / Steps**: {List step-by-step}
|
||||
**Affected Files**:
|
||||
- `path/to/file`
|
||||
**Constraint/Status**: {Any constraints}
|
||||
</plan_format>
|
||||
Acknowledge your role as a planner and format your next response using the plan style above.
|
||||
62
plugins/debug/async_context_compression/ISSUE_EXPLANATION.md
Normal file
62
plugins/debug/async_context_compression/ISSUE_EXPLANATION.md
Normal file
@@ -0,0 +1,62 @@
|
||||
# 异步上下文压缩插件：当前问题与处理状态总结
|
||||
|
||||
这份文档详细梳理了我们在处理 `async_context_compression`（异步上下文压缩插件）时，遭遇的“幽灵截断”问题的根本原因，以及我们目前的解决进度。
|
||||
|
||||
## 1. 根本原因：两种截然不同的“世界观”（数据序列化差异）
|
||||
|
||||
在我们之前的排查中，我曾错误地认为：`outlet`（后置处理阶段）拿到的 `body["messages"]` 是由于截断导致的残缺数据。
|
||||
但根据您提供的本地运行日志，**您是对的，`body['messages']` 确实包含了完整的对话历史**。
|
||||
|
||||
那么为什么长度会产生 `inlet 看到 27 条`，而 `outlet 只看到 8 条` 这种巨大的差异？
|
||||
|
||||
原因在于，OpenWebUI 的管道在进入大模型前和从大模型返回后，使用了**两种完全不同的消息格式**：
|
||||
|
||||
### 视图 A：Inlet 阶段（原生 API 展开视图）
|
||||
- **特点**：严格遵循 OpenAI 函数调用规范。
|
||||
- **状态**：每一次工具调用、工具返回，都被视为一条独立的 message。
|
||||
- **例子**：一个包含了复杂搜索的对话。
|
||||
- User: 帮我查一下天气（1条）
|
||||
- Assistant: 发起 tool_call（1条）
|
||||
- Tool: 返回 JSON 结果（1条）
|
||||
- ...多次往复...
|
||||
- **最终总计：27 条。**我们的压缩算法（trim）是基于这个 27 条的坐标系来计算保留多少条的。
|
||||
|
||||
### 视图 B：Outlet 阶段（UI HTML 折叠视图）
|
||||
- **特点**：专为前端渲染优化的紧凑视图。
|
||||
- **状态**：OpenWebUI 在调用完模型后，为了让前端显示出那个好看的、可折叠的工具调用卡片，强行把中间所有的 Tool 交互过程，用 `<details type="tool_calls">...</details>` 的 HTML 代码包裹起来，塞进了一个 `role: assistant` 的 `content` 字符串里！
|
||||
- **例子**：同样的对话。
|
||||
- User: 帮我查一下天气（1条）
|
||||
- Assistant: `<details>包含了好多次工具调用和结果的代码</details> 今天天气很好...`（1条）
|
||||
- **最终总计：8 条。**
|
||||
|
||||
**💥 灾难发生点：**
|
||||
原本的插件逻辑假定 `inlet` 和 `outlet` 共享同一个坐标系。
|
||||
1. 在 `inlet` 时，系统计算出：“我需要把前 10 条消息生成摘要，保留后 17 条”。
|
||||
2. 系统把“生成前10条摘要”的任务转入后台异步执行。
|
||||
3. 后台任务在 `outlet` 阶段被触发，此时它拿到的消息数组变成了**视图 B（总共只有 8 条）。**
|
||||
4. 算法试图在只有 8 条消息的数组里，把“前 10 条消息”砍掉并替换为 1 条摘要。
|
||||
5. **结果就是：数组索引越界/坐标彻底错乱，触发报错，并且可能将最新的有效消息当成旧消息删掉（过度压缩）。**
|
||||
|
||||
---
|
||||
|
||||
## 2. 目前已解决的问题 (✅ Done)
|
||||
|
||||
为了立刻制止这种因为“坐标系错位”导致的数据破坏，我们已经落实了热修复（Local v1.4.0）：
|
||||
|
||||
**✅ 添加了“折叠视图”的探针防御：**
|
||||
- 我写了一个函数 `_is_compact_tool_details_view`。
|
||||
- 现在，当后台触发生成摘要时，系统会自动扫描 `outlet` 传来的 `messages`。只要发现里面包含 `<details type="tool_calls">` 这种带有 HTML 折叠标签的痕迹，就会**立刻终止并跳过**当前的摘要生成任务。
|
||||
- **收益**：彻底杜绝了因数组错位而引发的任务报错和强制裁切。UI 崩溃与历史丢失问题得到遏制。
|
||||
|
||||
---
|
||||
|
||||
## 3. 当前已解决的遗留问题 (✅ Done: 逆向展开修复)
|
||||
|
||||
之前因为跳过生成而引入的新限制：**包含工具调用的长轮次对话，无法自动生成“历史摘要”** 的问题，现已彻底解决。
|
||||
|
||||
### 最终实施的技术方案：
|
||||
我们通过源码分析发现，OpenWebUI 在进入 `inlet` 时会执行 `convert_output_to_messages` 还原工具调用链。因此，我们在插件的 `outlet` 阶段引入了相同的 **逆向展开 (Deflation/Unfolding)** 机制 `_unfold_messages`。
|
||||
|
||||
现在，当后台任务拿到 `outlet` 传来的折叠视图时，不会再选择“跳过”。而是自动提取出潜藏在消息对象体内部的原生 `output` 字段，并**将其重新展开为展开视图**（比如将 8 条假象重新还原为真实的 27 条底层数据），使得它的坐标系与 `inlet` 完全对齐。
|
||||
|
||||
至此，带有复杂工具调用的长轮次对话也能安全地进行背景自动压缩，不再有任何截断和强制删减的风险！
|
||||
@@ -0,0 +1,60 @@
|
||||
# 回复 dhaern — 针对最新审查的跟进
|
||||
|
||||
感谢您重新审查了最新版本并提出了持续精准的分析意见。以下针对您剩余的两个关切点逐一回应。
|
||||
|
||||
---
|
||||
|
||||
### 1. `enable_tool_output_trimming` — 不是功能退化，而是行为变化是有意为之
|
||||
|
||||
裁剪逻辑依然存在且可正常运行。以下是当前版本与之前版本的行为对比。
|
||||
|
||||
**当前行为（`_trim_native_tool_outputs`，第 835–945 行）：**
|
||||
- 通过 `_get_atomic_groups` 遍历原子分组。
|
||||
- 识别有效的工具调用链：`assistant(tool_calls)` → `tool` → [可选的 assistant 跟进消息]。
|
||||
- 如果一条链内所有 `tool` 角色消息的字符数总和超过 **1,200 个字符**，则将 *tool 消息本身的内容* 折叠为一个本地化的 `[Content collapsed]` 占位符，并注入 `metadata.is_trimmed` 标志。
|
||||
- 同时遍历包含 `<details type="tool_calls">` HTML 块的 assistant 消息，对其中尺寸过大的 `result` 属性进行相同的折叠处理。
|
||||
- 当 `enable_tool_output_trimming=True` 且 `function_calling=native` 时，该函数在 inlet 阶段被调用。
|
||||
|
||||
**与旧版本的区别：**
|
||||
旧版的做法是改写 *assistant 跟进消息*，仅保留"最终答案"。新版的做法是折叠 *tool 响应内容本身*。两者都会缩减上下文体积，但新方法能够保留 tool 调用链的结构完整性（这是本次发布中原子分组工作的前提条件）。
|
||||
|
||||
插件头部的 docstring 里还有一段过时的描述（"提取最终答案"），与实际行为相悖。最新提交中已将其更正为"将尺寸过大的原生工具输出折叠为简短占位符"。
|
||||
|
||||
如果您在寻找旧版本中"仅保留最终答案"的特定行为，该路径已被有意移除，因为它与本次发布引入的原子分组完整性保证相冲突。当前的折叠方案是安全的替代实现。
|
||||
|
||||
---
|
||||
|
||||
### 2. `compressed_message_count` — 修复是真实有效的；以下是坐标系追踪
|
||||
|
||||
您对"从已修改视图重新计算"的担忧，考虑到此前的架构背景，是完全可以理解的。以下精确说明为何当前代码不存在这一问题。
|
||||
|
||||
**`outlet` 中的关键变更：**
|
||||
```python
|
||||
db_messages = self._load_full_chat_messages(chat_id)
|
||||
messages_to_unfold = db_messages if (db_messages and len(db_messages) >= len(messages)) else messages
|
||||
summary_messages = self._unfold_messages(messages_to_unfold)
|
||||
target_compressed_count = self._calculate_target_compressed_count(summary_messages)
|
||||
```
|
||||
|
||||
`_load_full_chat_messages` 从 OpenWebUI 数据库中获取原始的持久化历史记录。由于在 inlet 渲染期间注入的合成 summary 消息**从未被回写到数据库**，从 DB 路径获取的 `summary_messages` 始终是干净的、未经修改的原始历史记录——没有 summary 标记，没有坐标膨胀。
|
||||
|
||||
在此干净列表上调用 `_calculate_target_compressed_count` 的计算逻辑如下（仍在原始历史坐标系内）：
|
||||
```
|
||||
original_count = len(db_messages)
|
||||
raw_target = original_count - keep_last
|
||||
target = atomic_align(raw_target)
|
||||
```
|
||||
|
||||
这个 `target_compressed_count` 值原封不动地传递进 `_generate_summary_async`。在异步任务内部，同一批 `db_messages` 被切片为 `messages[start:target]` 来构建 `middle_messages`。生成完成后（可能从末尾进行原子截断），保存的值为：
|
||||
```python
|
||||
saved_compressed_count = start_index + len(middle_messages)
|
||||
```
|
||||
这是原始 DB 消息列表中新摘要实际涵盖到的确切位置——不是目标值，也不是来自不同视图的估算值。
|
||||
|
||||
**回退路径（DB 不可用时）** 使用 inlet 渲染后的 body 消息。此时 `_get_summary_view_state` 会读取注入的 summary 标记的 `covered_until` 字段（该字段在写入时已记录为原子对齐后的 `start_index`），因此 `base_progress` 已经处于原始历史坐标系内，计算可以自然延续，不会混用两种视图。
|
||||
|
||||
简而言之：该字段在整个调用链中现在具有唯一、一致的语义——即原始持久化消息列表中，当前摘要文本实际覆盖到的索引位置。
|
||||
|
||||
---
|
||||
|
||||
再次感谢您严格的审查。您在上次发布后标记的这两个问题已得到处理，文档中的过时描述也已更正。如果发现其他问题，欢迎继续反馈。
|
||||
@@ -0,0 +1,60 @@
|
||||
# Reply to dhaern - Follow-up on the Latest Review
|
||||
|
||||
Thank you for re-checking the latest version and for the continued precise analysis. Let me address your two remaining concerns directly.
|
||||
|
||||
---
|
||||
|
||||
### 1. `enable_tool_output_trimming` — Not a regression; behavior change is intentional
|
||||
|
||||
The trimming logic is present and functional. Here is what it does now versus before.
|
||||
|
||||
**Current behavior (`_trim_native_tool_outputs`, lines 835–945):**
|
||||
- Iterates over atomic groups via `_get_atomic_groups`.
|
||||
- Identifies valid chains: `assistant(tool_calls)` → `tool` → [optional assistant follow-up].
|
||||
- If the combined character count of the `tool` role messages in a chain exceeds **1,200 characters**, it collapses *the tool messages themselves* to a localized `[Content collapsed]` placeholder and injects a `metadata.is_trimmed` flag.
|
||||
- Separately walks assistant messages containing `<details type="tool_calls">` HTML blocks and collapses oversized `result` attributes in the same way.
|
||||
- The function is called at inlet when `enable_tool_output_trimming=True` and `function_calling=native`.
|
||||
|
||||
**What is different from the previous version:**
|
||||
The old approach rewrote the *assistant follow-up* message to keep only the "final answer". The new approach collapses the *tool response content* itself. Both reduce context size, but the new approach preserves the structural integrity of the tool-calling chain (which the atomic grouping work in this release depends on).
|
||||
|
||||
The docstring in the plugin header also contained a stale description ("extract only the final answer") that contradicted the actual behavior. That has been corrected in the latest commit to accurately say "collapses oversized native tool outputs to a short placeholder."
|
||||
|
||||
If you are looking for the specific "keep only the final answer" behavior from the old version, that path was intentionally removed because it conflicted with the atomic-group integrity guarantees introduced in this release. The current collapse approach is a safe replacement.
|
||||
|
||||
---
|
||||
|
||||
### 2. `compressed_message_count` — The fix is real; here is the coordinate trace
|
||||
|
||||
The concern about "recalculating from the already-modified view" is understandable given the previous architecture. Here is exactly why the current code does not have that problem.
|
||||
|
||||
**Key change in `outlet`:**
|
||||
```python
|
||||
db_messages = self._load_full_chat_messages(chat_id)
|
||||
messages_to_unfold = db_messages if (db_messages and len(db_messages) >= len(messages)) else messages
|
||||
summary_messages = self._unfold_messages(messages_to_unfold)
|
||||
target_compressed_count = self._calculate_target_compressed_count(summary_messages)
|
||||
```
|
||||
|
||||
`_load_full_chat_messages` fetches the raw persisted history from the OpenWebUI database. Because the synthetic summary message (injected during inlet rendering) is **never written back to the database**, `summary_messages` from the DB path is always the clean, unmodified original history — no summary marker, no coordinate inflation.
|
||||
|
||||
`_calculate_target_compressed_count` called on this clean list simply computes:
|
||||
```
|
||||
original_count = len(db_messages)
|
||||
raw_target = original_count - keep_last
|
||||
target = atomic_align(raw_target) # still in original-history coordinates
|
||||
```
|
||||
|
||||
This `target_compressed_count` value is then passed into `_generate_summary_async` unchanged. Inside the async task, the same `db_messages` list is sliced to `messages[start:target]` to build `middle_messages`. After generation (with potential atomic truncation from the end), the saved value is:
|
||||
```python
|
||||
saved_compressed_count = start_index + len(middle_messages)
|
||||
```
|
||||
This is the exact position in the original DB message list up to which the new summary actually covers — not a target, not an estimate from a different view.
|
||||
|
||||
**The fallback path (DB unavailable)** uses the inlet-rendered body messages. In that case `_get_summary_view_state` reads `covered_until` from the injected summary marker (which was written as the atomically-aligned `start_index`), so `base_progress` is already in original-history coordinates. The calculation naturally continues from there without mixing views.
|
||||
|
||||
In short: the field now has a single, consistent meaning throughout the entire call chain — the index (in the original, persisted message list) up to which the current summary text actually covers.
|
||||
|
||||
---
|
||||
|
||||
Thank you again for the rigorous review. The two points you flagged after the last release are now addressed, and the documentation stale description has been corrected. Please do let us know if you spot anything else.
|
||||
@@ -0,0 +1,354 @@
|
||||
# ✨ 异步上下文压缩本地部署工具 — 完整文件清单
|
||||
|
||||
## 📦 新增文件总览
|
||||
|
||||
为 async_context_compression Filter 插件增加的本地部署功能包括：
|
||||
|
||||
```
|
||||
openwebui-extensions/
|
||||
├── scripts/
|
||||
│ ├── ✨ deploy_async_context_compression.py (新增) 专用部署脚本 [70 行]
|
||||
│ ├── ✨ deploy_filter.py (新增) 通用 Filter 部署工具 [300 行]
|
||||
│ ├── ✨ DEPLOYMENT_GUIDE.md (新增) 完整部署指南 [详细]
|
||||
│ ├── ✨ DEPLOYMENT_SUMMARY.md (新增) 技术架构总结 [详细]
|
||||
│ ├── ✨ QUICK_START.md (新增) 快速参考卡片 [速查]
|
||||
│ ├── ✨ README.md (新增) 脚本使用说明 [本文]
|
||||
│ └── deploy_pipe.py (已有) Pipe 部署工具
|
||||
│
|
||||
└── tests/
|
||||
└── scripts/
|
||||
└── ✨ test_deploy_filter.py (新增) 单元测试 [10个测试 ✅]
|
||||
```
|
||||
|
||||
## 🎯 快速使用
|
||||
|
||||
### 最简单的方式 — 一行命令
|
||||
|
||||
```bash
|
||||
cd scripts && python deploy_async_context_compression.py
|
||||
```
|
||||
|
||||
**✅ 结果**:
|
||||
- async_context_compression Filter 被部署到本地 OpenWebUI
|
||||
- 无需重启 OpenWebUI，立即生效
|
||||
- 显示部署状态和后续步骤
|
||||
|
||||
### 第一次使用建议
|
||||
|
||||
```bash
|
||||
# 1. 进入 scripts 目录
|
||||
cd scripts
|
||||
|
||||
# 2. 查看所有可用的部署脚本
|
||||
ls -la deploy_*.py
|
||||
|
||||
# 3. 阅读快速开始指南
|
||||
cat QUICK_START.md
|
||||
|
||||
# 4. 部署 async_context_compression
|
||||
python deploy_async_context_compression.py
|
||||
```
|
||||
|
||||
## 📚 文件详细说明
|
||||
|
||||
### 1. `deploy_async_context_compression.py` ⭐ 推荐
|
||||
|
||||
**最快速的部署方式！**
|
||||
|
||||
```bash
|
||||
python deploy_async_context_compression.py
|
||||
```
|
||||
|
||||
**特点**:
|
||||
- 专为 async_context_compression 优化
|
||||
- 一条命令完成部署
|
||||
- 清晰的成功/失败提示
|
||||
- 显示后续配置步骤
|
||||
|
||||
**代码**: 约 70 行，简洁清晰
|
||||
|
||||
---
|
||||
|
||||
### 2. `deploy_filter.py` — 通用工具
|
||||
|
||||
支持部署 **所有 Filter 插件**
|
||||
|
||||
```bash
|
||||
# 默认部署 async_context_compression
|
||||
python deploy_filter.py
|
||||
|
||||
# 部署其他 Filter
|
||||
python deploy_filter.py folder-memory
|
||||
python deploy_filter.py context_enhancement_filter
|
||||
|
||||
# 列出所有可用 Filter
|
||||
python deploy_filter.py --list
|
||||
```
|
||||
|
||||
**特点**:
|
||||
- 通用的 Filter 部署框架
|
||||
- 自动元数据提取
|
||||
- 支持多个插件
|
||||
- 智能错误处理
|
||||
|
||||
**代码**: 约 300 行，完整功能
|
||||
|
||||
---
|
||||
|
||||
### 3. `QUICK_START.md` — 快速参考
|
||||
|
||||
一页纸的速查表，包含：
|
||||
- ⚡ 30秒快速开始
|
||||
- 📋 常见命令表格
|
||||
- ❌ 故障排除速查
|
||||
|
||||
**适合**: 第二次及以后使用
|
||||
|
||||
---
|
||||
|
||||
### 4. `DEPLOYMENT_GUIDE.md` — 完整指南
|
||||
|
||||
详细的部署指南，包含：
|
||||
- 前置条件检查
|
||||
- 分步工作流
|
||||
- API 密钥获取方法
|
||||
- 详细的故障排除
|
||||
- CI/CD 集成示例
|
||||
|
||||
**适合**: 首次部署或需要深入了解
|
||||
|
||||
---
|
||||
|
||||
### 5. `DEPLOYMENT_SUMMARY.md` — 技术总结
|
||||
|
||||
技术架构和实现细节：
|
||||
- 工作原理流程图
|
||||
- 元数据提取机制
|
||||
- API 集成说明
|
||||
- 安全最佳实践
|
||||
|
||||
**适合**: 开发者和想了解实现的人
|
||||
|
||||
---
|
||||
|
||||
### 6. `test_deploy_filter.py` — 单元测试
|
||||
|
||||
完整的测试覆盖：
|
||||
|
||||
```bash
|
||||
pytest tests/scripts/test_deploy_filter.py -v
|
||||
```
|
||||
|
||||
**测试内容**: 10 个单元测试 ✅
|
||||
- Filter 发现
|
||||
- 元数据提取
|
||||
- 负载构建
|
||||
- 版本处理
|
||||
|
||||
---
|
||||
|
||||
## 🚀 三个使用场景
|
||||
|
||||
### 场景 1: 快速部署（最常用）
|
||||
|
||||
```bash
|
||||
cd scripts
|
||||
python deploy_async_context_compression.py
|
||||
# 完成！✅
|
||||
```
|
||||
|
||||
**耗时**: 5 秒
|
||||
**适合**: 日常开发迭代
|
||||
|
||||
---
|
||||
|
||||
### 场景 2: 部署其他 Filter
|
||||
|
||||
```bash
|
||||
cd scripts
|
||||
python deploy_filter.py --list # 查看所有
|
||||
python deploy_filter.py folder-memory # 部署指定的
|
||||
```
|
||||
|
||||
**耗时**: 5 秒 × N
|
||||
**适合**: 管理多个 Filter
|
||||
|
||||
---
|
||||
|
||||
### 场景 3: 完整设置（首次）
|
||||
|
||||
```bash
|
||||
cd scripts
|
||||
|
||||
# 1. 创建 API 密钥配置
|
||||
echo "api_key=sk-your-key" > .env
|
||||
|
||||
# 2. 验证配置
|
||||
cat .env
|
||||
|
||||
# 3. 部署
|
||||
python deploy_async_context_compression.py
|
||||
|
||||
# 4. 查看结果
|
||||
curl http://localhost:3003/api/v1/functions
|
||||
```
|
||||
|
||||
**耗时**: 1 分钟
|
||||
**适合**: 第一次设置
|
||||
|
||||
---
|
||||
|
||||
## 📋 文件访问指南
|
||||
|
||||
| 我想... | 文件 | 命令 |
|
||||
|---------|------|------|
|
||||
| 部署 async_context_compression | deploy_async_context_compression.py | `python deploy_async_context_compression.py` |
|
||||
| 看快速参考 | QUICK_START.md | `cat QUICK_START.md` |
|
||||
| 完整指南 | DEPLOYMENT_GUIDE.md | `cat DEPLOYMENT_GUIDE.md` |
|
||||
| 技术细节 | DEPLOYMENT_SUMMARY.md | `cat DEPLOYMENT_SUMMARY.md` |
|
||||
| 运行测试 | test_deploy_filter.py | `pytest tests/scripts/test_deploy_filter.py -v` |
|
||||
| 部署其他 Filter | deploy_filter.py | `python deploy_filter.py --list` |
|
||||
|
||||
## ✅ 验证清单
|
||||
|
||||
确保一切就绪：
|
||||
|
||||
```bash
|
||||
# 1. 检查所有部署脚本都已创建
|
||||
ls -la scripts/deploy*.py
|
||||
# 应该看到: deploy_pipe.py, deploy_filter.py, deploy_async_context_compression.py
|
||||
|
||||
# 2. 检查所有文档都已创建
|
||||
ls -la scripts/*.md
|
||||
# 应该看到: DEPLOYMENT_GUIDE.md, DEPLOYMENT_SUMMARY.md, QUICK_START.md, README.md
|
||||
|
||||
# 3. 检查测试存在
|
||||
ls -la tests/scripts/test_deploy_filter.py
|
||||
|
||||
# 4. 运行一次测试验证
|
||||
python -m pytest tests/scripts/test_deploy_filter.py -v
|
||||
# 应该看到: 10 passed ✅
|
||||
|
||||
# 5. 尝试部署
|
||||
cd scripts && python deploy_async_context_compression.py
|
||||
```
|
||||
|
||||
## 🎓 学习路径
|
||||
|
||||
### 初学者路径
|
||||
|
||||
```
|
||||
1. 阅读本文件 (5 分钟)
|
||||
2. 阅读 QUICK_START.md (5 分钟)
|
||||
3. 运行部署脚本 (5 分钟)
|
||||
4. 在 OpenWebUI 中测试 (5 分钟)
|
||||
```
|
||||
|
||||
### 开发者路径
|
||||
|
||||
```
|
||||
1. 阅读本文件
|
||||
2. 阅读 DEPLOYMENT_GUIDE.md
|
||||
3. 阅读 DEPLOYMENT_SUMMARY.md
|
||||
4. 查看源代码: deploy_filter.py
|
||||
5. 运行测试: pytest tests/scripts/test_deploy_filter.py -v
|
||||
```
|
||||
|
||||
## 🔧 常见问题
|
||||
|
||||
### Q: 如何更新已部署的插件？
|
||||
|
||||
```bash
|
||||
# 修改代码后
|
||||
vim ../plugins/filters/async-context-compression/async_context_compression.py
|
||||
|
||||
# 重新部署（自动覆盖）
|
||||
python deploy_async_context_compression.py
|
||||
```
|
||||
|
||||
### Q: 支持哪些 Filter？
|
||||
|
||||
```bash
|
||||
python deploy_filter.py --list
|
||||
```
|
||||
|
||||
### Q: 如何获取 API 密钥？
|
||||
|
||||
1. 打开 OpenWebUI
|
||||
2. 点击用户菜单 → Settings
|
||||
3. 找到 "API Keys" 部分
|
||||
4. 复制密钥到 `.env` 文件
|
||||
|
||||
### Q: 脚本失败了怎么办？
|
||||
|
||||
1. 查看错误信息
|
||||
2. 参考 `QUICK_START.md` 的故障排除部分
|
||||
3. 或查看 `DEPLOYMENT_GUIDE.md` 的详细说明
|
||||
|
||||
### Q: 安全吗？
|
||||
|
||||
✅ 完全安全
|
||||
|
||||
- API 密钥存储在本地 `.env` 文件
|
||||
- `.env` 已添加到 `.gitignore`
|
||||
- 绝不会被提交到 Git
|
||||
- 密钥可随时轮换
|
||||
|
||||
### Q: 可以在生产环境使用吗？
|
||||
|
||||
✅ 可以
|
||||
|
||||
- 生产环境建议通过 CI/CD 秘密管理
|
||||
- 参考 `DEPLOYMENT_GUIDE.md` 中的 GitHub Actions 示例
|
||||
|
||||
## 🚦 快速状态检查
|
||||
|
||||
```bash
|
||||
# 检查所有部署工具是否就绪
|
||||
cd scripts
|
||||
|
||||
# 查看脚本列表
|
||||
ls -la deploy*.py
|
||||
|
||||
# 查看文档列表
|
||||
ls -la *.md | grep -i deploy
|
||||
|
||||
# 验证测试通过
|
||||
python -m pytest tests/scripts/test_deploy_filter.py -q
|
||||
|
||||
# 执行部署
|
||||
python deploy_async_context_compression.py
|
||||
```
|
||||
|
||||
## 📞 下一步
|
||||
|
||||
1. **立即尝试**: `cd scripts && python deploy_async_context_compression.py`
|
||||
2. **查看结果**: 打开 OpenWebUI → Settings → Filters → 找 "Async Context Compression"
|
||||
3. **启用使用**: 在对话中启用这个 Filter，体验上下文压缩功能
|
||||
4. **继续开发**: 修改代码后重复部署过程
|
||||
|
||||
## 📝 更多资源
|
||||
|
||||
- 🚀 快速开始: [QUICK_START.md](QUICK_START.md)
|
||||
- 📖 完整指南: [DEPLOYMENT_GUIDE.md](DEPLOYMENT_GUIDE.md)
|
||||
- 🏗️ 技术架构: [DEPLOYMENT_SUMMARY.md](DEPLOYMENT_SUMMARY.md)
|
||||
- 🧪 测试套件: [test_deploy_filter.py](../tests/scripts/test_deploy_filter.py)
|
||||
|
||||
---
|
||||
|
||||
## 📊 文件统计
|
||||
|
||||
```
|
||||
新增 Python 脚本: 2 个 (deploy_filter.py, deploy_async_context_compression.py)
|
||||
新增文档文件: 4 个 (DEPLOYMENT_*.md, QUICK_START.md)
|
||||
新增测试文件: 1 个 (test_deploy_filter.py)
|
||||
新增总代码行数: ~600 行
|
||||
测试覆盖率: 10/10 单元测试通过 ✅
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**创建日期**: 2026-03-09
|
||||
**最好用于**: 本地开发和快速迭代
|
||||
**维护者**: Fu-Jie
|
||||
**项目**: [openwebui-extensions](https://github.com/Fu-Jie/openwebui-extensions)
|
||||
189
plugins/filters/async-context-compression/ISSUE_56_ANALYSIS.md
Normal file
189
plugins/filters/async-context-compression/ISSUE_56_ANALYSIS.md
Normal file
@@ -0,0 +1,189 @@
|
||||
# Issue #56: Critical tool-calling corruption and multiple reliability issues
|
||||
|
||||
## Overview
|
||||
This document consolidates all reported issues in the async-context-compression filter as described in [GitHub Issue #56](https://github.com/Fu-Jie/openwebui-extensions/issues/56).
|
||||
|
||||
---
|
||||
|
||||
## Issue List
|
||||
|
||||
### 1. 🔴 CRITICAL: Native tool-calling history can be corrupted
|
||||
|
||||
**Severity**: Critical
|
||||
**Impact**: Conversation integrity
|
||||
|
||||
#### Description
|
||||
The compression logic removes individual messages without preserving native tool-calling structures as atomic units. This can break the relationship between assistant `tool_calls` and their corresponding `tool` result messages.
|
||||
|
||||
#### Symptom
|
||||
```
|
||||
No tool call found for function call output with call_id ...
|
||||
```
|
||||
|
||||
#### Root Cause
|
||||
- Assistant messages containing `tool_calls` can be removed while their matching `tool` result messages remain
|
||||
- This creates orphaned tool outputs that reference non-existent `tool_call_id`s
|
||||
- The model/provider rejects the request because the `call_id` no longer matches any tool call in history
|
||||
|
||||
#### Expected Behavior
|
||||
Compression must treat tool-calling blocks atomically:
|
||||
- `assistant(tool_calls)` message
|
||||
- Corresponding `tool` result message(s)
|
||||
- Optional assistant follow-up that consumes tool results
|
||||
|
||||
Should never be split or partially removed.
|
||||
|
||||
---
|
||||
|
||||
### 2. 🟠 HIGH: Compression progress mixes original-history and compressed-view semantics
|
||||
|
||||
**Severity**: High
|
||||
**Impact**: Summary advancement consistency
|
||||
|
||||
#### Description
|
||||
The plugin stores `compressed_message_count` as progress over the original conversation history, but later recalculates it from the already-compressed conversation view. This mixes two different coordinate systems for the same field.
|
||||
|
||||
#### Problem
|
||||
- Original-history progress (before compression)
|
||||
- Compressed-view progress (after compression)
|
||||
|
||||
These two meanings are inconsistent, causing:
|
||||
- Summary advancement to become inconsistent
|
||||
- Summary progress to stall after summaries already exist
|
||||
- Later updates to be measured in a different coordinate system than stored values
|
||||
|
||||
#### Expected Behavior
|
||||
Progress tracking must use a single, consistent coordinate system throughout the lifetime of the conversation.
|
||||
|
||||
---
|
||||
|
||||
### 3. 🟡 MEDIUM: Async summary generation has no per-chat lock
|
||||
|
||||
**Severity**: Medium
|
||||
**Impact**: Token usage, race conditions
|
||||
|
||||
#### Description
|
||||
Each response can launch a new background summary task for the same chat, even if one is already in progress.
|
||||
|
||||
#### Problems
|
||||
- Duplicate summary work
|
||||
- Increased token usage
|
||||
- Race conditions in saved summary state
|
||||
- Potential data consistency issues
|
||||
|
||||
#### Expected Behavior
|
||||
Use per-chat locking to ensure only one summary task runs per chat at a time.
|
||||
|
||||
---
|
||||
|
||||
### 4. 🟡 MEDIUM: Native tool-output trimming is too aggressive
|
||||
|
||||
**Severity**: Medium
|
||||
**Impact**: Content accuracy in technical conversations
|
||||
|
||||
#### Description
|
||||
The tool-output trimming heuristics can rewrite or trim normal assistant messages if they contain patterns such as:
|
||||
- Code fences (triple backticks)
|
||||
- `Arguments:` text
|
||||
- `<tool_code>` tags
|
||||
|
||||
#### Problem
|
||||
This is risky in technical conversations and may alter valid assistant content unintentionally.
|
||||
|
||||
#### Expected Behavior
|
||||
Trimming logic should be more conservative and avoid modifying assistant messages that are not actually tool-output summaries.
|
||||
|
||||
---
|
||||
|
||||
### 5. 🟡 MEDIUM: `max_context_tokens = 0` has inconsistent semantics
|
||||
|
||||
**Severity**: Medium
|
||||
**Impact**: Determinism, configuration clarity
|
||||
|
||||
#### Description
|
||||
The setting `max_context_tokens = 0` behaves inconsistently across different code paths:
|
||||
- In some paths: behaves like "no threshold" (special mode, no compression)
|
||||
- In other paths: still triggers reduction/truncation logic
|
||||
|
||||
#### Problem
|
||||
Non-deterministic behavior makes the setting unpredictable and confusing for users.
|
||||
|
||||
#### Expected Behavior
|
||||
- Define clear semantics for `max_context_tokens = 0`
|
||||
- Apply consistently across all code paths
|
||||
- Document the intended behavior
|
||||
|
||||
---
|
||||
|
||||
### 6. 🔵 LOW: Corrupted Korean i18n string
|
||||
|
||||
**Severity**: Low
|
||||
**Impact**: User experience for Korean speakers
|
||||
|
||||
#### Description
|
||||
One translation string contains broken mixed-language text.
|
||||
|
||||
#### Expected Behavior
|
||||
Clean up the Korean translation string to be properly formatted and grammatically correct.
|
||||
|
||||
---
|
||||
|
||||
## Related / Broader Context
|
||||
|
||||
**Note from issue reporter**: The critical bug is not limited to tool-calling fields alone. Because compression deletes or replaces whole message objects, it can also drop other per-message fields such as:
|
||||
- Message-level `id`
|
||||
- `metadata`
|
||||
- `name`
|
||||
- Similar per-message attributes
|
||||
|
||||
So the issue is broader than native tool-calling: any integration relying on per-message metadata may also be affected when messages are trimmed or replaced.
|
||||
|
||||
---
|
||||
|
||||
## Reproduction Steps
|
||||
|
||||
1. Start a chat with a model using native tool calling
|
||||
2. Enable the async-context-compression filter
|
||||
3. Send a conversation long enough to trigger compression / summary generation
|
||||
4. Let the model perform multiple tool calls across several turns
|
||||
5. Continue the same chat after the filter has already compressed part of the history
|
||||
|
||||
**Expected**: Chat continues normally
|
||||
**Actual**: Chat can become desynchronized and fail with errors like `No tool call found for function call output with call_id ...`
|
||||
|
||||
**Control Test**:
|
||||
- With filter disabled: failure does not occur
|
||||
- With filter enabled: failure reproduces reliably
|
||||
|
||||
---
|
||||
|
||||
## Suggested Fix Direction
|
||||
|
||||
### High Priority (Blocks Issue #56)
|
||||
|
||||
1. **Preserve tool-calling atomicity**: Compress history in a way that never separates `assistant(tool_calls)` from its corresponding `tool` messages
|
||||
2. **Unify progress tracking**: Use a single, consistent coordinate system for `compressed_message_count` throughout
|
||||
3. **Add per-chat locking**: Ensure only one background summary task runs per chat at a time
|
||||
|
||||
### Medium Priority
|
||||
|
||||
4. **Conservative trimming**: Refine tool-output trimming heuristics to avoid altering valid assistant content
|
||||
5. **Define `max_context_tokens = 0` semantics**: Make behavior consistent and predictable
|
||||
6. **Fix i18n**: Clean up the corrupted Korean translation string
|
||||
|
||||
---
|
||||
|
||||
## Environment
|
||||
|
||||
- **Plugin**: async-context-compression
|
||||
- **OpenWebUI Version**: 0.8.9
|
||||
- **OS**: Ubuntu 24.04 LTS ARM64
|
||||
- **Reported by**: @dhaern
|
||||
- **Issue Date**: [Recently opened]
|
||||
|
||||
---
|
||||
|
||||
## References
|
||||
|
||||
- [GitHub Issue #56](https://github.com/Fu-Jie/openwebui-extensions/issues/56)
|
||||
- Plugin: `plugins/filters/async-context-compression/async_context_compression.py`
|
||||
@@ -0,0 +1,189 @@
|
||||
# Issue #56: 异步上下文压缩中的关键工具调用破坏和多个可靠性问题
|
||||
|
||||
## 概述
|
||||
本文档汇总了 [GitHub Issue #56](https://github.com/Fu-Jie/openwebui-extensions/issues/56) 中所有关于异步上下文压缩过滤器的已报告问题。
|
||||
|
||||
---
|
||||
|
||||
## 问题列表
|
||||
|
||||
### 1. 🔴 关键：原生工具调用历史可能被破坏
|
||||
|
||||
**严重级别**: 关键
|
||||
**影响范围**: 对话完整性
|
||||
|
||||
#### 描述
|
||||
压缩逻辑逐条删除消息，而不是把原生工具调用结构作为原子整体保留。这可能会破坏 assistant `tool_calls` 与其对应 `tool` 结果消息的关系。
|
||||
|
||||
#### 症状
|
||||
```
|
||||
No tool call found for function call output with call_id ...
|
||||
```
|
||||
|
||||
#### 根本原因
|
||||
- 包含 `tool_calls` 的 assistant 消息可能被删除，但其对应的 `tool` 结果消息仍保留
|
||||
- 这会产生孤立的工具输出，引用不存在的 `tool_call_id`
|
||||
- 模型/API 提供商会拒绝该请求，因为 `call_id` 不再匹配历史中的任何工具调用
|
||||
|
||||
#### 期望行为
|
||||
压缩必须把工具调用块当作原子整体对待：
|
||||
- `assistant(tool_calls)` 消息
|
||||
- 对应的 `tool` 结果消息
|
||||
- 可选的 assistant 跟进消息（消费工具结果）
|
||||
|
||||
这些消息的任何部分都不应被分割或部分删除。
|
||||
|
||||
---
|
||||
|
||||
### 2. 🟠 高优先级：压缩进度混淆了原始历史和压缩视图语义
|
||||
|
||||
**严重级别**: 高
|
||||
**影响范围**: 摘要进度一致性
|
||||
|
||||
#### 描述
|
||||
插件将 `compressed_message_count` 存储为原始对话历史的进度，但稍后从已压缩的对话视图重新计算。这混淆了同一字段的两个不同坐标系。
|
||||
|
||||
#### 问题
|
||||
- 原始历史进度（压缩前）
|
||||
- 压缩视图进度（压缩后）
|
||||
|
||||
这两个含义不一致，造成：
|
||||
- 摘要进度变得不一致
|
||||
- 摘要已存在后进度可能停滞
|
||||
- 后续更新用不同于存储值的坐标系测量
|
||||
|
||||
#### 期望行为
|
||||
进度跟踪必须在对话整个生命周期中使用单一、一致的坐标系。
|
||||
|
||||
---
|
||||
|
||||
### 3. 🟡 中等优先级：异步摘要生成没有每聊天锁
|
||||
|
||||
**严重级别**: 中等
|
||||
**影响范围**: 令牌使用、竞态条件
|
||||
|
||||
#### 描述
|
||||
每个响应都可能为同一聊天启动新的后台摘要任务，即使已有任务在进行中。
|
||||
|
||||
#### 问题
|
||||
- 摘要工作重复
|
||||
- 令牌使用增加
|
||||
- 已保存摘要状态出现竞态条件
|
||||
- 数据一致性问题
|
||||
|
||||
#### 期望行为
|
||||
使用每聊天锁机制确保每次只有一个摘要任务在该聊天中运行。
|
||||
|
||||
---
|
||||
|
||||
### 4. 🟡 中等优先级：原生工具输出裁剪太激进
|
||||
|
||||
**严重级别**: 中等
|
||||
**影响范围**: 技术对话的内容准确性
|
||||
|
||||
#### 描述
|
||||
工具输出裁剪启发式方法会重写或裁剪普通 assistant 消息，如果包含诸如以下模式：
|
||||
- 代码围栏（三个反引号）
|
||||
- `Arguments:` 文本
|
||||
- `<tool_code>` 标签
|
||||
|
||||
#### 问题
|
||||
这在技术对话中存在风险，可能无意中更改有效的 assistant 内容。
|
||||
|
||||
#### 期望行为
|
||||
裁剪逻辑应更保守，避免修改非工具输出摘要的 assistant 消息。
|
||||
|
||||
---
|
||||
|
||||
### 5. 🟡 中等优先级：`max_context_tokens = 0` 语义不一致
|
||||
|
||||
**严重级别**: 中等
|
||||
**影响范围**: 确定性、配置清晰度
|
||||
|
||||
#### 描述
|
||||
设置 `max_context_tokens = 0` 在不同代码路径中行为不一致：
|
||||
- 在某些路径中：像"无阈值"一样（特殊模式，无压缩）
|
||||
- 在其他路径中：仍然触发缩减/截断逻辑
|
||||
|
||||
#### 问题
|
||||
非确定性行为使设置变得不可预测和令人困惑。
|
||||
|
||||
#### 期望行为
|
||||
- 为 `max_context_tokens = 0` 定义清晰语义
|
||||
- 在所有代码路径中一致应用
|
||||
- 清楚地记录预期行为
|
||||
|
||||
---
|
||||
|
||||
### 6. 🔵 低优先级：破损的韩文 i18n 字符串
|
||||
|
||||
**严重级别**: 低
|
||||
**影响范围**: 韩文使用者的用户体验
|
||||
|
||||
#### 描述
|
||||
一个翻译字符串包含破损的混合语言文本。
|
||||
|
||||
#### 期望行为
|
||||
清理韩文翻译字符串，使其格式正确和语法正确。
|
||||
|
||||
---
|
||||
|
||||
## 相关/更广泛的上下文
|
||||
|
||||
**问题报告者附注**：关键错误不仅限于工具调用字段。由于压缩删除或替换整个消息对象，它还可能丢弃其他每消息字段，例如：
|
||||
- 消息级 `id`
|
||||
- `metadata`
|
||||
- `name`
|
||||
- 其他每消息属性
|
||||
|
||||
因此问题范围广于原生工具调用：任何依赖每消息元数据的集成在消息被裁剪或替换时也可能受影响。
|
||||
|
||||
---
|
||||
|
||||
## 复现步骤
|
||||
|
||||
1. 使用原生工具调用启动与模型的聊天
|
||||
2. 启用异步上下文压缩过滤器
|
||||
3. 发送足够长的对话以触发压缩/摘要生成
|
||||
4. 让模型在几个回合中执行多个工具调用
|
||||
5. 在过滤器已压缩部分历史后继续同一聊天
|
||||
|
||||
**期望**: 聊天继续正常运行
|
||||
**实际**: 聊天可能变得不同步并失败，出现错误如 `No tool call found for function call output with call_id ...`
|
||||
|
||||
**对照测试**:
|
||||
- 禁用过滤器：不出现失败
|
||||
- 启用过滤器：可靠地复现失败
|
||||
|
||||
---
|
||||
|
||||
## 建议的修复方向
|
||||
|
||||
### 高优先级（阻止 Issue #56）
|
||||
|
||||
1. **保护工具调用原子性**：以不分割 `assistant(tool_calls)` 与其对应 `tool` 消息的方式压缩历史
|
||||
2. **统一进度跟踪**：在整个过程中使用单一、一致的坐标系统追踪 `compressed_message_count`
|
||||
3. **添加每聊天锁**：确保每次只有一个后台摘要任务在该聊天中运行
|
||||
|
||||
### 中等优先级
|
||||
|
||||
4. **保守的裁剪**：精化工具输出裁剪启发式方法，避免更改有效 assistant 内容
|
||||
5. **定义 `max_context_tokens = 0` 语义**：使行为一致且可预测
|
||||
6. **修复 i18n**：清理破损的韩文翻译字符串
|
||||
|
||||
---
|
||||
|
||||
## 环境
|
||||
|
||||
- **插件**: async-context-compression
|
||||
- **OpenWebUI 版本**: 0.8.9
|
||||
- **操作系统**: Ubuntu 24.04 LTS ARM64
|
||||
- **报告者**: @dhaern
|
||||
- **问题日期**: [最近提交]
|
||||
|
||||
---
|
||||
|
||||
## 参考资源
|
||||
|
||||
- [GitHub Issue #56](https://github.com/Fu-Jie/openwebui-extensions/issues/56)
|
||||
- 插件: `plugins/filters/async-context-compression/async_context_compression.py`
|
||||
@@ -1,16 +1,13 @@
|
||||
# Async Context Compression Filter
|
||||
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.3.0 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.4.1 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
|
||||
This filter reduces token consumption in long conversations through intelligent summarization and message compression while keeping conversations coherent.
|
||||
|
||||
## What's new in 1.3.0
|
||||
## What's new in 1.4.1
|
||||
|
||||
- **Internationalization (i18n)**: Complete localization of user-facing messages across 9 languages (English, Chinese, Japanese, Korean, French, German, Spanish, Italian).
|
||||
- **Smart Status Display**: Added `token_usage_status_threshold` valve (default 80%) to intelligently control when token usage status is shown.
|
||||
- **Improved Performance**: Frontend language detection and logging are optimized to be completely non-blocking, maintaining lightning-fast TTFB.
|
||||
- **Copilot SDK Integration**: Automatically detects and skips compression for copilot_sdk based models to prevent conflicts.
|
||||
- **Configuration**: `debug_mode` is now set to `false` by default for a quieter production experience.
|
||||
- **Reverse-Unfolding Mechanism**: Accurately reconstructs the expanded native tool-calling sequence during the outlet phase to permanently fix coordinate drift and missing summaries for long tool-based conversations.
|
||||
- **Safer Tool Trimming**: Refactored `enable_tool_output_trimming` to strictly use atomic block groups for safe trimming, completely preventing JSON payload corruption.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,18 +1,15 @@
|
||||
# 异步上下文压缩过滤器
|
||||
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 1.3.0 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 1.4.1 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
|
||||
> **重要提示**：为了确保所有过滤器的可维护性和易用性，每个过滤器都应附带清晰、完整的文档，以确保其功能、配置和使用方法得到充分说明。
|
||||
|
||||
本过滤器通过智能摘要和消息压缩技术，在保持对话连贯性的同时，显著降低长对话的 Token 消耗。
|
||||
|
||||
## 1.3.0 版本更新
|
||||
## 1.4.1 版本更新
|
||||
|
||||
- **国际化 (i18n) 支持**: 完成了所有用户可见消息的本地化，现已原生支持 9 种语言（含中、英、日、韩及欧洲主要语言）。
|
||||
- **智能状态显示**: 新增 `token_usage_status_threshold` 阀门（默认 80%），可以智能控制何时显示 Token 用量状态，减少不必要的打扰。
|
||||
- **性能大幅优化**: 对前端语言检测和日志处理流程进行了非阻塞重构，完全不影响首字节响应时间（TTFB），保持毫秒级极速推流。
|
||||
- **Copilot SDK 兼容**: 自动检测并跳过基于 `copilot_sdk` 模型的上下文压缩，避免冲突。
|
||||
- **配置项调整**: 为了提供更安静的生产环境体验，`debug_mode` 现已默认设置为 `false`。
|
||||
- **逆向展开机制**: 引入 `_unfold_messages` 机制以在 `outlet` 阶段精确对齐坐标系，彻底解决了由于前端视图折叠导致长轮次工具调用对话出现进度漂移或跳过生成摘要的问题。
|
||||
- **更安全的工具内容裁剪**: 重构了 `enable_tool_output_trimming`，现在严格使用原子级分组进行安全的原生工具内容裁剪，替代了激进的正则表达式匹配，防止 JSON 载荷损坏。
|
||||
|
||||
---
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
BIN
plugins/filters/async-context-compression/image.png
Normal file
BIN
plugins/filters/async-context-compression/image.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 139 KiB |
@@ -0,0 +1,169 @@
|
||||
# Async Context Compression 核心故障分析与修复总结 (Issue #56)
|
||||
|
||||
Report: <https://github.com/Fu-Jie/openwebui-extensions/issues/56>
|
||||
|
||||
## 1. 问题分析
|
||||
|
||||
### 1.1 Critical: Tool-Calling 结构损坏
|
||||
|
||||
- **故障根源**: 插件在压缩历史消息时采用了“消息感知 (Message-Aware)”而非“结构感知 (Structure-Aware)”的策略。大模型的 `tool-calling` 依赖于 `assistant(tool_calls)` 与紧随其后的 `tool(s)` 消息的严格配对。
|
||||
- **后果**: 如果压缩导致只有 `tool_calls` 被总结，而其对应的 `tool` 结果仍留在上下文，将触发 `No tool call found` 致命错误。
|
||||
|
||||
### 1.2 High: 坐标系偏移导致进度错位
|
||||
|
||||
- **故障根源**: 插件此前使用 `len(messages)` 计算总结进度。由于总结后消息列表变短，旧的索引无法正确映射回原始历史坐标。
|
||||
- **后果**: 导致总结逻辑在对话进行中反复处理重叠的区间，或在某些边界条件下停止推进。
|
||||
|
||||
### 1.3 Medium: 并发竞态与元数据丢失
|
||||
|
||||
- **并发**: 缺乏针对 `chat_id` 的后台任务锁，导致并发请求下可能触发多个 LLM 总结任务。
|
||||
- **元数据**: 消息被折叠为总结块后，其原始的 `id`、`name` 和扩展 `metadata` 彻底消失，破坏了依赖这些指纹的第三方集成。
|
||||
|
||||
---
|
||||
|
||||
## 2. 修复方案 (核心重构)
|
||||
|
||||
### 2.1 引入原子消息组 (Atomic Grouping)
|
||||
|
||||
实现 `_get_atomic_groups` 算法，将 `assistant-tool-assistant` 的调用链识别并标记。确保这些组被**整体保留或整体移除**。
|
||||
|
||||
该算法应用于两处截断路径：
|
||||
|
||||
1. **inlet 阶段**（有 summary / 无 summary 两条路径均已覆盖）
|
||||
2. **outlet 后台 summary 任务**中，当 `middle_messages` 超出 summary model 上下文窗口需要截断时，同样使用原子组删除，防止在进入 LLM 总结前产生孤立的 tool result。（2026-03-09 补丁）
|
||||
|
||||
具体做法：
|
||||
|
||||
- `_get_atomic_groups(messages)` 会把消息扫描成多个“不可拆分单元”。
|
||||
- 当遇到 `assistant` 且带 `tool_calls` 时，开启一个原子组。
|
||||
- 后续所有 `tool` 消息都会被并入这个原子组。
|
||||
- 如果紧跟着出现消费工具结果的 assistant 跟进回复，也会并入同一个原子组。
|
||||
- 这样做之后，裁剪逻辑不再按“单条消息”删除，而是按“整组消息”删除。
|
||||
|
||||
这解决了 Issue #56 最核心的问题：
|
||||
|
||||
- 过去：可能删掉 `assistant(tool_calls)`，却留下 `tool` 结果
|
||||
- 现在：要么整组一起保留，要么整组一起移除
|
||||
|
||||
也就是说，发送给模型的历史上下文不再出现孤立的 `tool_call_id`。
|
||||
|
||||
### 2.1.1 Tail 边界对齐 (Atomic Boundary Alignment)
|
||||
|
||||
除了按组删除之外，还新增了 `_align_tail_start_to_atomic_boundary` 来修正“保留尾部”的起点。
|
||||
|
||||
原因是：即使 `compressed_message_count` 本身来自旧数据或原始计数，如果它刚好落在一个工具调用链中间，直接拿来做 `tail` 起点仍然会造成损坏。
|
||||
|
||||
修复步骤如下：
|
||||
|
||||
1. 先计算理论上的 `raw_start_index`
|
||||
2. 调用 `_align_tail_start_to_atomic_boundary(messages, raw_start_index, protected_prefix)`
|
||||
3. 如果该起点落在某个原子组内部，就自动回退到该组起始位置
|
||||
4. 用修正后的 `start_index` 重建 `tail_messages`
|
||||
|
||||
这个逻辑同时用于：
|
||||
|
||||
- `inlet` 中已存在 summary 时的 tail 重建
|
||||
- `outlet` 中计算 `target_compressed_count`
|
||||
- 后台 summary 任务里计算 `middle_messages` / `tail` 分界线
|
||||
|
||||
因此，修复并不只是“删除时按组删除”，而是连“边界落点”本身都改成结构感知。
|
||||
|
||||
### 2.2 实现单会话异步锁 (Chat Session Lock)
|
||||
|
||||
在 `Filter` 类中维护 `_chat_locks`。在 `outlet` 阶段，如果检测到已有后台任务持有该锁，则自动跳过当前请求，确保一个 `chat_id` 始终只有一个任务在运行。
|
||||
|
||||
具体流程：
|
||||
|
||||
1. `outlet` 先通过 `_get_chat_lock(chat_id)` 取得当前会话的锁对象
|
||||
2. 如果 `chat_lock.locked()` 为真，直接跳过本次后台总结任务
|
||||
3. 如果没有任务在运行，则创建 `_locked_summary_task(...)`
|
||||
4. `_locked_summary_task` 内部用 `async with lock:` 包裹真正的 `_check_and_generate_summary_async(...)`
|
||||
|
||||
这样修复后，同一个会话不会再并发发起多个 summary LLM 调用，也不会出现多个后台任务互相覆盖 `compressed_message_count` 或 summary 内容的情况。
|
||||
|
||||
### 2.3 元数据溯源 (Metadata Traceability)
|
||||
|
||||
重构总结数据的格式化流程：
|
||||
|
||||
- 提取消息 ID (`msg[id]`)、参与者名称 (`msg[name]`) 和关键元数据。
|
||||
- 将这些身份标识以 `[ID: xxx] [Name: yyy]` 的形式注入 LLM 的总结输入。
|
||||
- 增强总结提示词 (Prompt)，要求模型按 ID 引用重要行为。
|
||||
|
||||
这里的修复目的不是“恢复被压缩消息的原始对象”，而是尽量保留它们的身份痕迹，降低以下风险：
|
||||
|
||||
- 压缩后 summary 完全失去消息来源
|
||||
- 某段关键决策、工具结果或用户要求在总结中无法追溯
|
||||
- 依赖消息身份的后续分析或人工排查变得困难
|
||||
|
||||
当前实现方式是 `_format_messages_for_summary`：
|
||||
|
||||
- 把每条消息格式化为 `[序号] Role [ID: ...] [Name: ...] [Meta: ...]: content`
|
||||
- 多模态内容会先抽出文本部分再汇总
|
||||
- summary prompt 中明确要求模型保留关键 ID / Name 的可追踪性
|
||||
|
||||
这不能等价替代原始消息对象，但比“直接丢掉所有身份信息后只保留一段自然语言总结”安全很多。
|
||||
|
||||
### 2.4 `max_context_tokens = 0` 语义统一
|
||||
|
||||
Issue #56 里还有一个不太显眼但实际会影响行为的一致性问题：
|
||||
|
||||
- `inlet` 路径已经把 `max_context_tokens <= 0` 视为“无限制，不做裁剪”
|
||||
- 但后台 summary 任务里，之前仍会继续拿 `0` 参与 `estimated_input_tokens > max_context_tokens` 判断
|
||||
|
||||
这会造成前台请求和后台总结对同一配置的解释不一致。
|
||||
|
||||
修复后：
|
||||
|
||||
- `inlet` 与后台 summary 路径统一使用 `<= 0` 表示“no limit”
|
||||
- 当 `max_context_tokens <= 0` 时，后台任务会直接跳过 `middle_messages` 的截断逻辑
|
||||
- 并新增回归测试，确保该行为不会再次退化
|
||||
|
||||
这一步虽然不如 tool-calling 原子化那么显眼，但它解决了“配置含义前后不一致”的稳定性问题。
|
||||
|
||||
### 2.5 tool-output trimming 的风险收敛
|
||||
|
||||
Issue #56 提到原先的 tool-output trimming 可能误伤普通 assistant 内容。对此没有继续扩展一套更复杂的启发式规则，而是采用了更保守的收敛策略：
|
||||
|
||||
- `enable_tool_output_trimming` 默认保持 `False`
|
||||
- 当前 trimming 分支不再主动重写普通 assistant 内容
|
||||
|
||||
这意味着插件优先保证“不误伤正常消息”，而不是冒险做激进裁剪。对于这个 bug 修复阶段，这是一个刻意的稳定性优先决策。
|
||||
|
||||
### 2.6 修复顺序总结
|
||||
|
||||
从实现层面看，这次修复不是单点补丁，而是一组按顺序落下去的结构性改动：
|
||||
|
||||
1. 先把消息从“单条处理”升级为“原子组处理”
|
||||
2. 再把 tail / middle 的边界从“裸索引”升级为“结构感知边界”
|
||||
3. 再加每会话异步锁，堵住并发 summary 覆盖
|
||||
4. 再补 summary 输入格式，让被压缩历史仍保留可追踪身份信息
|
||||
5. 最后统一 `max_context_tokens = 0` 的语义，并加测试防回归
|
||||
|
||||
因此，Issue #56 的修复本质上是：
|
||||
|
||||
把这个过滤器从“按字符串和长度裁剪消息”重构成“按对话结构和上下文契约裁剪消息”。
|
||||
|
||||
---
|
||||
|
||||
## 3. 修复覆盖范围对照表
|
||||
|
||||
| # | 严重级别 | 问题 | 状态 |
|
||||
|---|----------|------|------|
|
||||
| 1 | **Critical** | tool-calling 消息被单条压缩 → `No tool call found` | ✅ inlet 两条路径均已原子化 |
|
||||
| 2 | **High** | `compressed_message_count` 坐标系混用 | ✅ outlet 始终在原始消息空间计算 |
|
||||
| 3 | **Medium** | 无 per-chat 异步锁 | ✅ `_chat_locks` + `asyncio.Lock()` |
|
||||
| 4 | **Medium** | tool-output 修剪过于激进 | ✅ 默认 `False`；循环体已置空 |
|
||||
| 5 | **Medium** | `max_context_tokens = 0` 语义不一致 | ✅ 统一 `<= 0` 表示"无限制" |
|
||||
| 6 | **Low** | 韩语 i18n 字符串混入俄文字符 | ✅ 已替换为纯韩文 |
|
||||
| 7 | **(后发现)** | summary 任务内截断不使用原子组 | ✅ 2026-03-09 补丁：改用 `_get_atomic_groups` |
|
||||
|
||||
## 4. 验证结论
|
||||
|
||||
- **inlet 路径**: `_get_atomic_groups` 贯穿 `inlet` 两条分支，以原子组为单位丢弃消息，永不产生孤立 tool result。
|
||||
- **summary 任务**: 超出上下文限制时，同样以原子组截断 `middle_messages`，保证进入 LLM 的输入完整性。
|
||||
- **并发控制**: `chat_lock.locked()` 确保同一 `chat_id` 同时只有一个总结任务运行。
|
||||
- **元数据**: `_format_messages_for_summary` 以 `[ID: xxx]` 形式保留原始消息身份标识。
|
||||
|
||||
## 5. 后置建议
|
||||
|
||||
该修复旨在将过滤器从“关键词总结”提升到“结构感知代理”的层面。在后续开发中，应继续保持对 OpenWebUI 原生消息指纹的尊重。
|
||||
@@ -0,0 +1,461 @@
|
||||
import asyncio
|
||||
import importlib.util
|
||||
import os
|
||||
import sys
|
||||
import types
|
||||
import unittest
|
||||
|
||||
|
||||
PLUGIN_PATH = os.path.join(os.path.dirname(__file__), "async_context_compression.py")
|
||||
MODULE_NAME = "async_context_compression_under_test"
|
||||
|
||||
|
||||
def _ensure_module(name: str) -> types.ModuleType:
|
||||
module = sys.modules.get(name)
|
||||
if module is None:
|
||||
module = types.ModuleType(name)
|
||||
sys.modules[name] = module
|
||||
return module
|
||||
|
||||
|
||||
def _install_openwebui_stubs() -> None:
|
||||
_ensure_module("open_webui")
|
||||
_ensure_module("open_webui.utils")
|
||||
chat_module = _ensure_module("open_webui.utils.chat")
|
||||
_ensure_module("open_webui.models")
|
||||
users_module = _ensure_module("open_webui.models.users")
|
||||
models_module = _ensure_module("open_webui.models.models")
|
||||
chats_module = _ensure_module("open_webui.models.chats")
|
||||
main_module = _ensure_module("open_webui.main")
|
||||
_ensure_module("fastapi")
|
||||
fastapi_requests = _ensure_module("fastapi.requests")
|
||||
|
||||
async def generate_chat_completion(*args, **kwargs):
|
||||
return {}
|
||||
|
||||
class DummyUsers:
|
||||
pass
|
||||
|
||||
class DummyModels:
|
||||
@staticmethod
|
||||
def get_model_by_id(model_id):
|
||||
return None
|
||||
|
||||
class DummyChats:
|
||||
@staticmethod
|
||||
def get_chat_by_id(chat_id):
|
||||
return None
|
||||
|
||||
class DummyRequest:
|
||||
pass
|
||||
|
||||
chat_module.generate_chat_completion = generate_chat_completion
|
||||
users_module.Users = DummyUsers
|
||||
models_module.Models = DummyModels
|
||||
chats_module.Chats = DummyChats
|
||||
main_module.app = object()
|
||||
fastapi_requests.Request = DummyRequest
|
||||
|
||||
|
||||
_install_openwebui_stubs()
|
||||
spec = importlib.util.spec_from_file_location(MODULE_NAME, PLUGIN_PATH)
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
sys.modules[MODULE_NAME] = module
|
||||
assert spec.loader is not None
|
||||
spec.loader.exec_module(module)
|
||||
module.Filter._init_database = lambda self: None
|
||||
|
||||
|
||||
class TestAsyncContextCompression(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.filter = module.Filter()
|
||||
|
||||
def test_inlet_logs_tool_trimming_outcome_when_no_oversized_outputs(self):
|
||||
self.filter.valves.show_debug_log = True
|
||||
self.filter.valves.enable_tool_output_trimming = True
|
||||
|
||||
logged_messages = []
|
||||
|
||||
async def fake_log(message, log_type="info", event_call=None):
|
||||
logged_messages.append(message)
|
||||
|
||||
async def fake_user_context(__user__, __event_call__):
|
||||
return {"user_language": "en-US"}
|
||||
|
||||
async def fake_event_call(_payload):
|
||||
return True
|
||||
|
||||
self.filter._log = fake_log
|
||||
self.filter._get_user_context = fake_user_context
|
||||
self.filter._get_chat_context = lambda body, metadata=None: {
|
||||
"chat_id": "",
|
||||
"message_id": "",
|
||||
}
|
||||
self.filter._get_latest_summary = lambda chat_id: None
|
||||
|
||||
body = {
|
||||
"params": {"function_calling": "native"},
|
||||
"messages": [
|
||||
{
|
||||
"role": "assistant",
|
||||
"tool_calls": [{"id": "call_1", "type": "function"}],
|
||||
"content": "",
|
||||
},
|
||||
{"role": "tool", "content": "short result"},
|
||||
{"role": "assistant", "content": "Final answer"},
|
||||
],
|
||||
}
|
||||
|
||||
asyncio.run(self.filter.inlet(body, __event_call__=fake_event_call))
|
||||
|
||||
self.assertTrue(
|
||||
any("Tool trimming check:" in message for message in logged_messages)
|
||||
)
|
||||
self.assertTrue(
|
||||
any(
|
||||
"no oversized native tool outputs were found" in message
|
||||
for message in logged_messages
|
||||
)
|
||||
)
|
||||
|
||||
def test_inlet_logs_tool_trimming_skip_reason_when_disabled(self):
|
||||
self.filter.valves.show_debug_log = True
|
||||
self.filter.valves.enable_tool_output_trimming = False
|
||||
|
||||
logged_messages = []
|
||||
|
||||
async def fake_log(message, log_type="info", event_call=None):
|
||||
logged_messages.append(message)
|
||||
|
||||
async def fake_user_context(__user__, __event_call__):
|
||||
return {"user_language": "en-US"}
|
||||
|
||||
async def fake_event_call(_payload):
|
||||
return True
|
||||
|
||||
self.filter._log = fake_log
|
||||
self.filter._get_user_context = fake_user_context
|
||||
self.filter._get_chat_context = lambda body, metadata=None: {
|
||||
"chat_id": "",
|
||||
"message_id": "",
|
||||
}
|
||||
self.filter._get_latest_summary = lambda chat_id: None
|
||||
|
||||
body = {"messages": [], "params": {"function_calling": "native"}}
|
||||
|
||||
asyncio.run(self.filter.inlet(body, __event_call__=fake_event_call))
|
||||
|
||||
self.assertTrue(
|
||||
any("Tool trimming skipped: tool trimming disabled" in message for message in logged_messages)
|
||||
)
|
||||
|
||||
def test_normalize_native_tool_call_ids_keeps_links_aligned(self):
|
||||
long_tool_call_id = "call_abcdefghijklmnopqrstuvwxyz_1234567890abcd"
|
||||
messages = [
|
||||
{
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": long_tool_call_id,
|
||||
"type": "function",
|
||||
"function": {"name": "search", "arguments": "{}"},
|
||||
}
|
||||
],
|
||||
"content": "",
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": long_tool_call_id,
|
||||
"content": "tool result",
|
||||
},
|
||||
]
|
||||
|
||||
normalized_count = self.filter._normalize_native_tool_call_ids(messages)
|
||||
|
||||
normalized_id = messages[0]["tool_calls"][0]["id"]
|
||||
self.assertEqual(normalized_count, 1)
|
||||
self.assertLessEqual(len(normalized_id), 40)
|
||||
self.assertNotEqual(normalized_id, long_tool_call_id)
|
||||
self.assertEqual(messages[1]["tool_call_id"], normalized_id)
|
||||
|
||||
def test_trim_native_tool_outputs_restores_real_behavior(self):
|
||||
messages = [
|
||||
{
|
||||
"role": "assistant",
|
||||
"tool_calls": [{"id": "call_1", "type": "function"}],
|
||||
"content": "",
|
||||
},
|
||||
{"role": "tool", "content": "x" * 1600},
|
||||
{"role": "assistant", "content": "Final answer"},
|
||||
]
|
||||
|
||||
trimmed_count = self.filter._trim_native_tool_outputs(messages, "en-US")
|
||||
|
||||
self.assertEqual(trimmed_count, 1)
|
||||
self.assertEqual(messages[1]["content"], "... [Content collapsed] ...")
|
||||
self.assertTrue(messages[1]["metadata"]["is_trimmed"])
|
||||
self.assertTrue(messages[2]["metadata"]["tool_outputs_trimmed"])
|
||||
self.assertIn("Final answer", messages[2]["content"])
|
||||
self.assertIn("Tool outputs trimmed", messages[2]["content"])
|
||||
|
||||
def test_trim_native_tool_outputs_supports_embedded_tool_call_cards(self):
|
||||
messages = [
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": (
|
||||
'<details type="tool_calls" done="true" id="call-1" '
|
||||
'name="execute_code" arguments=""{}"" '
|
||||
f'result=""{"x" * 1600}"">\n'
|
||||
"<summary>Tool Executed</summary>\n"
|
||||
"</details>\n"
|
||||
"Final answer"
|
||||
),
|
||||
}
|
||||
]
|
||||
|
||||
trimmed_count = self.filter._trim_native_tool_outputs(messages, "en-US")
|
||||
|
||||
self.assertEqual(trimmed_count, 1)
|
||||
self.assertIn(
|
||||
'result=""... [Content collapsed] ...""',
|
||||
messages[0]["content"],
|
||||
)
|
||||
self.assertNotIn("x" * 200, messages[0]["content"])
|
||||
self.assertTrue(messages[0]["metadata"]["tool_outputs_trimmed"])
|
||||
|
||||
def test_function_calling_mode_reads_params_fallback(self):
|
||||
self.assertEqual(
|
||||
self.filter._get_function_calling_mode(
|
||||
{"params": {"function_calling": "native"}}
|
||||
),
|
||||
"native",
|
||||
)
|
||||
|
||||
def test_function_calling_mode_infers_native_from_message_shape(self):
|
||||
self.assertEqual(
|
||||
self.filter._get_function_calling_mode(
|
||||
{
|
||||
"messages": [
|
||||
{
|
||||
"role": "assistant",
|
||||
"tool_calls": [{"id": "call_1", "type": "function"}],
|
||||
"content": "",
|
||||
},
|
||||
{"role": "tool", "content": "tool result"},
|
||||
]
|
||||
}
|
||||
),
|
||||
"native",
|
||||
)
|
||||
|
||||
def test_trim_native_tool_outputs_handles_pending_tool_chain(self):
|
||||
messages = [
|
||||
{
|
||||
"role": "assistant",
|
||||
"tool_calls": [{"id": "call_1", "type": "function"}],
|
||||
"content": "",
|
||||
},
|
||||
{"role": "tool", "content": "x" * 1600},
|
||||
]
|
||||
|
||||
trimmed_count = self.filter._trim_native_tool_outputs(messages, "en-US")
|
||||
|
||||
self.assertEqual(trimmed_count, 1)
|
||||
self.assertEqual(messages[1]["content"], "... [Content collapsed] ...")
|
||||
self.assertTrue(messages[1]["metadata"]["is_trimmed"])
|
||||
|
||||
def test_target_progress_uses_original_history_coordinates(self):
|
||||
self.filter.valves.keep_last = 2
|
||||
summary_message = self.filter._build_summary_message(
|
||||
"older summary", "en-US", 6
|
||||
)
|
||||
messages = [
|
||||
{"role": "system", "content": "System prompt"},
|
||||
summary_message,
|
||||
{"role": "user", "content": "Question 1"},
|
||||
{"role": "assistant", "content": "Answer 1"},
|
||||
{"role": "user", "content": "Question 2"},
|
||||
{"role": "assistant", "content": "Answer 2"},
|
||||
]
|
||||
|
||||
self.assertEqual(self.filter._get_original_history_count(messages), 10)
|
||||
self.assertEqual(self.filter._calculate_target_compressed_count(messages), 8)
|
||||
|
||||
def test_load_full_chat_messages_rebuilds_active_history_branch(self):
|
||||
class FakeChats:
|
||||
@staticmethod
|
||||
def get_chat_by_id(chat_id):
|
||||
return types.SimpleNamespace(
|
||||
chat={
|
||||
"history": {
|
||||
"currentId": "m3",
|
||||
"messages": {
|
||||
"m1": {
|
||||
"id": "m1",
|
||||
"role": "user",
|
||||
"content": "Question",
|
||||
},
|
||||
"m2": {
|
||||
"id": "m2",
|
||||
"role": "assistant",
|
||||
"content": "Tool call",
|
||||
"tool_calls": [{"id": "call_1"}],
|
||||
"parentId": "m1",
|
||||
},
|
||||
"m3": {
|
||||
"id": "m3",
|
||||
"role": "tool",
|
||||
"content": "Tool result",
|
||||
"tool_call_id": "call_1",
|
||||
"parentId": "m2",
|
||||
},
|
||||
},
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
original_chats = module.Chats
|
||||
module.Chats = FakeChats
|
||||
try:
|
||||
messages = self.filter._load_full_chat_messages("chat-1")
|
||||
finally:
|
||||
module.Chats = original_chats
|
||||
|
||||
self.assertEqual([message["id"] for message in messages], ["m1", "m2", "m3"])
|
||||
self.assertEqual(messages[2]["role"], "tool")
|
||||
|
||||
def test_outlet_unfolds_compact_tool_details_view(self):
|
||||
compact_messages = [
|
||||
{"role": "user", "content": "U1"},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": (
|
||||
'<details type="tool_calls" done="true" id="call-1" '
|
||||
'name="search_notes" arguments=""{}"" '
|
||||
f'result=""{"x" * 3000}"">\n'
|
||||
"<summary>Tool Executed</summary>\n"
|
||||
"</details>\n"
|
||||
"Answer 1"
|
||||
),
|
||||
},
|
||||
{"role": "user", "content": "U2"},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": (
|
||||
'<details type="tool_calls" done="true" id="call-2" '
|
||||
'name="merge_notes" arguments=""{}"" '
|
||||
f'result=""{"y" * 4000}"">\n'
|
||||
"<summary>Tool Executed</summary>\n"
|
||||
"</details>\n"
|
||||
"Answer 2"
|
||||
),
|
||||
},
|
||||
]
|
||||
|
||||
async def fake_user_context(__user__, __event_call__):
|
||||
return {"user_language": "en-US"}
|
||||
|
||||
async def noop_log(*args, **kwargs):
|
||||
return None
|
||||
|
||||
create_task_called = False
|
||||
|
||||
def fake_create_task(coro):
|
||||
nonlocal create_task_called
|
||||
create_task_called = True
|
||||
coro.close()
|
||||
return None
|
||||
|
||||
self.filter._get_user_context = fake_user_context
|
||||
self.filter._get_chat_context = lambda body, metadata=None: {
|
||||
"chat_id": "chat-1",
|
||||
"message_id": "msg-1",
|
||||
}
|
||||
self.filter._should_skip_compression = lambda body, model: False
|
||||
self.filter._log = noop_log
|
||||
|
||||
# Set a low threshold so the task is guaranteed to trigger
|
||||
self.filter.valves.compression_threshold_tokens = 100
|
||||
|
||||
original_create_task = asyncio.create_task
|
||||
asyncio.create_task = fake_create_task
|
||||
try:
|
||||
asyncio.run(
|
||||
self.filter.outlet(
|
||||
{"model": "test-model", "messages": compact_messages},
|
||||
__event_call__=None,
|
||||
)
|
||||
)
|
||||
finally:
|
||||
asyncio.create_task = original_create_task
|
||||
|
||||
self.assertTrue(create_task_called)
|
||||
|
||||
def test_summary_save_progress_matches_truncated_input(self):
|
||||
self.filter.valves.keep_first = 1
|
||||
self.filter.valves.keep_last = 1
|
||||
self.filter.valves.summary_model = "fake-summary-model"
|
||||
self.filter.valves.summary_model_max_context = 0
|
||||
|
||||
captured = {}
|
||||
events = []
|
||||
|
||||
async def mock_emitter(event):
|
||||
events.append(event)
|
||||
|
||||
async def mock_summary_llm(
|
||||
previous_summary,
|
||||
new_conversation_text,
|
||||
body,
|
||||
user_data,
|
||||
__event_call__,
|
||||
):
|
||||
return "new summary"
|
||||
|
||||
def mock_save_summary(chat_id, summary, compressed_count):
|
||||
captured["chat_id"] = chat_id
|
||||
captured["summary"] = summary
|
||||
captured["compressed_count"] = compressed_count
|
||||
|
||||
async def noop_log(*args, **kwargs):
|
||||
return None
|
||||
|
||||
self.filter._log = noop_log
|
||||
self.filter._call_summary_llm = mock_summary_llm
|
||||
self.filter._save_summary = mock_save_summary
|
||||
self.filter._get_model_thresholds = lambda model_id: {
|
||||
"max_context_tokens": 3500
|
||||
}
|
||||
self.filter._calculate_messages_tokens = lambda messages: len(messages) * 1000
|
||||
self.filter._count_tokens = lambda text: 1000
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "System prompt"},
|
||||
{"role": "user", "content": "Question 1"},
|
||||
{"role": "assistant", "content": "Answer 1"},
|
||||
{"role": "user", "content": "Question 2"},
|
||||
{"role": "assistant", "content": "Answer 2"},
|
||||
{"role": "user", "content": "Question 3"},
|
||||
]
|
||||
|
||||
asyncio.run(
|
||||
self.filter._generate_summary_async(
|
||||
messages=messages,
|
||||
chat_id="chat-1",
|
||||
body={"model": "fake-summary-model"},
|
||||
user_data={"id": "user-1"},
|
||||
target_compressed_count=5,
|
||||
lang="en-US",
|
||||
__event_emitter__=mock_emitter,
|
||||
__event_call__=None,
|
||||
)
|
||||
)
|
||||
|
||||
self.assertEqual(captured["chat_id"], "chat-1")
|
||||
self.assertEqual(captured["summary"], "new summary")
|
||||
self.assertEqual(captured["compressed_count"], 2)
|
||||
self.assertTrue(any(event["type"] == "status" for event in events))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
24
plugins/filters/async-context-compression/v1.4.0.md
Normal file
24
plugins/filters/async-context-compression/v1.4.0.md
Normal file
@@ -0,0 +1,24 @@
|
||||
[](https://openwebui.com/posts/async_context_compression_b1655bc8)
|
||||
|
||||
## Overview
|
||||
|
||||
This release focuses on improving the structural integrity of chat history when using function-calling models and enhancing task reliability through concurrent task management. It introduces "Atomic Message Grouping" to prevent chat context corruption and a session-based locking mechanism to ensure stable background operations.
|
||||
|
||||
**[📖 README](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/async-context-compression/README.md)**
|
||||
|
||||
## New Features
|
||||
|
||||
- **Atomic Message Grouping**: A new structure-aware logic that identifies and groups `assistant-tool-tool-assistant` calling sequences. This ensures that tool results are never orphaned from their calls during compression.
|
||||
- **Tail Boundary Alignment**: Automatically corrects truncation indices to ensure the recent context "tail" starts at a valid message boundary, preventing partial tool-calling sequences from being sent to the LLM.
|
||||
- **Chat Session Locking**: Implements a per-chat-id asynchronous lock to prevent multiple summary tasks from running concurrently for the same session, reducing redundant LLM calls and race conditions.
|
||||
- **Metadata Traceability**: Summarization inputs now include message IDs, participant names, and key metadata labels, allowing the summary model to maintain better traceability in its output.
|
||||
|
||||
## Bug Fixes
|
||||
|
||||
- **Fixed "No tool call found" Errors**: By enforcing atomic grouping, the filter no longer truncates the context in a way that separates tool calls from their results.
|
||||
- **Improved Progress Calculation**: Fixed an issue where summarizing messages would cause the progress tracking to drift due to shifting list indices.
|
||||
- **Prevented Duplicate Summary Tasks**: The new locking mechanism ensures that only one background summary process is active per session.
|
||||
|
||||
## Related Issues
|
||||
|
||||
- **[#56](https://github.com/Fu-Jie/openwebui-extensions/issues/56)**: Tool-Calling context corruption and concurrent summary tasks.
|
||||
20
plugins/filters/async-context-compression/v1.4.0_CN.md
Normal file
20
plugins/filters/async-context-compression/v1.4.0_CN.md
Normal file
@@ -0,0 +1,20 @@
|
||||
[](https://openwebui.com/posts/async_context_compression_b1655bc8)
|
||||
|
||||
本次发布重点优化了在使用工具调用（Function Calling）模型时对话历史的结构完整性，并通过并发任务管理增强了系统的可靠性。新版本引入了“原子消息组”逻辑以防止上下文损坏，并增加了会话级锁定机制以确保后台任务的稳定运行。
|
||||
|
||||
## 新功能
|
||||
|
||||
- **原子消息组 (Atomic Grouping)**: 引入结构感知的消息处理逻辑，能够识别并成组处理 `assistant-tool-tool-assistant` 调用序列。这确保了在压缩过程中，工具结果永远不会与其调用指令分离。
|
||||
- **尾部边界自动对齐**: 自动修正截断索引，确保保留的“尾部”上下文从合法的消息边界开始，防止将残缺的工具调用序列发送给大模型。
|
||||
- **会话级异步锁**: 为每个 `chat_id` 实现异步锁，防止同一会话并发触发多个总结任务，减少冗余的 LLM 调用并消除竞态条件。
|
||||
- **元数据溯源增强**: 总结输入现在包含消息 ID、参与者名称和关键元数据标签，使总结模型能够在其输出中保持更好的可追踪性。
|
||||
|
||||
## 问题修复
|
||||
|
||||
- **彻底解决 "No tool call found" 错误**: 通过强制执行原子分组，过滤器不再会以分离工具调用及其结果的方式截断上下文。
|
||||
- **优化进度计算**: 修复了总结消息后由于列表索引偏移导致进度跟踪漂移的问题。
|
||||
- **防止重复总结任务**: 新的锁定机制确保每个会话在同一时间只有一个后台总结进程在运行。
|
||||
|
||||
## 相关 Issue
|
||||
|
||||
- **[#56](https://github.com/Fu-Jie/openwebui-extensions/issues/56)**: 修复工具调用上下文损坏及并发总结任务冲突问题。
|
||||
17
plugins/filters/async-context-compression/v1.4.1.md
Normal file
17
plugins/filters/async-context-compression/v1.4.1.md
Normal file
@@ -0,0 +1,17 @@
|
||||
[](https://openwebui.com/f/fujie/async_context_compression)
|
||||
|
||||
## Overview
|
||||
|
||||
This release addresses the critical progress coordinate drift issue in OpenWebUI's `outlet` phase, ensuring robust summarization for long tool-calling conversations.
|
||||
|
||||
[View on GitHub](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/async-context-compression/README.md)
|
||||
|
||||
- **New Features**
|
||||
- **Reverse-Unfolding Mechanism**: Accurately reconstructs the expanded native tool-calling sequence during the outlet phase to permanently fix coordinate drift and missing summaries for long tool-based conversations.
|
||||
- **Safer Tool Trimming**: Refactored `enable_tool_output_trimming` to strictly use atomic block groups for safe trimming, completely preventing JSON payload corruption.
|
||||
|
||||
- **Bug Fixes**
|
||||
- Fixed coordinate drift where `compressed_message_count` could lose track due to OpenWebUI's frontend view truncating tool calls.
|
||||
|
||||
- **Related Issues**
|
||||
- Closes #56
|
||||
@@ -1,81 +1,90 @@
|
||||
# Markdown Normalizer Filter
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.2.8 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
|
||||
**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 1.2.7 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
|
||||
|
||||
A content normalizer filter for Open WebUI that fixes common Markdown formatting issues in LLM outputs. It ensures that code blocks, LaTeX formulas, Mermaid diagrams, and other Markdown elements are rendered correctly.
|
||||
A powerful, context-aware content normalizer filter for Open WebUI designed to fix common Markdown formatting issues in LLM outputs. It ensures that code blocks, LaTeX formulas, Mermaid diagrams, and other structural Markdown elements are rendered flawlessly, without destroying valid technical content.
|
||||
|
||||
> 🏆 **Featured by OpenWebUI Official** — This plugin was recommended in the official OpenWebUI Community Newsletter: [January 28, 2026](https://openwebui.com/blog/newsletter-january-28-2026)
|
||||
|
||||
## 🔥 What's New in v1.2.7
|
||||
[English](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README.md) | [简体中文](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README_CN.md)
|
||||
|
||||
* **LaTeX Formula Protection**: Enhanced escape character cleaning to protect LaTeX commands like `\times`, `\nu`, and `\theta` from being corrupted.
|
||||
* **Expanded i18n Support**: Now supports 12 languages with automatic detection and fallback.
|
||||
* **Valves Optimization**: Optimized configuration descriptions to be English-only for better consistency.
|
||||
* **Bug Fixes**:
|
||||
* Resolved [Issue #49](https://github.com/Fu-Jie/openwebui-extensions/issues/49): Fixed a bug where consecutive bold parts on the same line caused spaces between them to be removed.
|
||||
* Fixed a `NameError` in the plugin code that caused test collection failures.
|
||||
---
|
||||
|
||||
## 🔥 What's New in v1.2.8
|
||||
* **Safe-by-Default Strategy**: The `enable_escape_fix` feature is now **disabled by default**. This prevents unwanted modifications to valid technical text like Windows file paths (`C:\new\test`) or complex LaTeX formulas.
|
||||
* **LaTeX Parsing Fix**: Improved the logic for identifying display math (`$$ ... $$`). Fixed a bug where LaTeX commands starting with `\n` (like `\nabla`) were incorrectly treated as newlines.
|
||||
* **Reliability Enhancement**: Complete error fallback mechanism. Guarantees 0% data loss during processing.
|
||||
* **Inline Code Protection**: Upgraded escaping logic to protect inline code blocks (`` `...` ``).
|
||||
* **Code Block Escaping Control**: The `enable_escape_fix_in_code_blocks` Valve now correctly targets broken newlines inside code blocks (perfect for fixing flat SQL queries) when enabled.
|
||||
* **Privacy Optimization**: `show_debug_log` now defaults to `False` to prevent console noise.
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Why do you need this plugin? (What does it do?)
|
||||
|
||||
Language Models (LLMs) often generate malformed Markdown due to tokenization artifacts, aggressive escaping, or hallucinated formatting. If you've ever seen:
|
||||
- A `mermaid` diagram fail to render because of missing quotes around labels.
|
||||
- A SQL block stuck on a single line because `\n` was output literally instead of a real newline.
|
||||
- A `<details>` block break the entire chat rendering because of missing newlines.
|
||||
- A LaTeX formula fail because the LLM used `\[` instead of `$$`.
|
||||
|
||||
**This plugin automatically intercepts the LLM's raw output, analyzes its structure, and surgically repairs these formatting errors in real-time before they reach your browser.**
|
||||
|
||||
## ✨ Comprehensive Feature List
|
||||
|
||||
### 1. Advanced Structural Protections (Context-Aware)
|
||||
Before making any changes, the plugin builds a semantic map of the text to protect your technical content:
|
||||
- **Code Block Protection**: Skips formatting inside ` ``` ` code blocks by default to protect code logic.
|
||||
- **Inline Code Protection**: Recognizes `` `code` `` snippets and protects regular expressions and file paths (e.g., `C:\Windows`) from being incorrectly unescaped.
|
||||
- **LaTeX Protection**: Identifies inline (`$`) and block (`$$`) formulas to prevent modifying critical math commands like `\times`, `\theta`, or `\nu`.
|
||||
|
||||
### 2. Auto-Healing Transformations
|
||||
- **Details Tag Normalization**: `<details>` blocks (often used for Chain of Thought) require strict spacing to render correctly. The plugin automatically injects blank lines after `</details>` and self-closing `<details />` tags.
|
||||
- **Mermaid Syntax Fixer**: One of the most common LLM errors is omitting quotes in Mermaid diagrams (e.g., `A --> B(Some text)`). This plugin parses the Mermaid syntax and auto-quotes labels and citations to guarantee the graph renders.
|
||||
- **Emphasis Spacing Fix**: Fixes formatting-breaking extra spaces inside bold/italic markers (e.g., `** text **` becomes `**text**`) while cleverly ignoring math expressions like `2 * 3 * 4`.
|
||||
- **Intelligent Escape Character Cleanup**: Removes excessive literal `\n` and `\t` generated by some models and converts them to actual structural newlines (only in safe text areas).
|
||||
- **LaTeX Standardization**: Automatically upgrades old-school LaTeX delimiters (`\[...\]` and `\(...\)`) to modern Markdown standards (`$$...$$` and `$ ... $`).
|
||||
- **Thought Tag Unification**: Standardizes various model thought outputs (`<think>`, `<thinking>`) into a unified `<thought>` tag.
|
||||
- **Broken Code Block Repair**: Fixes indentation issues, repairs mangled language prefixes (e.g., ` ```python`), and automatically closes unclosed code blocks if a generation was cut off.
|
||||
- **List & Table Formatting**: Injects missing newlines to repair broken numbered lists and adds missing closing pipes (`|`) to tables.
|
||||
- **XML Artifact Cleanup**: Silently removes leftover `<antArtifact>` or `<antThinking>` tags often leaked by Claude models.
|
||||
|
||||
### 3. Reliability & Safety
|
||||
- **100% Rollback Guarantee**: If any normalization logic fails or crashes, the plugin catches the error and silently returns the exact original text, ensuring your chat never breaks.
|
||||
|
||||
## 🌐 Multilingual Support
|
||||
|
||||
Supports automatic interface and status switching for the following languages:
|
||||
The plugin UI and status notifications automatically switch based on your language:
|
||||
`English`, `简体中文`, `繁體中文 (香港)`, `繁體中文 (台灣)`, `한국어`, `日本語`, `Français`, `Deutsch`, `Español`, `Italiano`, `Tiếng Việt`, `Bahasa Indonesia`.
|
||||
|
||||
## ✨ Core Features
|
||||
|
||||
* **Details Tag Normalization**: Ensures proper spacing for `<details>` tags (used for thought chains). Adds a blank line after `</details>` and ensures a newline after self-closing `<details />` tags to prevent rendering issues.
|
||||
* **Emphasis Spacing Fix**: Fixes extra spaces inside emphasis markers (e.g., `** text **` -> `**text**`) which can cause rendering failures. Includes safeguards to protect math expressions (e.g., `2 * 3 * 4`) and list variables.
|
||||
* **Mermaid Syntax Fix**: Automatically fixes common Mermaid syntax errors, such as unquoted node labels (including multi-line labels and citations) and unclosed subgraphs. **New in v1.1.2**: Comprehensive protection for edge labels (text on connecting lines) across all link types (solid, dotted, thick).
|
||||
* **Frontend Console Debugging**: Supports printing structured debug logs directly to the browser console (F12) for easier troubleshooting.
|
||||
* **Code Block Formatting**: Fixes broken code block prefixes, suffixes, and indentation.
|
||||
* **LaTeX Normalization**: Standardizes LaTeX formula delimiters (`\[` -> `$$`, `\(` -> `$`).
|
||||
* **Thought Tag Normalization**: Unifies thought tags (`<think>`, `<thinking>` -> `<thought>`).
|
||||
* **Escape Character Fix**: Cleans up excessive escape characters (`\\n`, `\\t`).
|
||||
* **List Formatting**: Ensures proper newlines in list items.
|
||||
* **Heading Fix**: Adds missing spaces in headings (`#Heading` -> `# Heading`).
|
||||
* **Table Fix**: Adds missing closing pipes in tables.
|
||||
* **XML Cleanup**: Removes leftover XML artifacts.
|
||||
|
||||
## How to Use 🛠️
|
||||
|
||||
1. Install the plugin in Open WebUI.
|
||||
2. Enable the filter globally or for specific models.
|
||||
3. Configure the enabled fixes in the **Valves** settings.
|
||||
4. (Optional) **Show Debug Log** is enabled by default in Valves. This prints structured logs to the browser console (F12).
|
||||
> [!WARNING]
|
||||
> As this is an initial version, some "negative fixes" might occur (e.g., breaking valid Markdown). If you encounter issues, please check the console logs, copy the "Original" vs "Normalized" content, and submit an issue.
|
||||
2. Enable the filter globally or assign it to specific models (highly recommended for models with poor formatting).
|
||||
3. Tune the specific fixes you want via the **Valves** settings.
|
||||
|
||||
## Configuration (Valves) ⚙️
|
||||
|
||||
| Parameter | Default | Description |
|
||||
| :--- | :--- | :--- |
|
||||
| `priority` | `50` | Filter priority. Higher runs later (recommended after other filters). |
|
||||
| `enable_escape_fix` | `True` | Fix excessive escape characters (`\n`, `\t`, etc.). |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | Apply escape fix inside code blocks (may affect valid code). |
|
||||
| `enable_thought_tag_fix` | `True` | Normalize thought tags (`</thought>`). |
|
||||
| `enable_details_tag_fix` | `True` | Normalize `<details>` tags and add safe spacing. |
|
||||
| `enable_code_block_fix` | `True` | Fix code block formatting (indentation/newlines). |
|
||||
| `enable_latex_fix` | `True` | Normalize LaTeX delimiters (`\[` -> `$$`, `\(` -> `$`). |
|
||||
| `priority` | `50` | Filter priority. Higher runs later (recommended to run this after all other content filters). |
|
||||
| `enable_escape_fix` | `False` | Convert excessive literal escape characters (`\n`, `\t`) to real spacing. (Default: False for safety). |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | **Pro-tip**: Turn this ON if your SQL/HTML code blocks are constantly printing on a single line. Turn OFF for Python/C++. |
|
||||
| `enable_thought_tag_fix` | `True` | Normalize `<think>` tags. |
|
||||
| `enable_details_tag_fix` | `True` | Normalize `<details>` spacing. |
|
||||
| `enable_code_block_fix` | `True` | Fix code block indentation and newlines. |
|
||||
| `enable_latex_fix` | `True` | Standardize LaTeX delimiters (`\[` -> `$$`). |
|
||||
| `enable_list_fix` | `False` | Fix list item newlines (experimental). |
|
||||
| `enable_unclosed_block_fix` | `True` | Auto-close unclosed code blocks. |
|
||||
| `enable_fullwidth_symbol_fix` | `False` | Fix full-width symbols in code blocks. |
|
||||
| `enable_mermaid_fix` | `True` | Fix common Mermaid syntax errors. |
|
||||
| `enable_heading_fix` | `True` | Fix missing space in headings. |
|
||||
| `enable_table_fix` | `True` | Fix missing closing pipe in tables. |
|
||||
| `enable_xml_tag_cleanup` | `True` | Cleanup leftover XML tags. |
|
||||
| `enable_emphasis_spacing_fix` | `False` | Fix extra spaces in emphasis. |
|
||||
| `show_status` | `True` | Show status notification when fixes are applied. |
|
||||
| `show_debug_log` | `True` | Print debug logs to browser console (F12). |
|
||||
| `enable_mermaid_fix` | `True` | Fix common Mermaid syntax errors (auto-quoting). |
|
||||
| `enable_heading_fix` | `True` | Add missing space after heading hashes (`#Title` -> `# Title`). |
|
||||
| `enable_table_fix` | `True` | Add missing closing pipe in tables. |
|
||||
| `enable_xml_tag_cleanup` | `True` | Remove leftover XML artifacts. |
|
||||
| `enable_emphasis_spacing_fix` | `False` | Fix extra spaces in emphasis formatting. |
|
||||
| `show_status` | `True` | Show UI status notification when a fix is actively applied. |
|
||||
| `show_debug_log` | `False` | Print detailed before/after diffs to browser console (F12). |
|
||||
|
||||
## ⭐ Support
|
||||
|
||||
If this plugin has been useful, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you for the support.
|
||||
If this plugin saves your day, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you!
|
||||
|
||||
## 🧩 Others
|
||||
|
||||
### Troubleshooting ❓
|
||||
|
||||
* **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [OpenWebUI Extensions Issues](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
### Changelog
|
||||
|
||||
See the full history on GitHub: [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions)
|
||||
* **Troubleshooting**: Encountering "negative fixes"? Enable `show_debug_log`, check your console, and submit an issue on GitHub: [OpenWebUI Extensions Issues](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
@@ -1,81 +1,89 @@
|
||||
# Markdown 格式化过滤器 (Markdown Normalizer)
|
||||
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 1.2.7 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 1.2.8 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
|
||||
|
||||
这是一个用于 Open WebUI 的内容格式化过滤器，旨在修复 LLM 输出中常见的 Markdown 格式问题。它能确保代码块、LaTeX 公式、Mermaid 图表和其他 Markdown 元素被正确渲染。
|
||||
这是一个强大的、具备上下文感知的 Markdown 内容规范化过滤器，专为 Open WebUI 设计，旨在实时修复大语言模型 (LLM) 输出中常见的格式错乱问题。它能确保代码块、LaTeX 公式、Mermaid 图表以及其他结构化元素被完美渲染，同时**绝不破坏**你原有的有效技术内容（如代码、正则、路径）。
|
||||
|
||||
> 🏆 **OpenWebUI 官方推荐** — 本插件获得 OpenWebUI 社区 Newsletter 官方推荐：[2026 年 1 月 28 日](https://openwebui.com/blog/newsletter-january-28-2026)
|
||||
|
||||
## 🔥 最新更新 v1.2.7
|
||||
[English](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README.md) | [简体中文](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/markdown_normalizer/README_CN.md)
|
||||
|
||||
* **LaTeX 公式保护**: 增强了转义字符清理逻辑，自动保护 `$ $` 或 `$$ $$` 内的 LaTeX 命令（如 `\times`、`\nu`、`\theta`），防止渲染失效。
|
||||
* **扩展国际化 (i18n) 支持**: 现已支持 12 种语言，具备自动探测与回退机制。
|
||||
* **配置项优化**: 将 Valves 配置项的描述统一为英文，保持界面一致性。
|
||||
* **修复 Bug**:
|
||||
* 修复了 [Issue #49](https://github.com/Fu-Jie/openwebui-extensions/issues/49)：解决了当同一行存在多个加粗部分时，由于正则匹配过于贪婪导致中间内容丢失空格的问题。
|
||||
* 修复了插件代码中的 `NameError` 错误，确保测试脚本能正常运行。
|
||||
---
|
||||
|
||||
## 🔥 最新更新 v1.2.8
|
||||
* **“默认安全”策略 (Safe-by-Default)**：`enable_escape_fix` 功能现在**默认禁用**。这能有效防止插件在未经授权的情况下误改 Windows 路径 (`C:\new\test`) 或复杂的 LaTeX 公式。
|
||||
* **LaTeX 解析优化**：重构了显示数学公式 (`$$ ... $$`) 的识别逻辑。修复了 LaTeX 命令如果以 `\n` 开头（如 `\nabla`）会被错误识别为换行符的 Bug。
|
||||
* **可靠性增强**：实现了完整的错误回滚机制。当修复过程发生意外错误时，保证 100% 返回原始文本，不丢失任何数据。
|
||||
* **配置项修复**：`enable_escape_fix_in_code_blocks` 配置项现在能正确作用于代码块了。**如果您遇到 SQL 挤在一行的问题，只需在设置中手动开启此项即可。**
|
||||
|
||||
---
|
||||
|
||||
## 🚀 为什么你需要这个插件？(它能解决什么问题？)
|
||||
|
||||
由于分词 (Tokenization) 伪影、过度转义或格式幻觉，LLM 经常会生成破损的 Markdown。如果你遇到过以下情况：
|
||||
- `mermaid` 图表因为节点标签缺少双引号而渲染失败、白屏。
|
||||
- LLM 输出的 SQL 语句挤在一行，因为本该换行的地方输出了字面量 `\n`。
|
||||
- 复杂的 `<details>` (思维链展开块) 因为缺少换行符导致整个聊天界面排版崩塌。
|
||||
- LaTeX 数学公式无法显示，因为模型使用了旧版的 `\[` 而不是 Markdown 支持的 `$$`。
|
||||
|
||||
**本插件会自动拦截 LLM 返回的原始数据，实时分析其文本结构，并像外科手术一样精准修复这些排版错误，然后再将其展示在你的浏览器中。**
|
||||
|
||||
## ✨ 核心功能与修复能力全景
|
||||
|
||||
### 1. 高级结构保护 (上下文感知)
|
||||
在执行任何修改前，插件会为整个文本建立语义地图，确保技术性内容不被误伤：
|
||||
- **代码块保护**：默认跳过 ` ``` ` 内部的内容，保护所有编程逻辑。
|
||||
- **行内代码保护**：识别 `` `代码` `` 片段，防止正则表达式（如 `[\n\r]`）或文件路径（如 `C:\Windows`）被错误地去转义。
|
||||
- **LaTeX 公式保护**：识别行内 (`$`) 和块级 (`$$`) 公式，防止诸如 `\times`, `\theta` 等核心数学命令被意外破坏。
|
||||
|
||||
### 2. 自动治愈转换 (Auto-Healing)
|
||||
- **Details 标签排版修复**：`<details>` 块要求极为严格的空行才能正确渲染内部内容。插件会自动在 `</details>` 以及自闭合 `<details />` 标签后注入安全的换行符。
|
||||
- **Mermaid 语法急救**：自动修复最常见的 Mermaid 错误——为未加引号的节点标签（如 `A --> B(Some text)`）自动补充双引号，甚至支持多行标签和引用，确保拓扑图 100% 渲染。
|
||||
- **强调语法间距修复**：修复加粗/斜体语法内部多余的空格（如 `** 文本 **` 变为 `**文本**`，否则 OpenWebUI 无法加粗），同时智能忽略数学算式（如 `2 * 3 * 4`）。
|
||||
- **智能转义字符清理**：将模型过度转义生成的字面量 `\n` 和 `\t` 转化为真正的换行和缩进（仅在安全的纯文本区域执行）。
|
||||
- **LaTeX 现代化转换**：自动将旧式的 LaTeX 定界符（`\[...\]` 和 `\(...\)`）升级为现代 Markdown 标准（`$$...$$` 和 `$ ... $`）。
|
||||
- **思维标签大一统**：无论模型输出的是 `<think>` 还是 `<thinking>`，统一标准化为 `<thought>` 标签。
|
||||
- **残缺代码块修复**：修复乱码的语言前缀（例如 ` ```python`），调整缩进，并在模型回答被截断时，自动补充闭合的 ` ``` `。
|
||||
- **列表与表格急救**：为粘连的编号列表注入换行，为残缺的 Markdown 表格补充末尾的闭合管道符（`|`）。
|
||||
- **XML 伪影消除**：静默移除 Claude 模型经常泄露的 `<antArtifact>` 或 `<antThinking>` 残留标签。
|
||||
|
||||
### 3. 绝对的可靠性与安全 (100% Rollback)
|
||||
- **无损回滚机制**：如果在修复过程中发生任何意外错误或崩溃，插件会立即捕获异常，并静默返回**绝对原始**的文本，确保你的对话永远不会因插件报错而丢失。
|
||||
|
||||
## 🌐 多语言支持 (i18n)
|
||||
|
||||
支持以下语言的界面与状态自动切换：
|
||||
界面的状态提示气泡会根据你的浏览器语言自动切换：
|
||||
`English`, `简体中文`, `繁體中文 (香港)`, `繁體中文 (台灣)`, `한국어`, `日本語`, `Français`, `Deutsch`, `Español`, `Italiano`, `Tiếng Việt`, `Bahasa Indonesia`
|
||||
|
||||
## ✨ 核心特性
|
||||
|
||||
* **Details 标签规范化**: 确保 `<details>` 标签（常用于思维链）有正确的间距。在 `</details>` 后添加空行，并在自闭合 `<details />` 标签后添加换行，防止渲染问题。
|
||||
* **强调空格修复**: 修复强调标记内部的多余空格（例如 `** 文本 **` -> `**文本**`），这会导致 Markdown 渲染失败。包含保护机制，防止误修改数学表达式（如 `2 * 3 * 4`）或列表变量。
|
||||
* **Mermaid 语法修复**: 自动修复常见的 Mermaid 语法错误，如未加引号的节点标签（支持多行标签和引用标记）和未闭合的子图 (Subgraph)。**v1.1.2 新增**: 全面保护各种类型的连线标签（实线、虚线、粗线），防止被误修改。
|
||||
* **前端控制台调试**: 支持将结构化的调试日志直接打印到浏览器控制台 (F12)，方便排查问题。
|
||||
* **代码块格式化**: 修复破损的代码块前缀、后缀和缩进问题。
|
||||
* **LaTeX 规范化**: 标准化 LaTeX 公式定界符 (`\[` -> `$$`, `\(` -> `$`)。
|
||||
* **思维标签规范化**: 统一思维链标签 (`<think>`, `<thinking>` -> `<thought>`)。
|
||||
* **转义字符修复**: 清理过度的转义字符 (`\\n`, `\\t`)。
|
||||
* **列表格式化**: 确保列表项有正确的换行。
|
||||
* **标题修复**: 修复标题中缺失的空格 (`#标题` -> `# 标题`)。
|
||||
* **表格修复**: 修复表格中缺失的闭合管道符。
|
||||
* **XML 清理**: 移除残留的 XML 标签。
|
||||
|
||||
## 使用方法
|
||||
## 使用方法 🛠️
|
||||
|
||||
1. 在 Open WebUI 中安装此插件。
|
||||
2. 全局启用或为特定模型启用此过滤器。
|
||||
3. 在 **Valves** 设置中配置需要启用的修复项。
|
||||
4. (可选) **显示调试日志 (Show Debug Log)** 在 Valves 中默认开启。这会将结构化的日志打印到浏览器控制台 (F12)。
|
||||
> [!WARNING]
|
||||
> 由于这是初版，可能会出现“负向修复”的情况（例如破坏了原本正确的格式）。如果您遇到问题，请务必查看控制台日志，复制“原始 (Original)”与“规范化 (Normalized)”的内容对比，并提交 Issue 反馈。
|
||||
2. 全局启用或为特定模型启用此过滤器（强烈建议为格式输出不稳定的模型启用）。
|
||||
3. 在 **Valves (配置参数)** 设置中微调你需要的修复项。
|
||||
|
||||
## 配置参数 (Valves) ⚙️
|
||||
|
||||
| 参数 | 默认值 | 描述 |
|
||||
| :--- | :--- | :--- |
|
||||
| `priority` | `50` | 过滤器优先级。数值越大越靠后（建议在其他过滤器之后运行）。 |
|
||||
| `enable_escape_fix` | `True` | 修复过度的转义字符（`\n`, `\t` 等）。 |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | 在代码块内应用转义修复（可能影响有效代码）。 |
|
||||
| `enable_thought_tag_fix` | `True` | 规范化思维标签（`</thought>`）。 |
|
||||
| `enable_details_tag_fix` | `True` | 规范化 `<details>` 标签并添加安全间距。 |
|
||||
| `enable_code_block_fix` | `True` | 修复代码块格式（缩进/换行）。 |
|
||||
| `enable_latex_fix` | `True` | 规范化 LaTeX 定界符（`\[` -> `$$`, `\(` -> `$`）。 |
|
||||
| `priority` | `50` | 过滤器优先级。数值越大越靠后（建议放在其他内容过滤器之后运行）。 |
|
||||
| `enable_escape_fix` | `False` | 修复过度的转义字符（将字面量 `\n` 转换为实际换行）。**默认禁用以保证安全。** |
|
||||
| `enable_escape_fix_in_code_blocks` | `False` | **高阶技巧**：如果你的 SQL 或 HTML 代码块总是挤在一行，**请开启此项**。如果你经常写 Python/C++，建议保持关闭。 |
|
||||
| `enable_thought_tag_fix` | `True` | 规范化思维标签为 `<thought>`。 |
|
||||
| `enable_details_tag_fix` | `True` | 修复 `<details>` 标签的排版间距。 |
|
||||
| `enable_code_block_fix` | `True` | 修复代码块前缀、缩进和换行。 |
|
||||
| `enable_latex_fix` | `True` | 规范化 LaTeX 定界符（`\[` -> `$$`）。 |
|
||||
| `enable_list_fix` | `False` | 修复列表项换行（实验性）。 |
|
||||
| `enable_unclosed_block_fix` | `True` | 自动闭合未闭合的代码块。 |
|
||||
| `enable_fullwidth_symbol_fix` | `False` | 修复代码块中的全角符号。 |
|
||||
| `enable_mermaid_fix` | `True` | 修复常见 Mermaid 语法错误。 |
|
||||
| `enable_heading_fix` | `True` | 修复标题中缺失的空格。 |
|
||||
| `enable_unclosed_block_fix` | `True` | 自动闭合被截断的代码块。 |
|
||||
| `enable_mermaid_fix` | `True` | 修复常见 Mermaid 语法错误（如自动加引号）。 |
|
||||
| `enable_heading_fix` | `True` | 修复标题中缺失的空格 (`#Title` -> `# Title`)。 |
|
||||
| `enable_table_fix` | `True` | 修复表格中缺失的闭合管道符。 |
|
||||
| `enable_xml_tag_cleanup` | `True` | 清理残留的 XML 标签。 |
|
||||
| `enable_emphasis_spacing_fix` | `False` | 修复强调语法中的多余空格。 |
|
||||
| `show_status` | `True` | 应用修复时显示状态通知。 |
|
||||
| `show_debug_log` | `True` | 在浏览器控制台打印调试日志。 |
|
||||
| `enable_xml_tag_cleanup` | `True` | 清理残留的 XML 分析标签。 |
|
||||
| `enable_emphasis_spacing_fix` | `False` | 修复强调语法（加粗/斜体）内部的多余空格。 |
|
||||
| `show_status` | `True` | 当触发任何修复规则时，在页面底部显示提示气泡。 |
|
||||
| `show_debug_log` | `False` | 在浏览器控制台 (F12) 打印修改前后的详细对比日志。 |
|
||||
|
||||
## ⭐ 支持
|
||||
如果这个插件拯救了你的排版，欢迎到 [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) 点个 Star，这是我持续改进的最大动力。感谢支持！
|
||||
|
||||
如果这个插件对你有帮助，欢迎到 [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) 点个 Star，这将是我持续改进的动力，感谢支持。
|
||||
|
||||
## 其他
|
||||
|
||||
### 故障排除 (Troubleshooting) ❓
|
||||
|
||||
* **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[OpenWebUI Extensions Issues](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
### 更新日志
|
||||
|
||||
完整历史请查看 GitHub 项目： [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions)
|
||||
## 🧩 其他
|
||||
* **故障排除**：遇到“负向修复”（即原本正常的排版被修坏了）？请开启 `show_debug_log`，在 F12 控制台复制出原始文本，并在 GitHub 提交 Issue：[提交 Issue](https://github.com/Fu-Jie/openwebui-extensions/issues)
|
||||
|
||||
@@ -3,7 +3,7 @@ title: Markdown Normalizer
|
||||
author: Fu-Jie
|
||||
author_url: https://github.com/Fu-Jie/openwebui-extensions
|
||||
funding_url: https://github.com/open-webui
|
||||
version: 1.2.7
|
||||
version: 1.2.8
|
||||
openwebui_id: baaa8732-9348-40b7-8359-7e009660e23c
|
||||
description: A content normalizer filter that fixes common Markdown formatting issues in LLM outputs, such as broken code blocks, LaTeX formulas, and list formatting. Including LaTeX command protection.
|
||||
"""
|
||||
@@ -236,7 +236,7 @@ TRANSLATIONS = {
|
||||
class NormalizerConfig:
|
||||
"""Configuration class for enabling/disabling specific normalization rules"""
|
||||
|
||||
enable_escape_fix: bool = True # Fix excessive escape characters
|
||||
enable_escape_fix: bool = False # Fix excessive escape characters (Default False for safety)
|
||||
enable_escape_fix_in_code_blocks: bool = (
|
||||
False # Apply escape fix inside code blocks (default: False for safety)
|
||||
)
|
||||
@@ -456,28 +456,47 @@ class ContentNormalizer:
|
||||
except Exception as e:
|
||||
# Production safeguard: return original content on error
|
||||
logger.error(f"Content normalization failed: {e}", exc_info=True)
|
||||
return content
|
||||
return original_content
|
||||
|
||||
def _fix_escape_characters(self, content: str) -> str:
|
||||
"""Fix excessive escape characters while protecting LaTeX and code blocks."""
|
||||
"""Fix excessive escape characters while protecting LaTeX, code blocks, and inline code."""
|
||||
|
||||
def clean_text(text: str) -> str:
|
||||
# Only fix \n and double backslashes, skip \t as it's dangerous for LaTeX (\times, \theta)
|
||||
# First handle literal escaped newlines
|
||||
text = text.replace("\\r\\n", "\n")
|
||||
text = text.replace("\\n", "\n")
|
||||
|
||||
# Then handle double backslashes that are not followed by n or r
|
||||
# (which would have been part of an escaped newline handled above)
|
||||
# Use regex to replace \\ with \ only if not followed by n or r
|
||||
# But wait, \n is already \n (actual newline) here.
|
||||
# So we can safely replace all remaining \\ with \
|
||||
text = text.replace("\\\\", "\\")
|
||||
return text
|
||||
|
||||
# 1. Protect code blocks
|
||||
# 1. Protect block code
|
||||
parts = content.split("```")
|
||||
for i in range(0, len(parts), 2): # Even indices are text
|
||||
# 2. Protect LaTeX formulas within text
|
||||
# Split by $ to find inline/block math
|
||||
sub_parts = parts[i].split("$")
|
||||
for j in range(0, len(sub_parts), 2): # Even indices are non-math text
|
||||
sub_parts[j] = clean_text(sub_parts[j])
|
||||
|
||||
parts[i] = "$".join(sub_parts)
|
||||
for i in range(0, len(parts)):
|
||||
is_code_block = (i % 2 != 0)
|
||||
if is_code_block and not self.config.enable_escape_fix_in_code_blocks:
|
||||
continue
|
||||
|
||||
if not is_code_block:
|
||||
# 2. Protect inline code
|
||||
inline_parts = parts[i].split("`")
|
||||
for k in range(0, len(inline_parts), 2): # Even indices are non-inline-code text
|
||||
# 3. Protect LaTeX formulas within text (safe for $$ and $)
|
||||
# Use regex to split and keep delimiters
|
||||
sub_parts = re.split(
|
||||
r"(\$\$.*?\$\$|\$.*?\$)", inline_parts[k], flags=re.DOTALL
|
||||
)
|
||||
for j in range(0, len(sub_parts), 2): # Even indices are non-math text
|
||||
sub_parts[j] = clean_text(sub_parts[j])
|
||||
inline_parts[k] = "".join(sub_parts)
|
||||
parts[i] = "`".join(inline_parts)
|
||||
else:
|
||||
# Inside code block and enable_escape_fix_in_code_blocks is True
|
||||
parts[i] = clean_text(parts[i])
|
||||
|
||||
return "```".join(parts)
|
||||
|
||||
@@ -707,8 +726,8 @@ class Filter:
|
||||
description="Priority level (lower = earlier).",
|
||||
)
|
||||
enable_escape_fix: bool = Field(
|
||||
default=True,
|
||||
description="Fix excessive escape characters (\\n, \\t, etc.).",
|
||||
default=False,
|
||||
description="Fix excessive escape characters (\\n, \\t, etc.). Default: False for safety.",
|
||||
)
|
||||
enable_escape_fix_in_code_blocks: bool = Field(
|
||||
default=False,
|
||||
@@ -767,7 +786,7 @@ class Filter:
|
||||
description="Show status notification when fixes are applied.",
|
||||
)
|
||||
show_debug_log: bool = Field(
|
||||
default=True,
|
||||
default=False,
|
||||
description="Print debug logs to browser console (F12).",
|
||||
)
|
||||
|
||||
|
||||
13
plugins/filters/markdown_normalizer/v1.2.8.md
Normal file
13
plugins/filters/markdown_normalizer/v1.2.8.md
Normal file
@@ -0,0 +1,13 @@
|
||||
# v1.2.8 Release Notes
|
||||
|
||||
This release focuses on significantly improving the reliability and safety of the Markdown Normalizer filter, ensuring that it never corrupts valid technical content and elegantly handles unexpected errors.
|
||||
|
||||
## Bug Fixes
|
||||
|
||||
- **Error Fallback Mechanism**: Fixed an issue where the plugin could return partially modified or broken text if an error occurred during normalization. It now guarantees a 100% rollback to the original text upon any failure.
|
||||
- **Inline Code Protection**: Refined the escape character fixing logic to accurately identify and protect inline code blocks (`` `...` ``). This prevents valid technical strings, such as regular expressions (`[\n\r]`) and Windows file paths (`C:\Windows`), from being unintentionally modified.
|
||||
- **Code Block Escaping Control**: Fixed a bug where the `enable_escape_fix_in_code_blocks` Valve setting was ignored. The setting now correctly applies, allowing users to optionally fix broken newlines inside code blocks (e.g., repairing flat SQL queries) when enabled.
|
||||
|
||||
## New Features
|
||||
|
||||
- **Privacy & Log Optimization**: The `show_debug_log` Valve now defaults to `False` instead of `True`. This prevents sensitive chat content from automatically printing to the browser console and reduces unnecessary log noise for general users.
|
||||
13
plugins/filters/markdown_normalizer/v1.2.8_CN.md
Normal file
13
plugins/filters/markdown_normalizer/v1.2.8_CN.md
Normal file
@@ -0,0 +1,13 @@
|
||||
# v1.2.8 版本发布说明
|
||||
|
||||
本次更新重点在于大幅提升 Markdown Normalizer 插件的可靠性与安全性，确保它在任何情况下都不会损坏有效的技术内容，并能优雅地处理各种意外错误。
|
||||
|
||||
## 问题修复
|
||||
|
||||
- **错误回滚机制 (Error Fallback)**：修复了规范化过程中如果发生错误会导致返回残缺或损坏文本的问题。现在，插件在遇到任何异常失败时，保证 100% 回滚并返回原始文本，确保对话内容不丢失。
|
||||
- **内联代码保护 (Inline Code Protection)**：优化了转义字符的修复逻辑，现在能够精准识别并保护内联代码块（`` `...` ``）。这防止了像正则表达式（`[\n\r]`）和 Windows 文件路径（`C:\Windows`）这样的有效技术字符串被意外修改。
|
||||
- **代码块转义控制修复 (Code Block Escaping Control)**：修复了 `enable_escape_fix_in_code_blocks` 配置项失效的 Bug。现在该选项可以正常生效，当开启时，用户可以借此修复代码块内部（例如 SQL 查询语句）因错误转义导致挤在一行的问题。
|
||||
|
||||
## 新功能
|
||||
|
||||
- **隐私与日志优化 (Privacy & Log Optimization)**：`show_debug_log` 的默认值从 `True` 更改为了 `False`。这避免了将可能包含敏感信息的对话内容自动打印到浏览器控制台，并减少了普通用户的日志噪音。
|
||||
@@ -54,6 +54,15 @@ from open_webui.storage.provider import Storage
|
||||
import mimetypes
|
||||
import uuid
|
||||
|
||||
if os.path.exists("/app/backend/data"):
|
||||
CHAT_MAPPING_FILE = Path(
|
||||
"/app/backend/data/copilot_workspace/api_key_chat_id_mapping.json"
|
||||
)
|
||||
else:
|
||||
CHAT_MAPPING_FILE = (
|
||||
Path(os.getcwd()) / "copilot_workspace" / "api_key_chat_id_mapping.json"
|
||||
)
|
||||
|
||||
# Get OpenWebUI version for capability detection
|
||||
try:
|
||||
from open_webui.env import VERSION as open_webui_version
|
||||
@@ -4879,6 +4888,41 @@ class Pipe:
|
||||
|
||||
return cwd
|
||||
|
||||
def _record_user_chat_mapping(
|
||||
self, user_id: Optional[str], chat_id: Optional[str]
|
||||
) -> None:
|
||||
"""Persist the latest chat_id for the current user."""
|
||||
if not user_id or not chat_id:
|
||||
return
|
||||
|
||||
mapping_file = CHAT_MAPPING_FILE
|
||||
|
||||
try:
|
||||
mapping_file.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
mapping: Dict[str, str] = {}
|
||||
if mapping_file.exists():
|
||||
try:
|
||||
loaded = json.loads(mapping_file.read_text(encoding="utf-8"))
|
||||
if isinstance(loaded, dict):
|
||||
mapping = {str(k): str(v) for k, v in loaded.items()}
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
f"[Session Tracking] Failed to read mapping file {mapping_file}: {e}"
|
||||
)
|
||||
|
||||
mapping[str(user_id)] = str(chat_id)
|
||||
|
||||
temp_file = mapping_file.with_suffix(mapping_file.suffix + ".tmp")
|
||||
temp_file.write_text(
|
||||
json.dumps(mapping, ensure_ascii=False, indent=2, sort_keys=True)
|
||||
+ "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
temp_file.replace(mapping_file)
|
||||
except Exception as e:
|
||||
logger.warning(f"[Session Tracking] Failed to persist mapping: {e}")
|
||||
|
||||
def _build_client_config(self, user_id: str = None, chat_id: str = None) -> dict:
|
||||
"""Build CopilotClient config from valves and request body."""
|
||||
cwd = self._get_workspace_dir(user_id=user_id, chat_id=chat_id)
|
||||
@@ -5837,6 +5881,8 @@ class Pipe:
|
||||
)
|
||||
is_admin = user_data.get("role") == "admin"
|
||||
|
||||
self._record_user_chat_mapping(user_data.get("id"), __chat_id__)
|
||||
|
||||
# Robustly parse User Valves
|
||||
user_valves = self._get_user_valves(__user__)
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# MkDocs Documentation Dependencies
|
||||
# Core MkDocs
|
||||
mkdocs>=1.5.0
|
||||
mkdocs>=1.5.0,<2.0.0
|
||||
|
||||
# Material Theme for MkDocs
|
||||
mkdocs-material>=9.5.0
|
||||
|
||||
26
scripts/.env.example
Normal file
26
scripts/.env.example
Normal file
@@ -0,0 +1,26 @@
|
||||
# OpenWebUI Bulk Installer Configuration
|
||||
#
|
||||
# Instructions:
|
||||
# - api_key: Copy from OpenWebUI Settings (starts with sk-)
|
||||
# - url: OpenWebUI server address (supports localhost, IP, and domain)
|
||||
#
|
||||
# URL Examples:
|
||||
# - Local: http://localhost:3000
|
||||
# - Remote IP: http://192.168.1.10:3000
|
||||
# - Domain: https://openwebui.example.com
|
||||
#
|
||||
# Environment variable precedence (highest to lowest):
|
||||
# 1. OPENWEBUI_API_KEY / OPENWEBUI_URL environment variables
|
||||
# 2. OPENWEBUI_BASE_URL environment variable
|
||||
# 3. Configuration in this .env file
|
||||
|
||||
# API Key (required)
|
||||
api_key=sk-your-api-key-here
|
||||
|
||||
# OpenWebUI server address (required)
|
||||
# Configure the baseURL where your OpenWebUI instance is running
|
||||
url=http://localhost:3000
|
||||
|
||||
# Alternatively, use environment variable format (both methods are equivalent)
|
||||
# OPENWEBUI_API_KEY=sk-your-api-key-here
|
||||
# OPENWEBUI_BASE_URL=http://localhost:3000
|
||||
206
scripts/DEPLOYMENT_GUIDE.md
Normal file
206
scripts/DEPLOYMENT_GUIDE.md
Normal file
@@ -0,0 +1,206 @@
|
||||
# 🚀 Local Deployment Scripts Guide
|
||||
|
||||
## Overview
|
||||
|
||||
This directory contains automated scripts for deploying plugins in development to a local OpenWebUI instance. They enable quick code pushes without restarting OpenWebUI.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. **OpenWebUI Running**: Make sure OpenWebUI is running locally (default `http://localhost:3000`)
|
||||
2. **API Key**: You need a valid OpenWebUI API key
|
||||
3. **Environment File**: Create a `.env` file in this directory containing your API key:
|
||||
```
|
||||
api_key=sk-xxxxxxxxxxxxx
|
||||
```
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Deploy a Pipe Plugin
|
||||
|
||||
```bash
|
||||
# Deploy GitHub Copilot SDK Pipe
|
||||
python deploy_pipe.py
|
||||
```
|
||||
|
||||
### Deploy a Filter Plugin
|
||||
|
||||
```bash
|
||||
# Deploy async_context_compression Filter (default)
|
||||
python deploy_filter.py
|
||||
|
||||
# Deploy a specific Filter plugin
|
||||
python deploy_filter.py my-filter-name
|
||||
|
||||
# List all available Filters
|
||||
python deploy_filter.py --list
|
||||
```
|
||||
|
||||
## Script Documentation
|
||||
|
||||
### `deploy_filter.py` — Filter Plugin Deployment Tool
|
||||
|
||||
Used to deploy Filter-type plugins (such as message filtering, context compression, etc.).
|
||||
|
||||
**Key Features**:
|
||||
- ✅ Auto-extracts metadata from Python files (version, author, description, etc.)
|
||||
- ✅ Attempts to update existing plugins, creates if not found
|
||||
- ✅ Supports multiple Filter plugin management
|
||||
- ✅ Detailed error messages and connection diagnostics
|
||||
|
||||
**Usage**:
|
||||
```bash
|
||||
# Deploy async_context_compression (default)
|
||||
python deploy_filter.py
|
||||
|
||||
# Deploy other Filters
|
||||
python deploy_filter.py async-context-compression
|
||||
python deploy_filter.py workflow-guide
|
||||
|
||||
# List all available Filters
|
||||
python deploy_filter.py --list
|
||||
python deploy_filter.py -l
|
||||
```
|
||||
|
||||
**Workflow**:
|
||||
1. Load API key from `.env`
|
||||
2. Find target Filter plugin directory
|
||||
3. Read Python source file
|
||||
4. Extract metadata from docstring (title, version, author, description, etc.)
|
||||
5. Build API request payload
|
||||
6. Send update request to OpenWebUI
|
||||
7. If update fails, auto-attempt to create new plugin
|
||||
8. Display results and diagnostic info
|
||||
|
||||
### `deploy_pipe.py` — Pipe Plugin Deployment Tool
|
||||
|
||||
Used to deploy Pipe-type plugins (such as GitHub Copilot SDK).
|
||||
|
||||
**Usage**:
|
||||
```bash
|
||||
python deploy_pipe.py
|
||||
```
|
||||
|
||||
## Get an API Key
|
||||
|
||||
### Method 1: Use Existing User Token (Recommended)
|
||||
|
||||
1. Open OpenWebUI interface
|
||||
2. Click user avatar → Settings
|
||||
3. Find the API Keys section
|
||||
4. Copy your API key (starts with sk-)
|
||||
5. Paste into `.env` file
|
||||
|
||||
### Method 2: Create a Long-term API Key
|
||||
|
||||
Create a dedicated long-term API key in OpenWebUI Settings for deployment purposes.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### "Connection error: Could not reach OpenWebUI at localhost:3000"
|
||||
|
||||
**Cause**: OpenWebUI is not running or port is different
|
||||
|
||||
**Solution**:
|
||||
- Make sure OpenWebUI is running
|
||||
- Check which port OpenWebUI is actually listening on (usually 3000)
|
||||
- Edit the URL in the script if needed
|
||||
|
||||
### ".env file not found"
|
||||
|
||||
**Cause**: `.env` file was not created
|
||||
|
||||
**Solution**:
|
||||
```bash
|
||||
echo "api_key=sk-your-api-key-here" > .env
|
||||
```
|
||||
|
||||
### "Filter 'xxx' not found"
|
||||
|
||||
**Cause**: Filter directory name is incorrect
|
||||
|
||||
**Solution**:
|
||||
```bash
|
||||
# List all available Filters
|
||||
python deploy_filter.py --list
|
||||
```
|
||||
|
||||
### "Failed to update or create. Status: 401"
|
||||
|
||||
**Cause**: API key is invalid or expired
|
||||
|
||||
**Solution**:
|
||||
1. Verify your API key is valid
|
||||
2. Generate a new API key
|
||||
3. Update the `.env` file
|
||||
|
||||
## Workflow Examples
|
||||
|
||||
### Develop and Deploy a New Filter
|
||||
|
||||
```bash
|
||||
# 1. Create new Filter directory in plugins/filters/
|
||||
mkdir plugins/filters/my-new-filter
|
||||
|
||||
# 2. Create my_new_filter.py with required metadata:
|
||||
# """
|
||||
# title: My New Filter
|
||||
# author: Your Name
|
||||
# version: 1.0.0
|
||||
# description: Filter description
|
||||
# """
|
||||
|
||||
# 3. Deploy to local OpenWebUI
|
||||
cd scripts
|
||||
python deploy_filter.py my-new-filter
|
||||
|
||||
# 4. Test the plugin in OpenWebUI UI
|
||||
|
||||
# 5. Continue development
|
||||
# ... modify code ...
|
||||
|
||||
# 6. Re-deploy (auto-overwrites)
|
||||
python deploy_filter.py my-new-filter
|
||||
```
|
||||
|
||||
### Fix a Bug and Deploy Quickly
|
||||
|
||||
```bash
|
||||
# 1. Modify the source code
|
||||
# vim ../plugins/filters/async-context-compression/async_context_compression.py
|
||||
|
||||
# 2. Deploy immediately to local
|
||||
python deploy_filter.py async-context-compression
|
||||
|
||||
# 3. Test the fix in OpenWebUI
|
||||
# (No need to restart OpenWebUI)
|
||||
```
|
||||
|
||||
## Security Considerations
|
||||
|
||||
⚠️ **Important**:
|
||||
- ✅ Add `.env` file to `.gitignore` (avoid committing sensitive info)
|
||||
- ✅ Never commit API keys to version control
|
||||
- ✅ Use only on trusted networks
|
||||
- ✅ Rotate API keys periodically
|
||||
|
||||
## File Structure
|
||||
|
||||
```
|
||||
scripts/
|
||||
├── deploy_filter.py # Filter plugin deployment tool
|
||||
├── deploy_pipe.py # Pipe plugin deployment tool
|
||||
├── .env # API key (local, not committed)
|
||||
├── README.md # This file
|
||||
└── ...
|
||||
```
|
||||
|
||||
## Reference Resources
|
||||
|
||||
- [OpenWebUI Documentation](https://docs.openwebui.com/)
|
||||
- [Plugin Development Guide](../docs/development/plugin-guide.md)
|
||||
- [Filter Plugin Examples](../plugins/filters/)
|
||||
|
||||
---
|
||||
|
||||
**Last Updated**: 2026-03-09
|
||||
**Author**: Fu-Jie
|
||||
378
scripts/DEPLOYMENT_SUMMARY.md
Normal file
378
scripts/DEPLOYMENT_SUMMARY.md
Normal file
@@ -0,0 +1,378 @@
|
||||
# 📦 Async Context Compression — Local Deployment Tools
|
||||
|
||||
## 🎯 Feature Overview
|
||||
|
||||
Added a complete local deployment toolchain for the `async_context_compression` Filter plugin, supporting fast iterative development without restarting OpenWebUI.
|
||||
|
||||
## 📋 New Files
|
||||
|
||||
### 1. **deploy_filter.py** — Filter Plugin Deployment Script
|
||||
- **Location**: `scripts/deploy_filter.py`
|
||||
- **Function**: Auto-deploy Filter-type plugins to local OpenWebUI instance
|
||||
- **Features**:
|
||||
- ✅ Auto-extract metadata from Python docstring
|
||||
- ✅ Smart semantic version recognition
|
||||
- ✅ Support multiple Filter plugin management
|
||||
- ✅ Auto-update or create plugins
|
||||
- ✅ Detailed error diagnostics and connection testing
|
||||
- ✅ List command to view all available Filters
|
||||
- **Code Lines**: ~300
|
||||
|
||||
### 2. **DEPLOYMENT_GUIDE.md** — Complete Deployment Guide
|
||||
- **Location**: `scripts/DEPLOYMENT_GUIDE.md`
|
||||
- **Contents**:
|
||||
- Prerequisites and quick start
|
||||
- Detailed script documentation
|
||||
- API key retrieval method
|
||||
- Troubleshooting guide
|
||||
- Step-by-step workflow examples
|
||||
|
||||
### 3. **QUICK_START.md** — Quick Reference Card
|
||||
- **Location**: `scripts/QUICK_START.md`
|
||||
- **Contents**:
|
||||
- One-line deployment command
|
||||
- Setup steps
|
||||
- Common commands table
|
||||
- Troubleshooting quick-reference table
|
||||
- CI/CD integration examples
|
||||
|
||||
### 4. **test_deploy_filter.py** — Unit Test Suite
|
||||
- **Location**: `tests/scripts/test_deploy_filter.py`
|
||||
- **Test Coverage**:
|
||||
- ✅ Filter file discovery (3 tests)
|
||||
- ✅ Metadata extraction (3 tests)
|
||||
- ✅ API payload building (4 tests)
|
||||
- **Pass Rate**: 10/10 ✅
|
||||
|
||||
## 🚀 Usage
|
||||
|
||||
### Basic Deploy (One-liner)
|
||||
|
||||
```bash
|
||||
cd scripts
|
||||
python deploy_filter.py
|
||||
```
|
||||
|
||||
### List All Available Filters
|
||||
|
||||
```bash
|
||||
python deploy_filter.py --list
|
||||
```
|
||||
|
||||
### Deploy Specific Filter
|
||||
|
||||
```bash
|
||||
python deploy_filter.py folder-memory
|
||||
python deploy_filter.py context_enhancement_filter
|
||||
```
|
||||
|
||||
## 🔧 How It Works
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────┐
|
||||
│ 1. Load API key (.env) │
|
||||
└──────────────────┬──────────────────────────────────────────┘
|
||||
│
|
||||
┌──────────────────▼──────────────────────────────────────────┐
|
||||
│ 2. Find Filter plugin file │
|
||||
│ - Infer file path from name │
|
||||
│ - Support hyphen-case and snake_case lookup │
|
||||
└──────────────────┬──────────────────────────────────────────┘
|
||||
│
|
||||
┌──────────────────▼──────────────────────────────────────────┐
|
||||
│ 3. Read Python source code │
|
||||
│ - Extract docstring metadata │
|
||||
│ - title, version, author, description, openwebui_id │
|
||||
└──────────────────┬──────────────────────────────────────────┘
|
||||
│
|
||||
┌──────────────────▼──────────────────────────────────────────┐
|
||||
│ 4. Build API request payload │
|
||||
│ - Assemble manifest and meta info │
|
||||
│ - Include complete source code content │
|
||||
└──────────────────┬──────────────────────────────────────────┘
|
||||
│
|
||||
┌──────────────────▼──────────────────────────────────────────┐
|
||||
│ 5. Send request │
|
||||
│ - POST /api/v1/functions/id/{id}/update (update) │
|
||||
│ - POST /api/v1/functions/create (create fallback) │
|
||||
└──────────────────┬──────────────────────────────────────────┘
|
||||
│
|
||||
┌──────────────────▼──────────────────────────────────────────┐
|
||||
│ 6. Display results and diagnostics │
|
||||
│ - ✅ Update/create success │
|
||||
│ - ❌ Error messages and solutions │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## 📊 Supported Filters List
|
||||
|
||||
Script auto-discovers the following Filters:
|
||||
|
||||
| Filter Name | Python File | Version |
|
||||
|-----------|-----------|------|
|
||||
| async-context-compression | async_context_compression.py | 1.3.0+ |
|
||||
| chat-session-mapping-filter | chat_session_mapping_filter.py | 0.1.0+ |
|
||||
| context_enhancement_filter | context_enhancement_filter.py | 0.3+ |
|
||||
| folder-memory | folder_memory.py | 0.1.0+ |
|
||||
| github_copilot_sdk_files_filter | github_copilot_sdk_files_filter.py | 0.1.3+ |
|
||||
| markdown_normalizer | markdown_normalizer.py | 1.2.8+ |
|
||||
| web_gemini_multimodel_filter | web_gemini_multimodel_filter.py | 0.3.2+ |
|
||||
|
||||
## ⚙️ Technical Details
|
||||
|
||||
### Metadata Extraction
|
||||
|
||||
Script extracts metadata from the docstring at the top of Python file:
|
||||
|
||||
```python
|
||||
"""
|
||||
title: Async Context Compression
|
||||
id: async_context_compression
|
||||
author: Fu-Jie
|
||||
author_url: https://github.com/Fu-Jie/openwebui-extensions
|
||||
funding_url: https://github.com/open-webui
|
||||
description: Reduces token consumption...
|
||||
version: 1.3.0
|
||||
openwebui_id: b1655bc8-6de9-4cad-8cb5-a6f7829a02ce
|
||||
"""
|
||||
```
|
||||
|
||||
**Supported Metadata Fields**:
|
||||
- `title` — Filter display name ✅
|
||||
- `id` — Unique identifier ✅
|
||||
- `author` — Author name ✅
|
||||
- `author_url` — Author homepage ✅
|
||||
- `funding_url` — Project link ✅
|
||||
- `description` — Feature description ✅
|
||||
- `version` — Semantic version number ✅
|
||||
- `openwebui_id` — OpenWebUI UUID (optional)
|
||||
|
||||
### API Integration
|
||||
|
||||
Script uses OpenWebUI REST API:
|
||||
|
||||
```
|
||||
POST /api/v1/functions/id/{filter_id}/update
|
||||
- Update existing Filter
|
||||
- HTTP 200: Update success
|
||||
- HTTP 404: Filter not found, auto-attempt create
|
||||
|
||||
POST /api/v1/functions/create
|
||||
- Create new Filter
|
||||
- HTTP 200: Creation success
|
||||
```
|
||||
|
||||
**Authentication**: Bearer token (API key method)
|
||||
|
||||
## 🔐 Security
|
||||
|
||||
### API Key Management
|
||||
|
||||
```bash
|
||||
# 1. Create .env file
|
||||
echo "api_key=sk-your-key-here" > scripts/.env
|
||||
|
||||
# 2. Add .env to .gitignore
|
||||
echo "scripts/.env" >> .gitignore
|
||||
|
||||
# 3. Don't commit API key
|
||||
git add scripts/.gitignore
|
||||
git commit -m "chore: add .env to gitignore"
|
||||
```
|
||||
|
||||
### Best Practices
|
||||
|
||||
- ✅ Use long-term auth tokens (not short-term JWT)
|
||||
- ✅ Rotate API keys periodically
|
||||
- ✅ Limit key permission scope
|
||||
- ✅ Use only on trusted networks
|
||||
- ✅ Use CI/CD secret management in production
|
||||
|
||||
## 🧪 Test Verification
|
||||
|
||||
### Run Test Suite
|
||||
|
||||
```bash
|
||||
pytest tests/scripts/test_deploy_filter.py -v
|
||||
```
|
||||
|
||||
### Test Coverage
|
||||
|
||||
```
|
||||
✅ TestFilterDiscovery (3 tests)
|
||||
- test_find_async_context_compression
|
||||
- test_find_nonexistent_filter
|
||||
- test_find_filter_with_underscores
|
||||
|
||||
✅ TestMetadataExtraction (3 tests)
|
||||
- test_extract_metadata_from_async_compression
|
||||
- test_extract_metadata_empty_file
|
||||
- test_extract_metadata_multiline_docstring
|
||||
|
||||
✅ TestPayloadBuilding (4 tests)
|
||||
- test_build_filter_payload_basic
|
||||
- test_payload_has_required_fields
|
||||
- test_payload_with_openwebui_id
|
||||
|
||||
✅ TestVersionExtraction (1 test)
|
||||
- test_extract_valid_version
|
||||
|
||||
Result: 10/10 PASSED ✅
|
||||
```
|
||||
|
||||
## 💡 Common Use Cases
|
||||
|
||||
### Use Case 1: Quick Test After Bug Fix
|
||||
|
||||
```bash
|
||||
# 1. Modify code
|
||||
vim plugins/filters/async-context-compression/async_context_compression.py
|
||||
|
||||
# 2. Deploy immediately (no OpenWebUI restart needed)
|
||||
cd scripts && python deploy_filter.py
|
||||
|
||||
# 3. Test fix in OpenWebUI
|
||||
# 4. Iterate (return to step 1)
|
||||
```
|
||||
|
||||
### Use Case 2: Develop New Filter
|
||||
|
||||
```bash
|
||||
# 1. Create new Filter directory
|
||||
mkdir plugins/filters/my-new-filter
|
||||
|
||||
# 2. Write code (include required docstring metadata)
|
||||
cat > plugins/filters/my-new-filter/my_new_filter.py << 'EOF'
|
||||
"""
|
||||
title: My New Filter
|
||||
author: Your Name
|
||||
version: 1.0.0
|
||||
description: Filter description
|
||||
"""
|
||||
|
||||
class Filter:
|
||||
# ... implementation ...
|
||||
EOF
|
||||
|
||||
# 3. First deployment (create)
|
||||
cd scripts && python deploy_filter.py my-new-filter
|
||||
|
||||
# 4. Test in OpenWebUI UI
|
||||
# 5. Repeat updates
|
||||
cd scripts && python deploy_filter.py my-new-filter
|
||||
```
|
||||
|
||||
### Use Case 3: Version Update and Release
|
||||
|
||||
```bash
|
||||
# 1. Update version number
|
||||
vim plugins/filters/async-context-compression/async_context_compression.py
|
||||
# Change: version: 1.3.0 → version: 1.4.0
|
||||
|
||||
# 2. Deploy new version
|
||||
cd scripts && python deploy_filter.py
|
||||
|
||||
# 3. After testing, commit
|
||||
git add plugins/filters/async-context-compression/
|
||||
git commit -m "feat(filters): update async-context-compression to 1.4.0"
|
||||
git push
|
||||
```
|
||||
|
||||
## 🔄 CI/CD Integration
|
||||
|
||||
### GitHub Actions Example
|
||||
|
||||
```yaml
|
||||
name: Deploy Filter on Release
|
||||
|
||||
on:
|
||||
release:
|
||||
types: [published]
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
- name: Deploy Filter
|
||||
run: |
|
||||
cd scripts
|
||||
python deploy_filter.py async-context-compression
|
||||
env:
|
||||
api_key: ${{ secrets.OPENWEBUI_API_KEY }}
|
||||
```
|
||||
|
||||
## 📚 Reference Documentation
|
||||
|
||||
- [Complete Deployment Guide](DEPLOYMENT_GUIDE.md)
|
||||
- [Quick Reference Card](QUICK_START.md)
|
||||
- [Test Suite](../tests/scripts/test_deploy_filter.py)
|
||||
- [Plugin Development Guide](../docs/development/plugin-guide.md)
|
||||
- [OpenWebUI Documentation](https://docs.openwebui.com/)
|
||||
|
||||
## 🎓 Learning Resources
|
||||
|
||||
### Architecture Understanding
|
||||
|
||||
```
|
||||
OpenWebUI System Design
|
||||
↓
|
||||
Filter Plugin Type Definition
|
||||
↓
|
||||
REST API Interface (/api/v1/functions)
|
||||
↓
|
||||
Local Deployment Script Implementation (deploy_filter.py)
|
||||
↓
|
||||
Metadata Extraction and Delivery
|
||||
```
|
||||
|
||||
### Debugging Tips
|
||||
|
||||
1. **Enable Verbose Logging**:
|
||||
```bash
|
||||
python deploy_filter.py 2>&1 | tee deploy.log
|
||||
```
|
||||
|
||||
2. **Test API Connection**:
|
||||
```bash
|
||||
curl -X GET http://localhost:3000/api/v1/functions \
|
||||
-H "Authorization: Bearer $API_KEY"
|
||||
```
|
||||
|
||||
3. **Verify .env File**:
|
||||
```bash
|
||||
grep "api_key=" scripts/.env
|
||||
```
|
||||
|
||||
## 📞 Troubleshooting
|
||||
|
||||
| Issue | Diagnosis | Solution |
|
||||
|-------|-----------|----------|
|
||||
| Connection error | Wrong OpenWebUI address/port | Check localhost:3000; modify URL if needed |
|
||||
| .env not found | Config file not created | `echo "api_key=sk-..." > scripts/.env` |
|
||||
| Filter not found | Wrong Plugin name | Run `python deploy_filter.py --list` |
|
||||
| Status 401 | Invalid/expired API key | Update key in `.env` |
|
||||
| Status 500 | Server error | Check OpenWebUI service logs |
|
||||
|
||||
## ✨ Highlight Features
|
||||
|
||||
| Feature | Description |
|
||||
|---------|-------------|
|
||||
| 🔍 Auto Discovery | Automatically find all Filter plugins |
|
||||
| 📊 Metadata Extraction | Auto-extract version and metadata from code |
|
||||
| ♻️ Auto-update | Smart handling of update or create |
|
||||
| 🛡️ Error Handling | Detailed error messages and diagnostics |
|
||||
| 🚀 Fast Iteration | Second-level deployment, no restart |
|
||||
| 🧪 Complete Testing | 10 unit tests covering core functions |
|
||||
|
||||
---
|
||||
|
||||
**Last Updated**: 2026-03-09
|
||||
**Author**: Fu-Jie
|
||||
**Project**: [openwebui-extensions](https://github.com/Fu-Jie/openwebui-extensions)
|
||||
113
scripts/QUICK_START.md
Normal file
113
scripts/QUICK_START.md
Normal file
@@ -0,0 +1,113 @@
|
||||
# ⚡ Quick Deployment Reference
|
||||
|
||||
## One-line Deploy Commands
|
||||
|
||||
```bash
|
||||
# Deploy async_context_compression Filter (default)
|
||||
cd scripts && python deploy_filter.py
|
||||
|
||||
# List all available Filters
|
||||
cd scripts && python deploy_filter.py --list
|
||||
```
|
||||
|
||||
## Setup Steps (One time only)
|
||||
|
||||
```bash
|
||||
# 1. Enter scripts directory
|
||||
cd scripts
|
||||
|
||||
# 2. Create .env file with your OpenWebUI API key
|
||||
echo "api_key=sk-your-api-key-here" > .env
|
||||
|
||||
# 3. Make sure OpenWebUI is running on localhost:3000
|
||||
```
|
||||
|
||||
## Get Your API Key
|
||||
|
||||
1. Open OpenWebUI → user avatar → Settings
|
||||
2. Find "API Keys" section
|
||||
3. Copy your key (starts with sk-)
|
||||
4. Paste into `.env` file
|
||||
|
||||
## Deployment Workflow
|
||||
|
||||
```bash
|
||||
# 1. Edit plugin code
|
||||
vim ../plugins/filters/async-context-compression/async_context_compression.py
|
||||
|
||||
# 2. Deploy to local
|
||||
python deploy_filter.py
|
||||
|
||||
# 3. Test in OpenWebUI (no restart needed)
|
||||
|
||||
# 4. Deploy again (auto-overwrites)
|
||||
python deploy_filter.py
|
||||
```
|
||||
|
||||
## Common Commands
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `python deploy_filter.py` | Deploy async_context_compression |
|
||||
| `python deploy_filter.py filter-name` | Deploy specific Filter |
|
||||
| `python deploy_filter.py --list` | List all available Filters |
|
||||
| `python deploy_pipe.py` | Deploy GitHub Copilot SDK Pipe |
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
| Error | Cause | Solution |
|
||||
|-------|-------|----------|
|
||||
| Connection error | OpenWebUI not running | Start OpenWebUI or check port |
|
||||
| .env not found | Config file not created | `echo "api_key=sk-..." > .env` |
|
||||
| Filter not found | Filter name is wrong | Run `python deploy_filter.py --list` |
|
||||
| Status 401 | API key invalid | Update key in `.env` |
|
||||
|
||||
## File Locations
|
||||
|
||||
```
|
||||
openwebui-extensions/
|
||||
├── scripts/
|
||||
│ ├── deploy_filter.py ← Filter deployment tool
|
||||
│ ├── deploy_pipe.py ← Pipe deployment tool
|
||||
│ ├── .env ← API key (don't commit)
|
||||
│ └── DEPLOYMENT_GUIDE.md ← Full guide
|
||||
│
|
||||
└── plugins/
|
||||
└── filters/
|
||||
└── async-context-compression/
|
||||
├── async_context_compression.py
|
||||
├── README.md
|
||||
└── README_CN.md
|
||||
```
|
||||
|
||||
## Suggested Workflow
|
||||
|
||||
### Fast Iterative Development
|
||||
|
||||
```bash
|
||||
# Terminal 1: Start OpenWebUI (if not running)
|
||||
docker run -d -p 3000:8080 ghcr.io/open-webui/open-webui:latest
|
||||
|
||||
# Terminal 2: Development loop (repeated)
|
||||
cd scripts
|
||||
code ../plugins/filters/async-context-compression/ # Edit code
|
||||
python deploy_filter.py # Deploy
|
||||
# → Test in OpenWebUI
|
||||
# → Go back to edit, repeat
|
||||
```
|
||||
|
||||
### CI/CD Integration
|
||||
|
||||
```bash
|
||||
# In GitHub Actions
|
||||
- name: Deploy filter to staging
|
||||
run: |
|
||||
cd scripts
|
||||
python deploy_filter.py async-context-compression
|
||||
env:
|
||||
api_key: ${{ secrets.OPENWEBUI_API_KEY }}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
📚 **More Help**: See `DEPLOYMENT_GUIDE.md`
|
||||
476
scripts/README.md
Normal file
476
scripts/README.md
Normal file
@@ -0,0 +1,476 @@
|
||||
# 🚀 Deployment Scripts Guide
|
||||
|
||||
## 📁 Deployment Tools
|
||||
|
||||
To support quick local deployment of async_context_compression and other Filter plugins, we've added the following files:
|
||||
|
||||
### File Inventory
|
||||
|
||||
```
|
||||
scripts/
|
||||
├── install_all_plugins.py ✨ Batch install Action/Filter/Pipe/Tool plugins
|
||||
├── deploy_filter.py ✨ Generic Filter deployment tool
|
||||
├── deploy_tool.py ✨ Tool plugin deployment tool
|
||||
├── deploy_async_context_compression.py ✨ Async Context Compression quick deploy
|
||||
├── deploy_pipe.py (existing) Pipe deployment tool
|
||||
├── DEPLOYMENT_GUIDE.md ✨ Complete deployment guide
|
||||
├── DEPLOYMENT_SUMMARY.md ✨ Deploy feature summary
|
||||
├── QUICK_START.md ✨ Quick reference card
|
||||
├── .env (create as needed) API key configuration
|
||||
└── ...other existing scripts
|
||||
```
|
||||
|
||||
## ⚡ Quick Start (30 seconds)
|
||||
|
||||
### Step 1: Prepare Your API Key
|
||||
|
||||
```bash
|
||||
cd scripts
|
||||
|
||||
# Get your OpenWebUI API key:
|
||||
# 1. Open OpenWebUI → User menu → Settings
|
||||
# 2. Find the "API Keys" section
|
||||
# 3. Copy your key (starts with sk-)
|
||||
|
||||
# Create .env file
|
||||
cat > .env <<'EOF'
|
||||
api_key=sk-your-key-here
|
||||
url=http://localhost:3000
|
||||
EOF
|
||||
```
|
||||
|
||||
### Step 2a: Install All Plugins (Recommended)
|
||||
|
||||
```bash
|
||||
python install_all_plugins.py
|
||||
```
|
||||
|
||||
### Step 2b: Or Deploy Individual Plugins
|
||||
|
||||
```bash
|
||||
# Easiest way - dedicated script
|
||||
python deploy_async_context_compression.py
|
||||
|
||||
# Or use generic script
|
||||
python deploy_filter.py
|
||||
|
||||
# Or specify plugin name
|
||||
python deploy_filter.py async-context-compression
|
||||
|
||||
# Or deploy a Tool
|
||||
python deploy_tool.py
|
||||
```
|
||||
|
||||
## 📋 Deployment Tools Detailed
|
||||
|
||||
### 1️⃣ `deploy_async_context_compression.py` — Dedicated Deployment Script
|
||||
|
||||
**The simplest way to deploy!**
|
||||
|
||||
```bash
|
||||
cd scripts
|
||||
python deploy_async_context_compression.py
|
||||
```
|
||||
|
||||
**Features**:
|
||||
- ✅ Optimized specifically for async_context_compression
|
||||
- ✅ Clear deployment steps and confirmation
|
||||
- ✅ Friendly error messages
|
||||
- ✅ Shows next steps after successful deployment
|
||||
|
||||
**Sample Output**:
|
||||
```
|
||||
======================================================================
|
||||
🚀 Deploying Async Context Compression Filter Plugin
|
||||
======================================================================
|
||||
|
||||
📦 Deploying filter 'Async Context Compression' (version 1.3.0)...
|
||||
File: /path/to/async_context_compression.py
|
||||
✅ Successfully updated 'Async Context Compression' filter!
|
||||
|
||||
======================================================================
|
||||
✅ Deployment successful!
|
||||
======================================================================
|
||||
|
||||
Next steps:
|
||||
1. Open OpenWebUI in your browser: http://localhost:3000
|
||||
2. Go to Settings → Filters
|
||||
3. Enable 'Async Context Compression'
|
||||
4. Configure Valves as needed
|
||||
5. Start using the filter in conversations
|
||||
```
|
||||
|
||||
### 2️⃣ `deploy_filter.py` — Generic Filter Deployment Tool
|
||||
|
||||
**Supports all Filter plugins!**
|
||||
|
||||
```bash
|
||||
# Deploy default async_context_compression
|
||||
python deploy_filter.py
|
||||
|
||||
# Deploy other Filters
|
||||
python deploy_filter.py folder-memory
|
||||
python deploy_filter.py context_enhancement_filter
|
||||
|
||||
# List all available Filters
|
||||
python deploy_filter.py --list
|
||||
```
|
||||
|
||||
**Features**:
|
||||
- ✅ Generic Filter deployment tool
|
||||
- ✅ Supports multiple plugins
|
||||
- ✅ Auto metadata extraction
|
||||
- ✅ Smart update/create logic
|
||||
- ✅ Complete error diagnostics
|
||||
|
||||
### 3️⃣ `deploy_pipe.py` — Pipe Deployment Tool
|
||||
|
||||
```bash
|
||||
python deploy_pipe.py
|
||||
```
|
||||
|
||||
Used to deploy Pipe-type plugins (like GitHub Copilot SDK).
|
||||
|
||||
### 3️⃣+ `deploy_tool.py` — Tool Deployment Tool
|
||||
|
||||
```bash
|
||||
# Deploy default Tool
|
||||
python deploy_tool.py
|
||||
|
||||
# Or specify a specific Tool
|
||||
python deploy_tool.py openwebui-skills-manager
|
||||
```
|
||||
|
||||
**Features**:
|
||||
- ✅ Supports Tools plugin deployment
|
||||
- ✅ Auto-detects `Tools` class definition
|
||||
- ✅ Smart update/create logic
|
||||
- ✅ Complete error diagnostics
|
||||
|
||||
**Use Case**:
|
||||
Deploy or reinstall a specific Tool individually, or deploy only Tools without running full batch installation. The script now calls OpenWebUI's native `/api/v1/tools/*` endpoints.
|
||||
|
||||
### 4️⃣ `install_all_plugins.py` — Batch Installation Script
|
||||
|
||||
One-command installation of all repository plugins that meet these criteria:
|
||||
|
||||
- Located in `plugins/actions`, `plugins/filters`, `plugins/pipes`, `plugins/tools`
|
||||
- Plugin header contains `openwebui_id`
|
||||
- Filename is not in Chinese characters
|
||||
- Filename does not end with `_cn.py`
|
||||
|
||||
```bash
|
||||
# Check which plugins will be installed
|
||||
python install_all_plugins.py --list
|
||||
|
||||
# Dry-run without calling API
|
||||
python install_all_plugins.py --dry-run
|
||||
|
||||
# Actually install all supported types (including Action/Filter/Pipe/Tool)
|
||||
python install_all_plugins.py
|
||||
|
||||
# Install only specific types
|
||||
python install_all_plugins.py --types pipe action
|
||||
```
|
||||
|
||||
The script prioritizes updating existing plugins and automatically creates new ones.
|
||||
|
||||
**Tool Integration**: Tool-type plugins now automatically use OpenWebUI's native `/api/v1/tools/create` and `/api/v1/tools/id/{id}/update` endpoints, no longer reusing the `functions` endpoint.
|
||||
|
||||
## 🔧 How It Works
|
||||
|
||||
```
|
||||
Your code changes
|
||||
↓
|
||||
Run deployment script
|
||||
↓
|
||||
Script reads the corresponding plugin file
|
||||
↓
|
||||
Auto-extracts metadata from code (title, version, author, etc.)
|
||||
↓
|
||||
Builds API request
|
||||
↓
|
||||
Sends to local OpenWebUI
|
||||
↓
|
||||
OpenWebUI updates or creates plugin
|
||||
↓
|
||||
Takes effect immediately! (no restart needed)
|
||||
```
|
||||
|
||||
## 📊 Available Filter List
|
||||
|
||||
Use `python deploy_filter.py --list` to see all available Filters:
|
||||
|
||||
| Filter Name | Python File | Description |
|
||||
|-----------|-----------|------|
|
||||
| **async-context-compression** | async_context_compression.py | Async context compression |
|
||||
| chat-session-mapping-filter | chat_session_mapping_filter.py | Chat session mapping |
|
||||
| context_enhancement_filter | context_enhancement_filter.py | Context enhancement |
|
||||
| folder-memory | folder_memory.py | Folder memory |
|
||||
| github_copilot_sdk_files_filter | github_copilot_sdk_files_filter.py | Copilot SDK Files |
|
||||
| markdown_normalizer | markdown_normalizer.py | Markdown normalization |
|
||||
| web_gemini_multimodel_filter | web_gemini_multimodel_filter.py | Gemini multimodal |
|
||||
|
||||
## 🎯 Common Use Cases
|
||||
|
||||
### Scenario 1: Deploy After Feature Development
|
||||
|
||||
```bash
|
||||
# 1. Modify code
|
||||
vim ../plugins/filters/async-context-compression/async_context_compression.py
|
||||
|
||||
# 2. Update version number (optional)
|
||||
# version: 1.3.0 → 1.3.1
|
||||
|
||||
# 3. Deploy
|
||||
python deploy_async_context_compression.py
|
||||
|
||||
# 4. Test in OpenWebUI
|
||||
# → No restart needed, takes effect immediately!
|
||||
|
||||
# 5. Continue development and repeat
|
||||
```
|
||||
|
||||
### Scenario 2: Fix Bug and Verify Quickly
|
||||
|
||||
```bash
|
||||
# 1. Find and fix bug
|
||||
vim ../plugins/filters/async-context-compression/async_context_compression.py
|
||||
|
||||
# 2. Quick deploy to verify
|
||||
python deploy_async_context_compression.py
|
||||
|
||||
# 3. Test bug fix in OpenWebUI
|
||||
# One-command deploy, instant feedback!
|
||||
```
|
||||
|
||||
### Scenario 3: Deploy Multiple Filters
|
||||
|
||||
```bash
|
||||
# Deploy all Filters that need updates
|
||||
python deploy_filter.py async-context-compression
|
||||
python deploy_filter.py folder-memory
|
||||
python deploy_filter.py context_enhancement_filter
|
||||
```
|
||||
|
||||
## 🔐 Security Tips
|
||||
|
||||
### Manage API Keys
|
||||
|
||||
```bash
|
||||
# 1. Create .env (local only)
|
||||
echo "api_key=sk-your-key" > .env
|
||||
|
||||
# 2. Add to .gitignore (prevent commit)
|
||||
echo "scripts/.env" >> ../.gitignore
|
||||
|
||||
# 3. Verify it won't be committed
|
||||
git status # should not show .env
|
||||
|
||||
# 4. Rotate keys regularly
|
||||
# → Generate new key in OpenWebUI Settings
|
||||
# → Update .env file
|
||||
```
|
||||
|
||||
### ✅ Security Checklist
|
||||
|
||||
- [ ] `.env` file is in `.gitignore`
|
||||
- [ ] Never hardcode API keys in code
|
||||
- [ ] Rotate API keys periodically
|
||||
- [ ] Use only on trusted networks
|
||||
- [ ] Use CI/CD secret management in production
|
||||
|
||||
## ❌ Troubleshooting
|
||||
|
||||
### Issue 1: "Connection error"
|
||||
|
||||
```
|
||||
❌ Connection error: Could not reach OpenWebUI at localhost:3000
|
||||
Make sure OpenWebUI is running and accessible.
|
||||
```
|
||||
|
||||
**Solution**:
|
||||
```bash
|
||||
# 1. Check if OpenWebUI is running
|
||||
curl http://localhost:3000
|
||||
|
||||
# 2. If port is different, edit URL in script
|
||||
# Default: http://localhost:3000
|
||||
# Location: "localhost:3000" in deploy_filter.py
|
||||
|
||||
# 3. Check firewall settings
|
||||
```
|
||||
|
||||
### Issue 2: ".env file not found"
|
||||
|
||||
```
|
||||
❌ [ERROR] .env file not found at .env
|
||||
Please create it with: api_key=sk-xxxxxxxxxxxx
|
||||
```
|
||||
|
||||
**Solution**:
|
||||
```bash
|
||||
echo "api_key=sk-your-api-key" > .env
|
||||
cat .env # verify file created
|
||||
```
|
||||
|
||||
### Issue 3: "Filter not found"
|
||||
|
||||
```
|
||||
❌ [ERROR] Filter 'xxx' not found in .../plugins/filters
|
||||
```
|
||||
|
||||
**Solution**:
|
||||
```bash
|
||||
# List all available Filters
|
||||
python deploy_filter.py --list
|
||||
|
||||
# Retry with correct name
|
||||
python deploy_filter.py async-context-compression
|
||||
```
|
||||
|
||||
### Issue 4: "Status 401" (Unauthorized)
|
||||
|
||||
```
|
||||
❌ Failed to update or create. Status: 401
|
||||
Error: {"error": "Unauthorized"}
|
||||
```
|
||||
|
||||
**Solution**:
|
||||
```bash
|
||||
# 1. Verify API key is correct
|
||||
grep "api_key=" .env
|
||||
|
||||
# 2. Check if key is still valid in OpenWebUI
|
||||
# Settings → API Keys → Check
|
||||
|
||||
# 3. Generate new key and update .env
|
||||
echo "api_key=sk-new-key" > .env
|
||||
```
|
||||
|
||||
## 📖 Documentation Navigation
|
||||
|
||||
| Document | Description |
|
||||
|------|------|
|
||||
| **README.md** (this file) | Quick reference and FAQs |
|
||||
| [QUICK_START.md](QUICK_START.md) | One-page cheat sheet |
|
||||
| [DEPLOYMENT_GUIDE.md](DEPLOYMENT_GUIDE.md) | Complete detailed guide |
|
||||
| [DEPLOYMENT_SUMMARY.md](DEPLOYMENT_SUMMARY.md) | Technical architecture |
|
||||
|
||||
## 🧪 Verify Deployment Success
|
||||
|
||||
### Method 1: Check Script Output
|
||||
|
||||
```bash
|
||||
python deploy_async_context_compression.py
|
||||
|
||||
# Success indicator:
|
||||
✅ Successfully updated 'Async Context Compression' filter!
|
||||
```
|
||||
|
||||
### Method 2: Verify in OpenWebUI
|
||||
|
||||
1. Open OpenWebUI: http://localhost:3000
|
||||
2. Go to Settings → Filters
|
||||
3. Check if 'Async Context Compression' is listed
|
||||
4. Verify version number is correct (should be latest)
|
||||
|
||||
### Method 3: Test Plugin Functionality
|
||||
|
||||
1. Open a new conversation
|
||||
2. Enable 'Async Context Compression' Filter
|
||||
3. Have multiple-turn conversation and verify compression/summarization works
|
||||
## 💡 Advanced Usage
|
||||
|
||||
### Automated Deploy & Test
|
||||
|
||||
```bash
|
||||
#!/bin/bash
|
||||
# deploy_and_test.sh
|
||||
|
||||
echo "Deploying plugin..."
|
||||
python scripts/deploy_async_context_compression.py
|
||||
|
||||
if [ $? -eq 0 ]; then
|
||||
echo "✅ Deploy successful, running tests..."
|
||||
python -m pytest tests/plugins/filters/async-context-compression/ -v
|
||||
else
|
||||
echo "❌ Deploy failed"
|
||||
exit 1
|
||||
fi
|
||||
```
|
||||
|
||||
### CI/CD Integration
|
||||
|
||||
```yaml
|
||||
# .github/workflows/deploy.yml
|
||||
name: Deploy on Push
|
||||
|
||||
on: [push]
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v4
|
||||
|
||||
- name: Deploy Async Context Compression
|
||||
run: python scripts/deploy_async_context_compression.py
|
||||
env:
|
||||
api_key: ${{ secrets.OPENWEBUI_API_KEY }}
|
||||
```
|
||||
|
||||
## 📞 Getting Help
|
||||
|
||||
### Check Script Status
|
||||
|
||||
```bash
|
||||
# List all available scripts
|
||||
ls -la scripts/*.py
|
||||
|
||||
# Check if deployment scripts exist
|
||||
ls -la scripts/deploy_*.py
|
||||
```
|
||||
|
||||
### View Script Help
|
||||
|
||||
```bash
|
||||
# View help (if supported)
|
||||
python scripts/deploy_filter.py --help # if supported
|
||||
python scripts/deploy_async_context_compression.py --help
|
||||
```
|
||||
|
||||
### Debug Mode
|
||||
|
||||
```bash
|
||||
# Save output to log file
|
||||
python scripts/deploy_async_context_compression.py | tee deploy.log
|
||||
|
||||
# Check log
|
||||
cat deploy.log
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📝 File Checklist
|
||||
|
||||
Newly created deployment-related files:
|
||||
|
||||
```
|
||||
✨ scripts/deploy_filter.py (new) ~300 lines
|
||||
✨ scripts/deploy_async_context_compression.py (new) ~70 lines
|
||||
✨ scripts/DEPLOYMENT_GUIDE.md (new) complete guide
|
||||
✨ scripts/DEPLOYMENT_SUMMARY.md (new) technical summary
|
||||
✨ scripts/QUICK_START.md (new) quick reference
|
||||
📄 tests/scripts/test_deploy_filter.py (new) 10 unit tests ✅
|
||||
|
||||
✅ All files created and tested successfully!
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Last Updated**: 2026-03-09
|
||||
**Script Status**: ✅ Ready for production
|
||||
**Test Coverage**: 10/10 passed ✅
|
||||
|
||||
345
scripts/UPDATE_MECHANISM.md
Normal file
345
scripts/UPDATE_MECHANISM.md
Normal file
@@ -0,0 +1,345 @@
|
||||
# 🔄 Deployment Scripts Update Mechanism
|
||||
|
||||
## Core Answer
|
||||
|
||||
✅ **Yes, re-deploying automatically updates the plugin!**
|
||||
|
||||
The deployment script uses a **smart two-stage strategy**:
|
||||
1. 🔄 **Try UPDATE First** (if plugin exists)
|
||||
2. 📝 **Auto CREATE** (if update fails — plugin doesn't exist)
|
||||
|
||||
## Workflow Diagram
|
||||
|
||||
```
|
||||
Run deploy script
|
||||
↓
|
||||
Read local code and metadata
|
||||
↓
|
||||
Send UPDATE request to OpenWebUI
|
||||
↓
|
||||
├─ HTTP 200 ✅
|
||||
│ └─ Plugin exists → Update successful!
|
||||
│
|
||||
└─ Other status codes (404, 400, etc.)
|
||||
└─ Plugin doesn't exist or update failed
|
||||
↓
|
||||
Send CREATE request
|
||||
↓
|
||||
├─ HTTP 200 ✅
|
||||
│ └─ Creation successful!
|
||||
│
|
||||
└─ Failed
|
||||
└─ Display error message
|
||||
```
|
||||
|
||||
## Detailed Step-by-step
|
||||
|
||||
### Step 1️⃣: Try UPDATE First
|
||||
|
||||
```python
|
||||
# Code location: deploy_filter.py line 220-230
|
||||
|
||||
update_url = "http://localhost:3000/api/v1/functions/id/{filter_id}/update"
|
||||
|
||||
response = requests.post(
|
||||
update_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
print(f"✅ Successfully updated '{title}' filter!")
|
||||
return True
|
||||
```
|
||||
|
||||
**What Happens**:
|
||||
- Send **POST** to `/api/v1/functions/id/{filter_id}/update`
|
||||
- If returns **HTTP 200**, plugin exists and update succeeded
|
||||
- Includes:
|
||||
- Complete latest code
|
||||
- Metadata (title, version, author, description, etc.)
|
||||
- Manifest information
|
||||
|
||||
### Step 2️⃣: If UPDATE Fails, Try CREATE
|
||||
|
||||
```python
|
||||
# Code location: deploy_filter.py line 231-245
|
||||
|
||||
if response.status_code != 200:
|
||||
print(f"⚠️ Update failed with status {response.status_code}, "
|
||||
"attempting to create instead...")
|
||||
|
||||
create_url = "http://localhost:3000/api/v1/functions/create"
|
||||
res_create = requests.post(
|
||||
create_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
if res_create.status_code == 200:
|
||||
print(f"✅ Successfully created '{title}' filter!")
|
||||
return True
|
||||
```
|
||||
|
||||
**What Happens**:
|
||||
- If update fails (HTTP ≠ 200), auto-attempt create
|
||||
- Send **POST** to `/api/v1/functions/create`
|
||||
- Uses **same payload** (code, metadata identical)
|
||||
- If creation succeeds, first deployment to OpenWebUI
|
||||
|
||||
## Real-world Scenarios
|
||||
|
||||
### Scenario A: First Deployment
|
||||
|
||||
```bash
|
||||
$ python deploy_async_context_compression.py
|
||||
|
||||
📦 Deploying filter 'Async Context Compression' (version 1.3.0)...
|
||||
File: .../async_context_compression.py
|
||||
⚠️ Update failed with status 404, attempting to create instead... ← First time, plugin doesn't exist
|
||||
✅ Successfully created 'Async Context Compression' filter! ← Creation succeeds
|
||||
```
|
||||
|
||||
**What Happens**:
|
||||
1. Try UPDATE → fails (HTTP 404 — plugin doesn't exist)
|
||||
2. Auto-try CREATE → succeeds (HTTP 200)
|
||||
3. Plugin created in OpenWebUI
|
||||
|
||||
---
|
||||
|
||||
### Scenario B: Re-deploy After Code Changes
|
||||
|
||||
```bash
|
||||
# Made first code change, deploying again
|
||||
$ python deploy_async_context_compression.py
|
||||
|
||||
📦 Deploying filter 'Async Context Compression' (version 1.3.1)...
|
||||
File: .../async_context_compression.py
|
||||
✅ Successfully updated 'Async Context Compression' filter! ← Direct update!
|
||||
```
|
||||
|
||||
**What Happens**:
|
||||
1. Read modified code
|
||||
2. Try UPDATE → succeeds (HTTP 200 — plugin exists)
|
||||
3. Plugin in OpenWebUI updated to latest code
|
||||
4. **No need to restart OpenWebUI**, takes effect immediately!
|
||||
|
||||
---
|
||||
|
||||
### Scenario C: Multiple Fast Iterations
|
||||
|
||||
```bash
|
||||
# 1st change
|
||||
$ python deploy_async_context_compression.py
|
||||
✅ Successfully updated 'Async Context Compression' filter!
|
||||
|
||||
# 2nd change
|
||||
$ python deploy_async_context_compression.py
|
||||
✅ Successfully updated 'Async Context Compression' filter!
|
||||
|
||||
# 3rd change
|
||||
$ python deploy_async_context_compression.py
|
||||
✅ Successfully updated 'Async Context Compression' filter!
|
||||
|
||||
# ... repeat infinitely ...
|
||||
```
|
||||
|
||||
**Characteristics**:
|
||||
- 🚀 Each update takes only 5 seconds
|
||||
- 📝 Each is an incremental update
|
||||
- ✅ No need to restart OpenWebUI
|
||||
- 🔄 Can repeat indefinitely
|
||||
|
||||
## What Gets Updated
|
||||
|
||||
Each deployment updates the following:
|
||||
|
||||
✅ **Code** — All latest Python code
|
||||
✅ **Version** — Auto-extracted from docstring
|
||||
✅ **Title** — Plugin display name
|
||||
✅ **Author Info** — author, author_url
|
||||
✅ **Description** — Plugin description
|
||||
✅ **Metadata** — funding_url, openwebui_id, etc.
|
||||
|
||||
❌ **Configuration NOT Overwritten** — User's Valves settings in OpenWebUI stay unchanged
|
||||
|
||||
## Version Number Management
|
||||
|
||||
### Does Version Change on Update?
|
||||
|
||||
✅ **Yes!**
|
||||
|
||||
```python
|
||||
# docstring in async_context_compression.py
|
||||
|
||||
"""
|
||||
title: Async Context Compression
|
||||
version: 1.3.0
|
||||
"""
|
||||
```
|
||||
|
||||
**Each deployment**:
|
||||
1. Script reads version from docstring
|
||||
2. Sends this version in manifest to OpenWebUI
|
||||
3. If you change version in code, deployment updates to new version
|
||||
|
||||
**Best Practice**:
|
||||
```bash
|
||||
# 1. Modify code
|
||||
vim async_context_compression.py
|
||||
|
||||
# 2. Update version (in docstring)
|
||||
# version: 1.3.0 → 1.3.1
|
||||
|
||||
# 3. Deploy
|
||||
python deploy_async_context_compression.py
|
||||
|
||||
# Result: OpenWebUI shows version 1.3.1
|
||||
```
|
||||
|
||||
## Deployment Failure Cases
|
||||
|
||||
### Case 1: Network Error
|
||||
|
||||
```bash
|
||||
❌ Connection error: Could not reach OpenWebUI at localhost:3000
|
||||
Make sure OpenWebUI is running and accessible.
|
||||
```
|
||||
|
||||
**Cause**: OpenWebUI not running or wrong port
|
||||
**Solution**: Check if OpenWebUI is running
|
||||
|
||||
### Case 2: Invalid API Key
|
||||
|
||||
```bash
|
||||
❌ Failed to update or create. Status: 401
|
||||
Error: {"error": "Unauthorized"}
|
||||
```
|
||||
|
||||
**Cause**: API key in .env is invalid or expired
|
||||
**Solution**: Update api_key in `.env` file
|
||||
|
||||
### Case 3: Server Error
|
||||
|
||||
```bash
|
||||
❌ Failed to update or create. Status: 500
|
||||
Error: Internal server error
|
||||
```
|
||||
|
||||
**Cause**: OpenWebUI server internal error
|
||||
**Solution**: Check OpenWebUI logs
|
||||
|
||||
## Setting Version Numbers — Best Practices
|
||||
|
||||
### Semantic Versioning
|
||||
|
||||
Follow `MAJOR.MINOR.PATCH` format:
|
||||
|
||||
```python
|
||||
"""
|
||||
version: 1.3.0
|
||||
│ │ │
|
||||
│ │ └─ PATCH: Bug fixes (1.3.0 → 1.3.1)
|
||||
│ └────── MINOR: New features (1.3.0 → 1.4.0)
|
||||
└───────── MAJOR: Breaking changes (1.3.0 → 2.0.0)
|
||||
"""
|
||||
```
|
||||
|
||||
**Examples**:
|
||||
|
||||
```python
|
||||
# Bug fix (PATCH)
|
||||
version: 1.3.0 → 1.3.1
|
||||
|
||||
# New feature (MINOR)
|
||||
version: 1.3.0 → 1.4.0
|
||||
|
||||
# Major update (MAJOR)
|
||||
version: 1.3.0 → 2.0.0
|
||||
```
|
||||
|
||||
## Complete Iteration Workflow
|
||||
|
||||
```bash
|
||||
# 1. First deployment
|
||||
cd scripts
|
||||
python deploy_async_context_compression.py
|
||||
# Result: Plugin created (first time)
|
||||
|
||||
# 2. Modify code
|
||||
vim ../plugins/filters/async-context-compression/async_context_compression.py
|
||||
# Edit code...
|
||||
|
||||
# 3. Deploy again (auto-update)
|
||||
python deploy_async_context_compression.py
|
||||
# Result: Plugin updated (takes effect immediately, no OpenWebUI restart)
|
||||
|
||||
# 4. Repeat steps 2-3 indefinitely
|
||||
# Modify → Deploy → Test → Improve → Repeat
|
||||
```
|
||||
|
||||
## Benefits of Auto-update
|
||||
|
||||
| Benefit | Details |
|
||||
|---------|---------|
|
||||
| ⚡ **Fast Iteration** | Code change → Deploy (5s) → Test, no waiting |
|
||||
| 🔄 **Auto-detection** | No manual decision between create/update |
|
||||
| 📝 **Version Management** | Version auto-extracted from code |
|
||||
| ✅ **No Restart Needed** | OpenWebUI runs continuously, config stays same |
|
||||
| 🛡️ **Safe Updates** | User settings (Valves) never overwritten |
|
||||
|
||||
## Disable Auto-update? ❌
|
||||
|
||||
Usually **not needed** because:
|
||||
|
||||
1. ✅ Updates are idempotent (same code deployed multiple times = no change)
|
||||
2. ✅ User configuration not modified
|
||||
3. ✅ Version numbers auto-managed
|
||||
4. ✅ Failures auto-rollback
|
||||
|
||||
但如果真的需要控制，可以：
|
||||
- 手动修改脚本 (修改 `deploy_filter.py`)
|
||||
- 或分别使用 UPDATE/CREATE 的具体 API 端点
|
||||
|
||||
## 常见问题
|
||||
|
||||
### Q: 更新是否会丢失用户的配置？
|
||||
|
||||
❌ **不会！**
|
||||
用户在 OpenWebUI 中设置的 Valves (参数配置) 会被保留。
|
||||
|
||||
### Q: 是否可以回到旧版本？
|
||||
|
||||
✅ **可以！**
|
||||
修改代码中的 `version` 号为旧版本，然后重新部署。
|
||||
|
||||
### Q: 更新需要多长时间？
|
||||
|
||||
⚡ **约 5 秒**
|
||||
包括: 读文件 (1s) + 发送请求 (3s) + 响应 (1s)
|
||||
|
||||
### Q: 可以同时部署多个插件吗？
|
||||
|
||||
✅ **可以！**
|
||||
```bash
|
||||
python deploy_filter.py async-context-compression
|
||||
python deploy_filter.py folder-memory
|
||||
python deploy_filter.py context_enhancement_filter
|
||||
```
|
||||
|
||||
### Q: 部署失败了会怎样？
|
||||
|
||||
✅ **OpenWebUI 中的插件保持不变**
|
||||
失败不会修改已部署的插件。
|
||||
|
||||
---
|
||||
|
||||
**总结**: 部署脚本的更新机制完全自动化，开发者只需修改代码，每次运行 `deploy_async_context_compression.py` 就会自动：
|
||||
1. ✅ 创建（第一次）或更新（后续）插件
|
||||
2. ✅ 从代码提取最新的元数据和版本号
|
||||
3. ✅ 立即生效，无需重启 OpenWebUI
|
||||
4. ✅ 保留用户的配置不变
|
||||
|
||||
这使得本地开发和快速迭代变得极其流畅！🚀
|
||||
91
scripts/UPDATE_QUICK_REF.md
Normal file
91
scripts/UPDATE_QUICK_REF.md
Normal file
@@ -0,0 +1,91 @@
|
||||
# 🔄 Quick Reference: Deployment Update Mechanism
|
||||
|
||||
## The Shortest Answer
|
||||
|
||||
✅ **Re-deploying automatically updates the plugin.**
|
||||
|
||||
## How It Works (30-second understanding)
|
||||
|
||||
```
|
||||
Each time you run the deploy script:
|
||||
1. Priority: try UPDATE (if plugin exists) → succeeds
|
||||
2. Fallback: auto CREATE (first deployment) → succeeds
|
||||
|
||||
Result:
|
||||
✅ Works correctly every time, regardless of deployment count
|
||||
✅ No manual judgement needed between create vs update
|
||||
✅ Takes effect immediately, no restart needed
|
||||
```
|
||||
|
||||
## Three Scenarios
|
||||
|
||||
| Scenario | What Happens | Result |
|
||||
|----------|-------------|--------|
|
||||
| **First deployment** | UPDATE fails → CREATE succeeds | ✅ Plugin created |
|
||||
| **Deploy after code change** | UPDATE succeeds directly | ✅ Plugin updates instantly |
|
||||
| **Deploy without changes** | UPDATE succeeds (no change) | ✅ Safe (no effect) |
|
||||
|
||||
## Development Workflow
|
||||
|
||||
```bash
|
||||
# 1. First deployment
|
||||
python deploy_async_context_compression.py
|
||||
# Result: ✅ Created
|
||||
|
||||
# 2. Modify code
|
||||
vim ../plugins/filters/async-context-compression/async_context_compression.py
|
||||
# Edit...
|
||||
|
||||
# 3. Deploy again (auto-update)
|
||||
python deploy_async_context_compression.py
|
||||
# Result: ✅ Updated
|
||||
|
||||
# 4. Continue editing and redeploying
|
||||
# ... can repeat infinitely ...
|
||||
```
|
||||
|
||||
## Key Points
|
||||
|
||||
✅ **Automated** — No need to worry about create vs update
|
||||
✅ **Fast** — Each deployment takes 5 seconds
|
||||
✅ **Safe** — User configuration never gets overwritten
|
||||
✅ **Instant** — No need to restart OpenWebUI
|
||||
✅ **Version Management** — Auto-extracted from code
|
||||
|
||||
## How to Manage Version Numbers?
|
||||
|
||||
Modify the version in your code:
|
||||
|
||||
```python
|
||||
# async_context_compression.py
|
||||
|
||||
"""
|
||||
version: 1.3.0 → 1.3.1 (Bug fixes)
|
||||
version: 1.3.0 → 1.4.0 (New features)
|
||||
version: 1.3.0 → 2.0.0 (Major updates)
|
||||
"""
|
||||
```
|
||||
|
||||
Then deploy, the script will auto-read the new version and update.
|
||||
|
||||
## Quick Q&A
|
||||
|
||||
**Q: Will user configuration be overwritten?**
|
||||
A: ❌ No, Valves configuration stays the same
|
||||
|
||||
**Q: Do I need to restart OpenWebUI?**
|
||||
A: ❌ No, takes effect immediately
|
||||
|
||||
**Q: What if update fails?**
|
||||
A: ✅ Safe, keeps original plugin intact
|
||||
|
||||
**Q: Can I deploy unlimited times?**
|
||||
A: ✅ Yes, completely idempotent
|
||||
|
||||
## One-liner Summary
|
||||
|
||||
> First deployment creates plugin, subsequent deployments auto-update, 5-second feedback, no restart needed.
|
||||
|
||||
---
|
||||
|
||||
📖 Full docs: `scripts/UPDATE_MECHANISM.md`
|
||||
71
scripts/deploy_async_context_compression.py
Normal file
71
scripts/deploy_async_context_compression.py
Normal file
@@ -0,0 +1,71 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Deploy Async Context Compression Filter Plugin
|
||||
|
||||
Fast deployment script specifically for async_context_compression Filter plugin.
|
||||
This is a shortcut for: python deploy_filter.py async-context-compression
|
||||
|
||||
Usage:
|
||||
python deploy_async_context_compression.py
|
||||
|
||||
To get started:
|
||||
1. Create .env file with your OpenWebUI API key:
|
||||
echo "api_key=sk-your-key-here" > .env
|
||||
|
||||
2. Make sure OpenWebUI is running on localhost:3000
|
||||
|
||||
3. Run this script:
|
||||
python deploy_async_context_compression.py
|
||||
"""
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# Import the generic filter deployment function
|
||||
SCRIPTS_DIR = Path(__file__).parent
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
|
||||
from deploy_filter import deploy_filter
|
||||
|
||||
|
||||
def main():
|
||||
"""Deploy async_context_compression filter to local OpenWebUI."""
|
||||
print("=" * 70)
|
||||
print("🚀 Deploying Async Context Compression Filter Plugin")
|
||||
print("=" * 70)
|
||||
print()
|
||||
|
||||
# Deploy the filter
|
||||
success = deploy_filter("async-context-compression")
|
||||
|
||||
if success:
|
||||
print()
|
||||
print("=" * 70)
|
||||
print("✅ Deployment successful!")
|
||||
print("=" * 70)
|
||||
print()
|
||||
print("Next steps:")
|
||||
print(" 1. Open OpenWebUI in your browser: http://localhost:3000")
|
||||
print(" 2. Go to Settings → Filters")
|
||||
print(" 3. Enable 'Async Context Compression'")
|
||||
print(" 4. Configure Valves as needed")
|
||||
print(" 5. Start using the filter in conversations")
|
||||
print()
|
||||
else:
|
||||
print()
|
||||
print("=" * 70)
|
||||
print("❌ Deployment failed!")
|
||||
print("=" * 70)
|
||||
print()
|
||||
print("Troubleshooting:")
|
||||
print(" • Check that OpenWebUI is running: http://localhost:3000")
|
||||
print(" • Verify API key in .env file")
|
||||
print(" • Check network connectivity")
|
||||
print()
|
||||
return 1
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
306
scripts/deploy_filter.py
Normal file
306
scripts/deploy_filter.py
Normal file
@@ -0,0 +1,306 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Deploy Filter plugins to OpenWebUI instance.
|
||||
|
||||
This script deploys filter plugins (like async_context_compression) to a running
|
||||
OpenWebUI instance. It reads the plugin metadata and submits it to the local API.
|
||||
|
||||
Usage:
|
||||
python deploy_filter.py # Deploy async_context_compression
|
||||
python deploy_filter.py <filter_name> # Deploy specific filter
|
||||
"""
|
||||
|
||||
import requests
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Optional, Dict, Any
|
||||
|
||||
# ─── Configuration ───────────────────────────────────────────────────────────
|
||||
SCRIPT_DIR = Path(__file__).parent
|
||||
ENV_FILE = SCRIPT_DIR / ".env"
|
||||
FILTERS_DIR = SCRIPT_DIR.parent / "plugins/filters"
|
||||
|
||||
# Default target filter
|
||||
DEFAULT_FILTER = "async-context-compression"
|
||||
|
||||
|
||||
def _load_api_key() -> str:
|
||||
"""Load API key from .env file in the same directory as this script.
|
||||
|
||||
The .env file should contain a line like:
|
||||
api_key=sk-xxxxxxxxxxxx
|
||||
"""
|
||||
if not ENV_FILE.exists():
|
||||
raise FileNotFoundError(
|
||||
f".env file not found at {ENV_FILE}. "
|
||||
"Please create it with: api_key=sk-xxxxxxxxxxxx"
|
||||
)
|
||||
|
||||
for line in ENV_FILE.read_text(encoding="utf-8").splitlines():
|
||||
line = line.strip()
|
||||
if line.startswith("api_key="):
|
||||
key = line.split("=", 1)[1].strip()
|
||||
if key:
|
||||
return key
|
||||
|
||||
raise ValueError("api_key not found in .env file.")
|
||||
|
||||
|
||||
def _find_filter_file(filter_name: str) -> Optional[Path]:
|
||||
"""Find the main Python file for a filter.
|
||||
|
||||
Args:
|
||||
filter_name: Directory name of the filter (e.g., 'async-context-compression')
|
||||
|
||||
Returns:
|
||||
Path to the main Python file, or None if not found.
|
||||
"""
|
||||
filter_dir = FILTERS_DIR / filter_name
|
||||
if not filter_dir.exists():
|
||||
return None
|
||||
|
||||
# Try to find a .py file matching the filter name
|
||||
py_files = list(filter_dir.glob("*.py"))
|
||||
|
||||
# Prefer a file with the filter name (with hyphens converted to underscores)
|
||||
preferred_name = filter_name.replace("-", "_") + ".py"
|
||||
for py_file in py_files:
|
||||
if py_file.name == preferred_name:
|
||||
return py_file
|
||||
|
||||
# Otherwise, return the first .py file (usually the only one)
|
||||
if py_files:
|
||||
return py_files[0]
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _extract_metadata(content: str) -> Dict[str, Any]:
|
||||
"""Extract metadata from the plugin docstring.
|
||||
|
||||
Args:
|
||||
content: Python file content
|
||||
|
||||
Returns:
|
||||
Dictionary with extracted metadata (title, author, version, etc.)
|
||||
"""
|
||||
metadata = {}
|
||||
|
||||
# Extract docstring
|
||||
match = re.search(r'"""(.*?)"""', content, re.DOTALL)
|
||||
if not match:
|
||||
return metadata
|
||||
|
||||
docstring = match.group(1)
|
||||
|
||||
# Extract key-value pairs
|
||||
for line in docstring.split("\n"):
|
||||
line = line.strip()
|
||||
if ":" in line and not line.startswith("#") and not line.startswith("═"):
|
||||
parts = line.split(":", 1)
|
||||
key = parts[0].strip().lower()
|
||||
value = parts[1].strip()
|
||||
metadata[key] = value
|
||||
|
||||
return metadata
|
||||
|
||||
|
||||
def _build_filter_payload(
|
||||
filter_name: str, file_path: Path, content: str, metadata: Dict[str, Any]
|
||||
) -> Dict[str, Any]:
|
||||
"""Build the payload for the filter update/create API.
|
||||
|
||||
Args:
|
||||
filter_name: Directory name of the filter
|
||||
file_path: Path to the plugin file
|
||||
content: File content
|
||||
metadata: Extracted metadata
|
||||
|
||||
Returns:
|
||||
Payload dictionary ready for API submission
|
||||
"""
|
||||
# Generate a unique ID from filter name
|
||||
filter_id = metadata.get("id", filter_name).replace("-", "_")
|
||||
title = metadata.get("title", filter_name)
|
||||
author = metadata.get("author", "Fu-Jie")
|
||||
author_url = metadata.get("author_url", "https://github.com/Fu-Jie/openwebui-extensions")
|
||||
funding_url = metadata.get("funding_url", "https://github.com/open-webui")
|
||||
description = metadata.get("description", f"Filter plugin: {title}")
|
||||
version = metadata.get("version", "1.0.0")
|
||||
openwebui_id = metadata.get("openwebui_id", "")
|
||||
|
||||
payload = {
|
||||
"id": filter_id,
|
||||
"name": title,
|
||||
"meta": {
|
||||
"description": description,
|
||||
"manifest": {
|
||||
"title": title,
|
||||
"author": author,
|
||||
"author_url": author_url,
|
||||
"funding_url": funding_url,
|
||||
"description": description,
|
||||
"version": version,
|
||||
"type": "filter",
|
||||
},
|
||||
"type": "filter",
|
||||
},
|
||||
"content": content,
|
||||
}
|
||||
|
||||
# Add openwebui_id if available
|
||||
if openwebui_id:
|
||||
payload["meta"]["manifest"]["openwebui_id"] = openwebui_id
|
||||
|
||||
return payload
|
||||
|
||||
|
||||
def deploy_filter(filter_name: str = DEFAULT_FILTER) -> bool:
|
||||
"""Deploy a filter plugin to OpenWebUI.
|
||||
|
||||
Args:
|
||||
filter_name: Directory name of the filter to deploy
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
# 1. Load API key
|
||||
try:
|
||||
api_key = _load_api_key()
|
||||
except (FileNotFoundError, ValueError) as e:
|
||||
print(f"[ERROR] {e}")
|
||||
return False
|
||||
|
||||
# 2. Find filter file
|
||||
file_path = _find_filter_file(filter_name)
|
||||
if not file_path:
|
||||
print(f"[ERROR] Filter '{filter_name}' not found in {FILTERS_DIR}")
|
||||
print(f"[INFO] Available filters:")
|
||||
for d in FILTERS_DIR.iterdir():
|
||||
if d.is_dir() and not d.name.startswith("_"):
|
||||
print(f" - {d.name}")
|
||||
return False
|
||||
|
||||
# 3. Read local source file
|
||||
if not file_path.exists():
|
||||
print(f"[ERROR] Source file not found: {file_path}")
|
||||
return False
|
||||
|
||||
content = file_path.read_text(encoding="utf-8")
|
||||
metadata = _extract_metadata(content)
|
||||
|
||||
if not metadata:
|
||||
print(f"[ERROR] Could not extract metadata from {file_path}")
|
||||
return False
|
||||
|
||||
version = metadata.get("version", "1.0.0")
|
||||
title = metadata.get("title", filter_name)
|
||||
filter_id = metadata.get("id", filter_name).replace("-", "_")
|
||||
|
||||
# 4. Build payload
|
||||
payload = _build_filter_payload(filter_name, file_path, content, metadata)
|
||||
|
||||
# 5. Build headers
|
||||
headers = {
|
||||
"Accept": "application/json",
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
}
|
||||
|
||||
# 6. Send update request
|
||||
update_url = "http://localhost:3000/api/v1/functions/id/{}/update".format(filter_id)
|
||||
create_url = "http://localhost:3000/api/v1/functions/create"
|
||||
|
||||
print(f"📦 Deploying filter '{title}' (version {version})...")
|
||||
print(f" File: {file_path}")
|
||||
|
||||
try:
|
||||
# Try update first
|
||||
response = requests.post(
|
||||
update_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
print(f"✅ Successfully updated '{title}' filter!")
|
||||
return True
|
||||
else:
|
||||
print(
|
||||
f"⚠️ Update failed with status {response.status_code}, "
|
||||
"attempting to create instead..."
|
||||
)
|
||||
|
||||
# Try create if update fails
|
||||
res_create = requests.post(
|
||||
create_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
if res_create.status_code == 200:
|
||||
print(f"✅ Successfully created '{title}' filter!")
|
||||
return True
|
||||
else:
|
||||
print(f"❌ Failed to update or create. Status: {res_create.status_code}")
|
||||
try:
|
||||
error_msg = res_create.json()
|
||||
print(f" Error: {error_msg}")
|
||||
except:
|
||||
print(f" Response: {res_create.text[:500]}")
|
||||
return False
|
||||
|
||||
except requests.exceptions.ConnectionError:
|
||||
print(
|
||||
"❌ Connection error: Could not reach OpenWebUI at localhost:3000"
|
||||
)
|
||||
print(" Make sure OpenWebUI is running and accessible.")
|
||||
return False
|
||||
except requests.exceptions.Timeout:
|
||||
print("❌ Request timeout: OpenWebUI took too long to respond")
|
||||
return False
|
||||
except Exception as e:
|
||||
print(f"❌ Request error: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def list_filters() -> None:
|
||||
"""List all available filters."""
|
||||
print("📋 Available filters:")
|
||||
filters = [d.name for d in FILTERS_DIR.iterdir() if d.is_dir() and not d.name.startswith("_")]
|
||||
|
||||
if not filters:
|
||||
print(" (No filters found)")
|
||||
return
|
||||
|
||||
for filter_name in sorted(filters):
|
||||
filter_dir = FILTERS_DIR / filter_name
|
||||
py_file = _find_filter_file(filter_name)
|
||||
|
||||
if py_file:
|
||||
content = py_file.read_text(encoding="utf-8")
|
||||
metadata = _extract_metadata(content)
|
||||
title = metadata.get("title", filter_name)
|
||||
version = metadata.get("version", "?")
|
||||
print(f" - {filter_name:<30} {title:<40} v{version}")
|
||||
else:
|
||||
print(f" - {filter_name:<30} (no Python file found)")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if len(sys.argv) > 1:
|
||||
if sys.argv[1] == "--list" or sys.argv[1] == "-l":
|
||||
list_filters()
|
||||
else:
|
||||
filter_name = sys.argv[1]
|
||||
success = deploy_filter(filter_name)
|
||||
sys.exit(0 if success else 1)
|
||||
else:
|
||||
# Deploy default filter
|
||||
success = deploy_filter()
|
||||
sys.exit(0 if success else 1)
|
||||
@@ -9,7 +9,7 @@ SCRIPT_DIR = Path(__file__).parent
|
||||
ENV_FILE = SCRIPT_DIR / ".env"
|
||||
|
||||
URL = (
|
||||
"http://localhost:3003/api/v1/functions/id/github_copilot_official_sdk_pipe/update"
|
||||
"http://localhost:3000/api/v1/functions/id/github_copilot_official_sdk_pipe/update"
|
||||
)
|
||||
FILE_PATH = SCRIPT_DIR.parent / "plugins/pipes/github-copilot-sdk/github_copilot_sdk.py"
|
||||
|
||||
@@ -103,7 +103,7 @@ def deploy_pipe() -> None:
|
||||
print(
|
||||
f"⚠️ Update failed with status {response.status_code}, attempting to create instead..."
|
||||
)
|
||||
CREATE_URL = "http://localhost:3003/api/v1/functions/create"
|
||||
CREATE_URL = "http://localhost:3000/api/v1/functions/create"
|
||||
res_create = requests.post(
|
||||
CREATE_URL, headers=headers, data=json.dumps(payload)
|
||||
)
|
||||
|
||||
322
scripts/deploy_tool.py
Normal file
322
scripts/deploy_tool.py
Normal file
@@ -0,0 +1,322 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Deploy Tools plugins to OpenWebUI instance.
|
||||
|
||||
This script deploys tool plugins to a running OpenWebUI instance.
|
||||
It reads the plugin metadata and submits it to the local API.
|
||||
|
||||
Usage:
|
||||
python deploy_tool.py # Deploy OpenWebUI Skills Manager Tool
|
||||
python deploy_tool.py <tool_name> # Deploy specific tool
|
||||
python deploy_tool.py --list # List available tools
|
||||
"""
|
||||
|
||||
import requests
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Optional, Dict, Any
|
||||
|
||||
# ─── Configuration ───────────────────────────────────────────────────────────
|
||||
SCRIPT_DIR = Path(__file__).parent
|
||||
ENV_FILE = SCRIPT_DIR / ".env"
|
||||
TOOLS_DIR = SCRIPT_DIR.parent / "plugins/tools"
|
||||
|
||||
# Default target tool
|
||||
DEFAULT_TOOL = "openwebui-skills-manager"
|
||||
|
||||
|
||||
def _load_api_key() -> str:
|
||||
"""Load API key from .env file in the same directory as this script."""
|
||||
env_values = {}
|
||||
if ENV_FILE.exists():
|
||||
for line in ENV_FILE.read_text(encoding="utf-8").splitlines():
|
||||
line = line.strip()
|
||||
if not line or line.startswith("#") or "=" not in line:
|
||||
continue
|
||||
key, value = line.split("=", 1)
|
||||
env_values[key.strip().lower()] = value.strip().strip('"').strip("'")
|
||||
|
||||
api_key = (
|
||||
os.getenv("OPENWEBUI_API_KEY")
|
||||
or os.getenv("api_key")
|
||||
or env_values.get("api_key")
|
||||
or env_values.get("openwebui_api_key")
|
||||
)
|
||||
|
||||
if not api_key:
|
||||
raise ValueError(
|
||||
f"Missing api_key. Please create {ENV_FILE} with: "
|
||||
"api_key=sk-xxxxxxxxxxxx"
|
||||
)
|
||||
return api_key
|
||||
|
||||
|
||||
def _get_base_url() -> str:
|
||||
"""Load base URL from .env file or environment."""
|
||||
env_values = {}
|
||||
if ENV_FILE.exists():
|
||||
for line in ENV_FILE.read_text(encoding="utf-8").splitlines():
|
||||
line = line.strip()
|
||||
if not line or line.startswith("#") or "=" not in line:
|
||||
continue
|
||||
key, value = line.split("=", 1)
|
||||
env_values[key.strip().lower()] = value.strip().strip('"').strip("'")
|
||||
|
||||
base_url = (
|
||||
os.getenv("OPENWEBUI_URL")
|
||||
or os.getenv("OPENWEBUI_BASE_URL")
|
||||
or os.getenv("url")
|
||||
or env_values.get("url")
|
||||
or env_values.get("openwebui_url")
|
||||
or env_values.get("openwebui_base_url")
|
||||
)
|
||||
|
||||
if not base_url:
|
||||
raise ValueError(
|
||||
f"Missing url. Please create {ENV_FILE} with: "
|
||||
"url=http://localhost:3000"
|
||||
)
|
||||
return base_url.rstrip("/")
|
||||
|
||||
|
||||
def _find_tool_file(tool_name: str) -> Optional[Path]:
|
||||
"""Find the main Python file for a tool.
|
||||
|
||||
Args:
|
||||
tool_name: Directory name of the tool (e.g., 'openwebui-skills-manager')
|
||||
|
||||
Returns:
|
||||
Path to the main Python file, or None if not found.
|
||||
"""
|
||||
tool_dir = TOOLS_DIR / tool_name
|
||||
if not tool_dir.exists():
|
||||
return None
|
||||
|
||||
# Try to find a .py file matching the tool name
|
||||
py_files = list(tool_dir.glob("*.py"))
|
||||
|
||||
# Prefer a file with the tool name (with hyphens converted to underscores)
|
||||
preferred_name = tool_name.replace("-", "_") + ".py"
|
||||
for py_file in py_files:
|
||||
if py_file.name == preferred_name:
|
||||
return py_file
|
||||
|
||||
# Otherwise, return the first .py file (usually the only one)
|
||||
if py_files:
|
||||
return py_files[0]
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _extract_metadata(content: str) -> Dict[str, Any]:
|
||||
"""Extract metadata from the plugin docstring."""
|
||||
metadata = {}
|
||||
|
||||
# Extract docstring
|
||||
match = re.search(r'"""(.*?)"""', content, re.DOTALL)
|
||||
if not match:
|
||||
return metadata
|
||||
|
||||
docstring = match.group(1)
|
||||
|
||||
# Extract key-value pairs
|
||||
for line in docstring.split("\n"):
|
||||
line = line.strip()
|
||||
if ":" in line and not line.startswith("#") and not line.startswith("═"):
|
||||
parts = line.split(":", 1)
|
||||
key = parts[0].strip().lower()
|
||||
value = parts[1].strip()
|
||||
metadata[key] = value
|
||||
|
||||
return metadata
|
||||
|
||||
|
||||
def _build_tool_payload(
|
||||
tool_name: str, file_path: Path, content: str, metadata: Dict[str, Any]
|
||||
) -> Dict[str, Any]:
|
||||
"""Build the payload for the tool update/create API."""
|
||||
tool_id = metadata.get("id", tool_name).replace("-", "_")
|
||||
title = metadata.get("title", tool_name)
|
||||
author = metadata.get("author", "Fu-Jie")
|
||||
author_url = metadata.get("author_url", "https://github.com/Fu-Jie/openwebui-extensions")
|
||||
funding_url = metadata.get("funding_url", "https://github.com/open-webui")
|
||||
description = metadata.get("description", f"Tool plugin: {title}")
|
||||
version = metadata.get("version", "1.0.0")
|
||||
openwebui_id = metadata.get("openwebui_id", "")
|
||||
|
||||
payload = {
|
||||
"id": tool_id,
|
||||
"name": title,
|
||||
"meta": {
|
||||
"description": description,
|
||||
"manifest": {
|
||||
"title": title,
|
||||
"author": author,
|
||||
"author_url": author_url,
|
||||
"funding_url": funding_url,
|
||||
"description": description,
|
||||
"version": version,
|
||||
"type": "tool",
|
||||
},
|
||||
"type": "tool",
|
||||
},
|
||||
"content": content,
|
||||
}
|
||||
|
||||
# Add openwebui_id if available
|
||||
if openwebui_id:
|
||||
payload["meta"]["manifest"]["openwebui_id"] = openwebui_id
|
||||
|
||||
return payload
|
||||
|
||||
|
||||
def deploy_tool(tool_name: str = DEFAULT_TOOL) -> bool:
|
||||
"""Deploy a tool plugin to OpenWebUI.
|
||||
|
||||
Args:
|
||||
tool_name: Directory name of the tool to deploy
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
# 1. Load API key and base URL
|
||||
try:
|
||||
api_key = _load_api_key()
|
||||
base_url = _get_base_url()
|
||||
except ValueError as e:
|
||||
print(f"[ERROR] {e}")
|
||||
return False
|
||||
|
||||
# 2. Find tool file
|
||||
file_path = _find_tool_file(tool_name)
|
||||
if not file_path:
|
||||
print(f"[ERROR] Tool '{tool_name}' not found in {TOOLS_DIR}")
|
||||
print(f"[INFO] Available tools:")
|
||||
for d in TOOLS_DIR.iterdir():
|
||||
if d.is_dir() and not d.name.startswith("_"):
|
||||
print(f" - {d.name}")
|
||||
return False
|
||||
|
||||
# 3. Read local source file
|
||||
if not file_path.exists():
|
||||
print(f"[ERROR] Source file not found: {file_path}")
|
||||
return False
|
||||
|
||||
content = file_path.read_text(encoding="utf-8")
|
||||
metadata = _extract_metadata(content)
|
||||
|
||||
if not metadata:
|
||||
print(f"[ERROR] Could not extract metadata from {file_path}")
|
||||
return False
|
||||
|
||||
version = metadata.get("version", "1.0.0")
|
||||
title = metadata.get("title", tool_name)
|
||||
tool_id = metadata.get("id", tool_name).replace("-", "_")
|
||||
|
||||
# 4. Build payload
|
||||
payload = _build_tool_payload(tool_name, file_path, content, metadata)
|
||||
|
||||
# 5. Build headers
|
||||
headers = {
|
||||
"Accept": "application/json",
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
}
|
||||
|
||||
# 6. Send update request through the native tool endpoints
|
||||
update_url = f"{base_url}/api/v1/tools/id/{tool_id}/update"
|
||||
create_url = f"{base_url}/api/v1/tools/create"
|
||||
|
||||
print(f"📦 Deploying tool '{title}' (version {version})...")
|
||||
print(f" File: {file_path}")
|
||||
|
||||
try:
|
||||
# Try update first
|
||||
response = requests.post(
|
||||
update_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
print(f"✅ Successfully updated '{title}' tool!")
|
||||
return True
|
||||
else:
|
||||
print(
|
||||
f"⚠️ Update failed with status {response.status_code}, "
|
||||
"attempting to create instead..."
|
||||
)
|
||||
|
||||
# Try create if update fails
|
||||
res_create = requests.post(
|
||||
create_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
if res_create.status_code == 200:
|
||||
print(f"✅ Successfully created '{title}' tool!")
|
||||
return True
|
||||
else:
|
||||
print(f"❌ Failed to update or create. Status: {res_create.status_code}")
|
||||
try:
|
||||
error_msg = res_create.json()
|
||||
print(f" Error: {error_msg}")
|
||||
except:
|
||||
print(f" Response: {res_create.text[:500]}")
|
||||
return False
|
||||
|
||||
except requests.exceptions.ConnectionError:
|
||||
print(
|
||||
"❌ Connection error: Could not reach OpenWebUI at {base_url}"
|
||||
)
|
||||
print(" Make sure OpenWebUI is running and accessible.")
|
||||
return False
|
||||
except requests.exceptions.Timeout:
|
||||
print("❌ Request timeout: OpenWebUI took too long to respond")
|
||||
return False
|
||||
except Exception as e:
|
||||
print(f"❌ Request error: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def list_tools() -> None:
|
||||
"""List all available tools."""
|
||||
print("📋 Available tools:")
|
||||
tools = [d.name for d in TOOLS_DIR.iterdir() if d.is_dir() and not d.name.startswith("_")]
|
||||
|
||||
if not tools:
|
||||
print(" (No tools found)")
|
||||
return
|
||||
|
||||
for tool_name in sorted(tools):
|
||||
tool_dir = TOOLS_DIR / tool_name
|
||||
py_file = _find_tool_file(tool_name)
|
||||
|
||||
if py_file:
|
||||
content = py_file.read_text(encoding="utf-8")
|
||||
metadata = _extract_metadata(content)
|
||||
title = metadata.get("title", tool_name)
|
||||
version = metadata.get("version", "?")
|
||||
print(f" - {tool_name:<30} {title:<40} v{version}")
|
||||
else:
|
||||
print(f" - {tool_name:<30} (no Python file found)")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if len(sys.argv) > 1:
|
||||
if sys.argv[1] == "--list" or sys.argv[1] == "-l":
|
||||
list_tools()
|
||||
else:
|
||||
tool_name = sys.argv[1]
|
||||
success = deploy_tool(tool_name)
|
||||
sys.exit(0 if success else 1)
|
||||
else:
|
||||
# Deploy default tool
|
||||
success = deploy_tool()
|
||||
sys.exit(0 if success else 1)
|
||||
@@ -285,9 +285,8 @@ def format_release_notes(
|
||||
prev_ver = prev_manifest.get("version") or prev.get("version")
|
||||
|
||||
readme_url = _get_readme_url(curr.get("file_path", ""))
|
||||
lines.append(f"- **{curr_title}**: v{prev_ver} → v{curr_ver}")
|
||||
if readme_url:
|
||||
lines.append(f" - 📖 [README]({readme_url})")
|
||||
readme_link = f" | [📖 README]({readme_url})" if readme_url else ""
|
||||
lines.append(f"- **{curr_title}**: v{prev_ver} → v{curr_ver}{readme_link}")
|
||||
lines.append("")
|
||||
|
||||
if comparison["removed"] and not ignore_removed:
|
||||
|
||||
441
scripts/install_all_plugins.py
Normal file
441
scripts/install_all_plugins.py
Normal file
@@ -0,0 +1,441 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Bulk install OpenWebUI plugins from this repository.
|
||||
|
||||
This script installs plugins from the local repository into a target OpenWebUI
|
||||
instance. It only installs plugins that:
|
||||
- live under plugins/actions, plugins/filters, plugins/pipes, or plugins/tools
|
||||
- contain an `openwebui_id` in the plugin header docstring
|
||||
- do not use a Chinese filename
|
||||
- do not use a `_cn.py` localized filename suffix
|
||||
|
||||
Supported Plugin Types:
|
||||
- Action (standard Function class)
|
||||
- Filter (standard Function class)
|
||||
- Pipe (standard Function class)
|
||||
- Tool (native Tools class via /api/v1/tools endpoints)
|
||||
|
||||
Configuration:
|
||||
Create `scripts/.env` with:
|
||||
api_key=sk-your-api-key
|
||||
url=http://localhost:3000
|
||||
|
||||
Usage:
|
||||
python scripts/install_all_plugins.py
|
||||
python scripts/install_all_plugins.py --list
|
||||
python scripts/install_all_plugins.py --dry-run
|
||||
python scripts/install_all_plugins.py --types pipe action filter tool
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Sequence, Tuple
|
||||
|
||||
import requests
|
||||
|
||||
SCRIPT_DIR = Path(__file__).resolve().parent
|
||||
REPO_ROOT = SCRIPT_DIR.parent
|
||||
ENV_FILE = SCRIPT_DIR / ".env"
|
||||
DEFAULT_TIMEOUT = 20
|
||||
DEFAULT_TYPES = ("pipe", "action", "filter", "tool")
|
||||
SKIP_PREFIXES = ("test_", "verify_")
|
||||
DOCSTRING_PATTERN = re.compile(r'^\s*"""\n(.*?)\n"""', re.DOTALL)
|
||||
|
||||
PLUGIN_TYPE_DIRS = {
|
||||
"action": REPO_ROOT / "plugins" / "actions",
|
||||
"filter": REPO_ROOT / "plugins" / "filters",
|
||||
"pipe": REPO_ROOT / "plugins" / "pipes",
|
||||
"tool": REPO_ROOT / "plugins" / "tools",
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class PluginCandidate:
|
||||
plugin_type: str
|
||||
file_path: Path
|
||||
metadata: Dict[str, str]
|
||||
content: str
|
||||
function_id: str
|
||||
|
||||
@property
|
||||
def title(self) -> str:
|
||||
return self.metadata.get("title", self.file_path.stem)
|
||||
|
||||
@property
|
||||
def version(self) -> str:
|
||||
return self.metadata.get("version", "unknown")
|
||||
|
||||
|
||||
def _load_env_file(env_path: Path = ENV_FILE) -> Dict[str, str]:
|
||||
values: Dict[str, str] = {}
|
||||
if not env_path.exists():
|
||||
return values
|
||||
|
||||
for raw_line in env_path.read_text(encoding="utf-8").splitlines():
|
||||
line = raw_line.strip()
|
||||
if not line or line.startswith("#") or "=" not in line:
|
||||
continue
|
||||
key, value = line.split("=", 1)
|
||||
key_lower = key.strip().lower()
|
||||
values[key_lower] = value.strip().strip('"').strip("'")
|
||||
return values
|
||||
|
||||
|
||||
def load_config(env_path: Path = ENV_FILE) -> Tuple[str, str]:
|
||||
env_values = _load_env_file(env_path)
|
||||
|
||||
api_key = (
|
||||
os.getenv("OPENWEBUI_API_KEY")
|
||||
or os.getenv("api_key")
|
||||
or env_values.get("api_key")
|
||||
or env_values.get("openwebui_api_key")
|
||||
)
|
||||
base_url = (
|
||||
os.getenv("OPENWEBUI_URL")
|
||||
or os.getenv("OPENWEBUI_BASE_URL")
|
||||
or os.getenv("url")
|
||||
or env_values.get("url")
|
||||
or env_values.get("openwebui_url")
|
||||
or env_values.get("openwebui_base_url")
|
||||
)
|
||||
|
||||
missing = []
|
||||
if not api_key:
|
||||
missing.append("api_key")
|
||||
if not base_url:
|
||||
missing.append("url")
|
||||
|
||||
if missing:
|
||||
joined = ", ".join(missing)
|
||||
raise ValueError(
|
||||
f"Missing required config: {joined}. "
|
||||
f"Please set them in environment variables or {env_path}."
|
||||
)
|
||||
|
||||
return api_key, normalize_base_url(base_url)
|
||||
|
||||
|
||||
def normalize_base_url(url: str) -> str:
|
||||
normalized = url.strip()
|
||||
if not normalized:
|
||||
raise ValueError("URL cannot be empty.")
|
||||
return normalized.rstrip("/")
|
||||
|
||||
|
||||
def extract_metadata(content: str) -> Dict[str, str]:
|
||||
match = DOCSTRING_PATTERN.search(content)
|
||||
if not match:
|
||||
return {}
|
||||
|
||||
metadata: Dict[str, str] = {}
|
||||
for raw_line in match.group(1).splitlines():
|
||||
line = raw_line.strip()
|
||||
if not line or line.startswith("#") or ":" not in line:
|
||||
continue
|
||||
key, value = line.split(":", 1)
|
||||
metadata[key.strip().lower()] = value.strip()
|
||||
return metadata
|
||||
|
||||
|
||||
def contains_non_ascii_filename(file_path: Path) -> bool:
|
||||
try:
|
||||
file_path.stem.encode("ascii")
|
||||
return False
|
||||
except UnicodeEncodeError:
|
||||
return True
|
||||
|
||||
|
||||
def should_skip_plugin_file(file_path: Path) -> Optional[str]:
|
||||
stem = file_path.stem.lower()
|
||||
|
||||
if contains_non_ascii_filename(file_path):
|
||||
return "non-ascii filename"
|
||||
if stem.endswith("_cn"):
|
||||
return "localized _cn file"
|
||||
if stem.startswith(SKIP_PREFIXES):
|
||||
return "test or helper script"
|
||||
return None
|
||||
|
||||
|
||||
def slugify_function_id(value: str) -> str:
|
||||
slug = re.sub(r"[^a-z0-9]+", "_", value.lower()).strip("_")
|
||||
slug = re.sub(r"_+", "_", slug)
|
||||
return slug or "plugin"
|
||||
|
||||
|
||||
def build_function_id(file_path: Path, metadata: Dict[str, str]) -> str:
|
||||
if metadata.get("id"):
|
||||
return slugify_function_id(metadata["id"])
|
||||
if metadata.get("title"):
|
||||
return slugify_function_id(metadata["title"])
|
||||
return slugify_function_id(file_path.stem)
|
||||
|
||||
|
||||
def has_tools_class(content: str) -> bool:
|
||||
"""Check if plugin content defines a Tools class instead of Function class."""
|
||||
return "\nclass Tools:" in content or "\nclass Tools (" in content
|
||||
|
||||
|
||||
def build_payload(candidate: PluginCandidate) -> Dict[str, object]:
|
||||
manifest = dict(candidate.metadata)
|
||||
manifest.setdefault("title", candidate.title)
|
||||
manifest.setdefault("author", "Fu-Jie")
|
||||
manifest.setdefault(
|
||||
"author_url", "https://github.com/Fu-Jie/openwebui-extensions"
|
||||
)
|
||||
manifest.setdefault("funding_url", "https://github.com/open-webui")
|
||||
manifest.setdefault(
|
||||
"description", f"{candidate.plugin_type.title()} plugin: {candidate.title}"
|
||||
)
|
||||
manifest.setdefault("version", "1.0.0")
|
||||
manifest["type"] = candidate.plugin_type
|
||||
|
||||
if candidate.plugin_type == "tool":
|
||||
return {
|
||||
"id": candidate.function_id,
|
||||
"name": manifest["title"],
|
||||
"meta": {
|
||||
"description": manifest["description"],
|
||||
"manifest": {},
|
||||
},
|
||||
"content": candidate.content,
|
||||
"access_grants": [],
|
||||
}
|
||||
|
||||
return {
|
||||
"id": candidate.function_id,
|
||||
"name": manifest["title"],
|
||||
"meta": {
|
||||
"description": manifest["description"],
|
||||
"manifest": manifest,
|
||||
"type": candidate.plugin_type,
|
||||
},
|
||||
"content": candidate.content,
|
||||
}
|
||||
|
||||
|
||||
def build_api_urls(base_url: str, candidate: PluginCandidate) -> Tuple[str, str]:
|
||||
if candidate.plugin_type == "tool":
|
||||
return (
|
||||
f"{base_url}/api/v1/tools/id/{candidate.function_id}/update",
|
||||
f"{base_url}/api/v1/tools/create",
|
||||
)
|
||||
return (
|
||||
f"{base_url}/api/v1/functions/id/{candidate.function_id}/update",
|
||||
f"{base_url}/api/v1/functions/create",
|
||||
)
|
||||
|
||||
|
||||
def discover_plugins(plugin_types: Sequence[str]) -> Tuple[List[PluginCandidate], List[Tuple[Path, str]]]:
|
||||
candidates: List[PluginCandidate] = []
|
||||
skipped: List[Tuple[Path, str]] = []
|
||||
|
||||
for plugin_type in plugin_types:
|
||||
plugin_dir = PLUGIN_TYPE_DIRS[plugin_type]
|
||||
if not plugin_dir.exists():
|
||||
continue
|
||||
|
||||
for file_path in sorted(plugin_dir.rglob("*.py")):
|
||||
skip_reason = should_skip_plugin_file(file_path)
|
||||
if skip_reason:
|
||||
skipped.append((file_path, skip_reason))
|
||||
continue
|
||||
|
||||
content = file_path.read_text(encoding="utf-8")
|
||||
metadata = extract_metadata(content)
|
||||
if not metadata:
|
||||
skipped.append((file_path, "missing plugin header"))
|
||||
continue
|
||||
if not metadata.get("openwebui_id"):
|
||||
skipped.append((file_path, "missing openwebui_id"))
|
||||
continue
|
||||
|
||||
candidates.append(
|
||||
PluginCandidate(
|
||||
plugin_type=plugin_type,
|
||||
file_path=file_path,
|
||||
metadata=metadata,
|
||||
content=content,
|
||||
function_id=build_function_id(file_path, metadata),
|
||||
)
|
||||
)
|
||||
|
||||
candidates.sort(key=lambda item: (item.plugin_type, item.file_path.as_posix()))
|
||||
skipped.sort(key=lambda item: item[0].as_posix())
|
||||
return candidates, skipped
|
||||
|
||||
|
||||
def install_plugin(
|
||||
candidate: PluginCandidate,
|
||||
api_key: str,
|
||||
base_url: str,
|
||||
timeout: int = DEFAULT_TIMEOUT,
|
||||
) -> Tuple[bool, str]:
|
||||
headers = {
|
||||
"Accept": "application/json",
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
}
|
||||
payload = build_payload(candidate)
|
||||
update_url, create_url = build_api_urls(base_url, candidate)
|
||||
|
||||
try:
|
||||
update_response = requests.post(
|
||||
update_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=timeout,
|
||||
)
|
||||
if 200 <= update_response.status_code < 300:
|
||||
return True, "updated"
|
||||
|
||||
create_response = requests.post(
|
||||
create_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=timeout,
|
||||
)
|
||||
if 200 <= create_response.status_code < 300:
|
||||
return True, "created"
|
||||
|
||||
message = _response_message(create_response)
|
||||
return False, f"create failed ({create_response.status_code}): {message}"
|
||||
except requests.exceptions.Timeout:
|
||||
return False, "request timed out"
|
||||
except requests.exceptions.ConnectionError:
|
||||
return False, f"cannot connect to {base_url}"
|
||||
except Exception as exc:
|
||||
return False, str(exc)
|
||||
|
||||
|
||||
def _response_message(response: requests.Response) -> str:
|
||||
try:
|
||||
return json.dumps(response.json(), ensure_ascii=False)
|
||||
except Exception:
|
||||
return response.text[:500]
|
||||
|
||||
|
||||
def print_candidates(candidates: Sequence[PluginCandidate]) -> None:
|
||||
if not candidates:
|
||||
print("No installable plugins found.")
|
||||
return
|
||||
|
||||
print(f"Found {len(candidates)} installable plugins:")
|
||||
for candidate in candidates:
|
||||
relative_path = candidate.file_path.relative_to(REPO_ROOT)
|
||||
print(
|
||||
f" - [{candidate.plugin_type}] {candidate.title} "
|
||||
f"v{candidate.version} -> {relative_path}"
|
||||
)
|
||||
|
||||
|
||||
def print_skipped_summary(skipped: Sequence[Tuple[Path, str]]) -> None:
|
||||
if not skipped:
|
||||
return
|
||||
|
||||
counts: Dict[str, int] = {}
|
||||
for _, reason in skipped:
|
||||
counts[reason] = counts.get(reason, 0) + 1
|
||||
|
||||
summary = ", ".join(f"{reason}: {count}" for reason, count in sorted(counts.items()))
|
||||
print(f"Skipped {len(skipped)} files ({summary}).")
|
||||
|
||||
|
||||
def parse_args(argv: Optional[Sequence[str]] = None) -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Install repository plugins into an OpenWebUI instance."
|
||||
)
|
||||
parser.add_argument(
|
||||
"--types",
|
||||
nargs="+",
|
||||
choices=sorted(PLUGIN_TYPE_DIRS.keys()),
|
||||
default=list(DEFAULT_TYPES),
|
||||
help="Plugin types to install. Defaults to all supported types.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--list",
|
||||
action="store_true",
|
||||
help="List installable plugins without calling the API.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--dry-run",
|
||||
action="store_true",
|
||||
help="Show what would be installed without calling the API.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--timeout",
|
||||
type=int,
|
||||
default=DEFAULT_TIMEOUT,
|
||||
help=f"Request timeout in seconds. Default: {DEFAULT_TIMEOUT}.",
|
||||
)
|
||||
return parser.parse_args(argv)
|
||||
|
||||
|
||||
def main(argv: Optional[Sequence[str]] = None) -> int:
|
||||
args = parse_args(argv)
|
||||
candidates, skipped = discover_plugins(args.types)
|
||||
|
||||
print_candidates(candidates)
|
||||
print_skipped_summary(skipped)
|
||||
|
||||
if args.list or args.dry_run:
|
||||
return 0
|
||||
|
||||
if not candidates:
|
||||
print("Nothing to install.")
|
||||
return 1
|
||||
|
||||
try:
|
||||
api_key, base_url = load_config()
|
||||
except ValueError as exc:
|
||||
print(f"[ERROR] {exc}")
|
||||
return 1
|
||||
|
||||
print(f"Installing to: {base_url}")
|
||||
|
||||
success_count = 0
|
||||
failed_candidates = []
|
||||
for candidate in candidates:
|
||||
relative_path = candidate.file_path.relative_to(REPO_ROOT)
|
||||
print(
|
||||
f"\nInstalling [{candidate.plugin_type}] {candidate.title} "
|
||||
f"v{candidate.version} ({relative_path})"
|
||||
)
|
||||
ok, message = install_plugin(
|
||||
candidate=candidate,
|
||||
api_key=api_key,
|
||||
base_url=base_url,
|
||||
timeout=args.timeout,
|
||||
)
|
||||
if ok:
|
||||
success_count += 1
|
||||
print(f" [OK] {message}")
|
||||
else:
|
||||
failed_candidates.append(candidate)
|
||||
print(f" [FAILED] {message}")
|
||||
|
||||
print(f"\n" + "="*80)
|
||||
print(
|
||||
f"Finished: {success_count}/{len(candidates)} plugins installed successfully."
|
||||
)
|
||||
|
||||
if failed_candidates:
|
||||
print(f"\n❌ {len(failed_candidates)} plugin(s) failed to install:")
|
||||
for candidate in failed_candidates:
|
||||
print(f" • {candidate.title} ({candidate.plugin_type})")
|
||||
print(f" → Check the error message above")
|
||||
print()
|
||||
|
||||
print("="*80)
|
||||
return 0 if success_count == len(candidates) else 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
104
scripts/verify_deployment_tools.py
Normal file
104
scripts/verify_deployment_tools.py
Normal file
@@ -0,0 +1,104 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Quick verification script to ensure all deployment tools are in place.
|
||||
|
||||
This script checks that all necessary files for async_context_compression
|
||||
local deployment are present and functional.
|
||||
"""
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
def main():
|
||||
"""Check all deployment tools are ready."""
|
||||
base_dir = Path(__file__).parent.parent
|
||||
|
||||
print("\n" + "="*80)
|
||||
print("✨ Async Context Compression Local Deployment Tools — Verification Status")
|
||||
print("="*80 + "\n")
|
||||
|
||||
files_to_check = {
|
||||
"🐍 Python Scripts": [
|
||||
"scripts/deploy_async_context_compression.py",
|
||||
"scripts/deploy_filter.py",
|
||||
"scripts/deploy_pipe.py",
|
||||
],
|
||||
"📖 Deployment Documentation": [
|
||||
"scripts/README.md",
|
||||
"scripts/QUICK_START.md",
|
||||
"scripts/DEPLOYMENT_GUIDE.md",
|
||||
"scripts/DEPLOYMENT_SUMMARY.md",
|
||||
"plugins/filters/async-context-compression/DEPLOYMENT_REFERENCE.md",
|
||||
],
|
||||
"🧪 Test Files": [
|
||||
"tests/scripts/test_deploy_filter.py",
|
||||
],
|
||||
}
|
||||
|
||||
all_exist = True
|
||||
|
||||
for category, files in files_to_check.items():
|
||||
print(f"\n{category}:")
|
||||
print("-" * 80)
|
||||
|
||||
for file_path in files:
|
||||
full_path = base_dir / file_path
|
||||
exists = full_path.exists()
|
||||
status = "✅" if exists else "❌"
|
||||
|
||||
print(f" {status} {file_path}")
|
||||
|
||||
if exists and file_path.endswith(".py"):
|
||||
size = full_path.stat().st_size
|
||||
lines = len(full_path.read_text().split('\n'))
|
||||
print(f" └─ [{size} bytes, ~{lines} lines]")
|
||||
|
||||
if not exists:
|
||||
all_exist = False
|
||||
|
||||
print("\n" + "="*80)
|
||||
|
||||
if all_exist:
|
||||
print("✅ All deployment tool files are ready!")
|
||||
print("="*80 + "\n")
|
||||
|
||||
print("🚀 Quick Start (3 ways):\n")
|
||||
|
||||
print(" Method 1: Easiest (Recommended)")
|
||||
print(" ─────────────────────────────────────────────────────────")
|
||||
print(" cd scripts")
|
||||
print(" python deploy_async_context_compression.py")
|
||||
print()
|
||||
|
||||
print(" Method 2: Generic Tool")
|
||||
print(" ─────────────────────────────────────────────────────────")
|
||||
print(" cd scripts")
|
||||
print(" python deploy_filter.py")
|
||||
print()
|
||||
|
||||
print(" Method 3: Deploy Other Filters")
|
||||
print(" ─────────────────────────────────────────────────────────")
|
||||
print(" cd scripts")
|
||||
print(" python deploy_filter.py --list")
|
||||
print(" python deploy_filter.py folder-memory")
|
||||
print()
|
||||
|
||||
print("="*80 + "\n")
|
||||
print("📚 Documentation References:\n")
|
||||
print(" • Quick Start: scripts/QUICK_START.md")
|
||||
print(" • Complete Guide: scripts/DEPLOYMENT_GUIDE.md")
|
||||
print(" • Technical Summary: scripts/DEPLOYMENT_SUMMARY.md")
|
||||
print(" • Script Info: scripts/README.md")
|
||||
print(" • Test Coverage: pytest tests/scripts/test_deploy_filter.py -v")
|
||||
print()
|
||||
|
||||
print("="*80 + "\n")
|
||||
return 0
|
||||
else:
|
||||
print("❌ Some files are missing!")
|
||||
print("="*80 + "\n")
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -0,0 +1,22 @@
|
||||
from plugins.filters.markdown_normalizer.markdown_normalizer import ContentNormalizer, NormalizerConfig
|
||||
|
||||
def test_latex_display_math_protection():
|
||||
"""Verify that $$\nabla$$ is NOT broken by escape fix."""
|
||||
config = NormalizerConfig(enable_escape_fix=True)
|
||||
norm = ContentNormalizer(config)
|
||||
|
||||
# Input has literal backslash + n (represented as \\n in python code)
|
||||
# Total input: $$ \ n a b l a $$
|
||||
text = r"$$\nabla$$"
|
||||
res = norm.normalize(text)
|
||||
|
||||
# It should NOT change literal \n to a newline inside $$
|
||||
assert "\n" not in res, f"LaTeX display math was corrupted with a real newline: {repr(res)}"
|
||||
assert res == text, f"Expected {repr(text)}, got {repr(res)}"
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
test_latex_display_math_protection()
|
||||
print("✅ LaTeX protection test passed.")
|
||||
except AssertionError as e:
|
||||
print(f"❌ LaTeX protection test FAILED: {e}")
|
||||
@@ -0,0 +1,53 @@
|
||||
from plugins.filters.markdown_normalizer.markdown_normalizer import ContentNormalizer, NormalizerConfig
|
||||
|
||||
def test_error_rollback():
|
||||
"""Issue 57-1: Ensure content is NOT modified if a cleaner raises an exception."""
|
||||
def broken_cleaner(text): raise RuntimeError("Plugin Crash Simulation")
|
||||
config = NormalizerConfig(custom_cleaners=[broken_cleaner])
|
||||
norm = ContentNormalizer(config)
|
||||
raw_text = "Content that should NOT be modified on error."
|
||||
res = norm.normalize(raw_text)
|
||||
assert res == raw_text
|
||||
|
||||
def test_inline_code_protection():
|
||||
"""Issue 57-2: Protect backslashes inside inline code blocks."""
|
||||
norm = ContentNormalizer(NormalizerConfig(enable_escape_fix=True))
|
||||
inline_code = "Regex: `[\\\\n\\\\r]` and Path: `C:\\\\\\\\Windows` and Normal: \\\\n"
|
||||
res = norm.normalize(inline_code)
|
||||
# The normal \\\\n at the end SHOULD be converted to actual \n
|
||||
# The backslashes inside ` ` should NOT be converted.
|
||||
assert "`[\\\\n\\\\r]`" in res
|
||||
assert "`C:\\\\\\\\Windows`" in res
|
||||
assert "\n" in res
|
||||
|
||||
def test_code_block_escape_control():
|
||||
"""Issue 57-3: Verify enable_escape_fix_in_code_blocks valve."""
|
||||
# input code: print('\\n')
|
||||
# representation: "print('\\\\n')"
|
||||
block_text = "```python\nprint('\\\\n')\n```"
|
||||
|
||||
# Subcase A: Disabled (Default)
|
||||
norm_off = ContentNormalizer(NormalizerConfig(enable_escape_fix_in_code_blocks=False))
|
||||
assert norm_off.normalize(block_text) == block_text
|
||||
|
||||
# Subcase B: Enabled
|
||||
norm_on = ContentNormalizer(NormalizerConfig(enable_escape_fix_in_code_blocks=True))
|
||||
# Expected: "```python\nprint('\n')\n```"
|
||||
res = norm_on.normalize(block_text)
|
||||
assert "\n" in res
|
||||
assert "\\n" not in res.split("```")[1]
|
||||
|
||||
def test_latex_protection():
|
||||
"""Regression: Ensure LaTeX commands are not corrupted by escape fix."""
|
||||
norm = ContentNormalizer(NormalizerConfig(enable_escape_fix=True))
|
||||
latex_text = "Math: $\\\\times \\\\theta \\\\nu$ and Normal: \\\\n"
|
||||
res = norm.normalize(latex_text)
|
||||
assert "$\\\\times \\\\theta \\\\nu$" in res
|
||||
assert "\n" in res
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_error_rollback()
|
||||
test_inline_code_protection()
|
||||
test_code_block_escape_control()
|
||||
test_latex_protection()
|
||||
print("All tests passed!")
|
||||
173
tests/scripts/test_install_all_plugins.py
Normal file
173
tests/scripts/test_install_all_plugins.py
Normal file
@@ -0,0 +1,173 @@
|
||||
import importlib.util
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
MODULE_PATH = Path(__file__).resolve().parents[2] / "scripts" / "install_all_plugins.py"
|
||||
SPEC = importlib.util.spec_from_file_location("install_all_plugins", MODULE_PATH)
|
||||
install_all_plugins = importlib.util.module_from_spec(SPEC)
|
||||
assert SPEC.loader is not None
|
||||
sys.modules[SPEC.name] = install_all_plugins
|
||||
SPEC.loader.exec_module(install_all_plugins)
|
||||
|
||||
|
||||
PLUGIN_HEADER = '''"""
|
||||
title: Example Plugin
|
||||
version: 1.0.0
|
||||
openwebui_id: 12345678-1234-1234-1234-123456789abc
|
||||
description: Example description.
|
||||
"""
|
||||
'''
|
||||
|
||||
|
||||
def write_plugin(path: Path, header: str) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(header + "\nclass Action:\n pass\n", encoding="utf-8")
|
||||
|
||||
|
||||
def test_should_skip_plugin_file_filters_localized_and_helper_names():
|
||||
assert (
|
||||
install_all_plugins.should_skip_plugin_file(Path("flash_card_cn.py"))
|
||||
== "localized _cn file"
|
||||
)
|
||||
assert (
|
||||
install_all_plugins.should_skip_plugin_file(Path("verify_generation.py"))
|
||||
== "test or helper script"
|
||||
)
|
||||
assert (
|
||||
install_all_plugins.should_skip_plugin_file(Path("测试.py"))
|
||||
== "non-ascii filename"
|
||||
)
|
||||
assert install_all_plugins.should_skip_plugin_file(Path("flash_card.py")) is None
|
||||
|
||||
|
||||
def test_build_function_id_prefers_id_then_title_then_filename():
|
||||
from_id = install_all_plugins.build_function_id(
|
||||
Path("dummy.py"), {"id": "Async Context Compression"}
|
||||
)
|
||||
from_title = install_all_plugins.build_function_id(
|
||||
Path("dummy.py"), {"title": "GitHub Copilot Official SDK Pipe"}
|
||||
)
|
||||
from_file = install_all_plugins.build_function_id(Path("dummy_plugin.py"), {})
|
||||
|
||||
assert from_id == "async_context_compression"
|
||||
assert from_title == "github_copilot_official_sdk_pipe"
|
||||
assert from_file == "dummy_plugin"
|
||||
|
||||
|
||||
def test_build_payload_uses_native_tool_shape_for_tools():
|
||||
candidate = install_all_plugins.PluginCandidate(
|
||||
plugin_type="tool",
|
||||
file_path=Path("plugins/tools/demo/demo_tool.py"),
|
||||
metadata={
|
||||
"title": "Demo Tool",
|
||||
"description": "Demo tool description",
|
||||
"openwebui_id": "12345678-1234-1234-1234-123456789abc",
|
||||
},
|
||||
content='class Tools:\n pass\n',
|
||||
function_id="demo_tool",
|
||||
)
|
||||
|
||||
payload = install_all_plugins.build_payload(candidate)
|
||||
|
||||
assert payload == {
|
||||
"id": "demo_tool",
|
||||
"name": "Demo Tool",
|
||||
"meta": {
|
||||
"description": "Demo tool description",
|
||||
"manifest": {},
|
||||
},
|
||||
"content": 'class Tools:\n pass\n',
|
||||
"access_grants": [],
|
||||
}
|
||||
|
||||
|
||||
def test_build_api_urls_uses_tool_endpoints_for_tools():
|
||||
candidate = install_all_plugins.PluginCandidate(
|
||||
plugin_type="tool",
|
||||
file_path=Path("plugins/tools/demo/demo_tool.py"),
|
||||
metadata={"title": "Demo Tool"},
|
||||
content='class Tools:\n pass\n',
|
||||
function_id="demo_tool",
|
||||
)
|
||||
|
||||
update_url, create_url = install_all_plugins.build_api_urls(
|
||||
"http://localhost:3000", candidate
|
||||
)
|
||||
|
||||
assert update_url == "http://localhost:3000/api/v1/tools/id/demo_tool/update"
|
||||
assert create_url == "http://localhost:3000/api/v1/tools/create"
|
||||
|
||||
|
||||
def test_discover_plugins_only_returns_supported_openwebui_plugins(tmp_path, monkeypatch):
|
||||
actions_dir = tmp_path / "plugins" / "actions"
|
||||
filters_dir = tmp_path / "plugins" / "filters"
|
||||
pipes_dir = tmp_path / "plugins" / "pipes"
|
||||
tools_dir = tmp_path / "plugins" / "tools"
|
||||
|
||||
write_plugin(actions_dir / "flash-card" / "flash_card.py", PLUGIN_HEADER)
|
||||
write_plugin(actions_dir / "flash-card" / "flash_card_cn.py", PLUGIN_HEADER)
|
||||
write_plugin(actions_dir / "infographic" / "verify_generation.py", PLUGIN_HEADER)
|
||||
write_plugin(filters_dir / "missing-id" / "missing_id.py", '"""\ntitle: Missing ID\n"""\n')
|
||||
write_plugin(pipes_dir / "sdk" / "github_copilot_sdk.py", PLUGIN_HEADER)
|
||||
write_plugin(tools_dir / "skills" / "openwebui_skills_manager.py", PLUGIN_HEADER)
|
||||
|
||||
monkeypatch.setattr(
|
||||
install_all_plugins,
|
||||
"PLUGIN_TYPE_DIRS",
|
||||
{
|
||||
"action": actions_dir,
|
||||
"filter": filters_dir,
|
||||
"pipe": pipes_dir,
|
||||
"tool": tools_dir,
|
||||
},
|
||||
)
|
||||
monkeypatch.setattr(install_all_plugins, "REPO_ROOT", tmp_path)
|
||||
|
||||
candidates, skipped = install_all_plugins.discover_plugins(
|
||||
["action", "filter", "pipe", "tool"]
|
||||
)
|
||||
|
||||
candidate_names = [candidate.file_path.name for candidate in candidates]
|
||||
skipped_reasons = {path.name: reason for path, reason in skipped}
|
||||
|
||||
assert candidate_names == [
|
||||
"flash_card.py",
|
||||
"github_copilot_sdk.py",
|
||||
"openwebui_skills_manager.py",
|
||||
]
|
||||
assert skipped_reasons["missing_id.py"] == "missing openwebui_id"
|
||||
assert skipped_reasons["flash_card_cn.py"] == "localized _cn file"
|
||||
assert skipped_reasons["verify_generation.py"] == "test or helper script"
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("header", "expected_reason"),
|
||||
[
|
||||
('"""\ntitle: Missing ID\n"""\n', "missing openwebui_id"),
|
||||
("class Action:\n pass\n", "missing plugin header"),
|
||||
],
|
||||
)
|
||||
def test_discover_plugins_reports_missing_metadata(tmp_path, monkeypatch, header, expected_reason):
|
||||
action_dir = tmp_path / "plugins" / "actions"
|
||||
plugin_file = action_dir / "demo" / "demo.py"
|
||||
write_plugin(plugin_file, header)
|
||||
|
||||
monkeypatch.setattr(
|
||||
install_all_plugins,
|
||||
"PLUGIN_TYPE_DIRS",
|
||||
{
|
||||
"action": action_dir,
|
||||
"filter": tmp_path / "plugins" / "filters",
|
||||
"pipe": tmp_path / "plugins" / "pipes",
|
||||
"tool": tmp_path / "plugins" / "tools",
|
||||
},
|
||||
)
|
||||
monkeypatch.setattr(install_all_plugins, "REPO_ROOT", tmp_path)
|
||||
|
||||
candidates, skipped = install_all_plugins.discover_plugins(["action"])
|
||||
|
||||
assert candidates == []
|
||||
assert skipped == [(plugin_file, expected_reason)]
|
||||
Reference in New Issue
Block a user