2 Commits

Author SHA1 Message Date
StressTestor e222e92153 fix(personal): serialize add/remove/reload on an async job lock
The #5558 fix took the job lock INSIDE the threadpool worker and only on the
add path, so (1) remove_directory and /reload mutated PersonalDocsManager's
unsynchronized list/index concurrently with an in-flight add — the inconsistent
state the PR claimed to prevent — and (2) a queued add blocked on the lock while
holding an AnyIO threadpool token, starving the shared pool.

Move the lock to an asyncio.Lock acquired in the async handler BEFORE offloading,
and route add, remove and reload through it. A waiting request now parks on the
event loop instead of pinning a worker, and all three mutators are serialized so
the 'add/remove are serialized and cannot leave inconsistent state' guarantee
holds. remove and reload also run their blocking work off the event loop. The
lock is per-router so each app binds it to its own loop; single-process scope.

Tests: add-vs-remove and add-vs-reload serialization regressions (async via
ASGITransport, since asyncio.Lock deadlocks starlette TestClient's portal); the
existing add-vs-add test converted to the same driver.
2026-07-27 20:43:04 +00:00
StressTestor b91f48f50a fix(personal): run directory indexing off the event loop (#5558)
POST /api/personal/add_directory called rag.index_personal_documents
inline from an async handler, so the whole indexing job (os.walk, file
reads, per-chunk embedding, Chroma inserts) ran on the event loop and
every other request queued behind it. Indexing a real directory froze
the UI and API for 25+ minutes with no sign of life.

Move the blocking section into the threadpool via run_in_threadpool.
personal_docs_manager.add_directory stays inside it because its
refresh_index() re-extracts text across tracked directories, which is
also blocking work. A module-level lock serializes index jobs so the
threadpool move does not introduce parallel jobs racing
PersonalDocsManager's unsynchronized list mutations and file writes;
they previously serialized on the blocked loop, so one-at-a-time is
behavior parity.
2026-07-27 20:43:04 +00:00
37 changed files with 503 additions and 682 deletions
-1
View File
@@ -189,7 +189,6 @@ SEARXNG_INSTANCE=http://localhost:8080
# ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=26214400 # email compose attachment (25 MB)
# ODYSSEUS_STT_MAX_AUDIO_BYTES=26214400 # speech-to-text audio (25 MB)
# ODYSSEUS_ICS_MAX_BYTES=10485760 # calendar .ics import (10 MB)
# ODYSSEUS_TTS_CACHE_MAX_BYTES=524288000 # TTS cache (500 MB)
# ============================================================
# Host Docker access (explicit opt-in)
+3 -10
View File
@@ -153,16 +153,6 @@ module.exports = async ({ github, context, core }) => {
}
}
const LABEL_BAD = 'needs more info';
const LABEL_GOOD = 'ready for review';
// Closed issues are no longer awaiting review.
// This also prevents later edits to closed issues from restoring the label.
if (issue.state === 'closed') {
await dropLabel(LABEL_GOOD);
return;
}
// ── Find existing bot comment to update in-place ──────────────────────────
const MARKER = '<!-- issue-description-check -->';
const { data: comments } = await github.rest.issues.listComments({
@@ -170,6 +160,9 @@ module.exports = async ({ github, context, core }) => {
});
const existing = comments.find(c => c.user.type === 'Bot' && c.body.includes(MARKER));
const LABEL_BAD = 'needs more info';
const LABEL_GOOD = 'ready for review';
if (failures.length === 0) {
if (existing) {
await github.rest.issues.deleteComment({ owner, repo, comment_id: existing.id });
+7 -7
View File
@@ -21,7 +21,7 @@ jobs:
runs-on: ubuntu-latest
continue-on-error: true
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
fetch-depth: 0
persist-credentials: false
@@ -73,10 +73,10 @@ jobs:
name: Python syntax (compileall)
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
with:
python-version: "3.11"
# Byte-compile sources — catches syntax errors without installing deps.
@@ -86,10 +86,10 @@ jobs:
name: JS syntax (node --check)
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
with:
node-version: "20"
# Syntax-check our own JS (skip vendored libs in static/lib).
@@ -108,7 +108,7 @@ jobs:
# ROADMAP "fresh install smoke tests" item; make this required once green.
continue-on-error: true
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
fetch-depth: 0
persist-credentials: false
@@ -135,7 +135,7 @@ jobs:
echo "docs_only=false" >> "$GITHUB_OUTPUT"
fi
- uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
if: steps.docs-check.outputs.docs_only != 'true'
with:
python-version: "3.11"
+3 -3
View File
@@ -27,15 +27,15 @@ jobs:
language: [actions, javascript-typescript, python]
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Initialize CodeQL
uses: github/codeql-action/init@f205ea1c3313d32999d8d6a48b4f6530d4437b38 # v4.37.4
uses: github/codeql-action/init@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v4.36.2
with:
languages: ${{ matrix.language }}
build-mode: none
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@f205ea1c3313d32999d8d6a48b4f6530d4437b38 # v4.37.4
uses: github/codeql-action/analyze@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v4.36.2
with:
category: "/language:${{ matrix.language }}"
+2 -2
View File
@@ -37,12 +37,12 @@ jobs:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Lint Dockerfile
uses: hadolint/hadolint-action@2a66e89f53d0771bb131a7fa31f3136336094aa6 # v3.4.0
uses: hadolint/hadolint-action@2332a7b74a6de0dda2e2221d575162eba76ba5e5 # v3.3.0
with:
dockerfile: Dockerfile
# DL3008: pinning apt package versions is impractical on a -slim base
+7 -7
View File
@@ -52,17 +52,17 @@ jobs:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Set up Buildx
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
# Build without pushing so a broken Dockerfile is caught here, and the
# exact image we ship is what gets scanned.
- name: Build image
uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf # v7.2.0
with:
context: .
push: false
@@ -93,15 +93,15 @@ jobs:
security-events: write # upload SARIF to the Security tab
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Set up Buildx
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
- name: Build image
uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf # v7.2.0
with:
context: .
push: false
@@ -119,7 +119,7 @@ jobs:
TRIVY_DB_REPOSITORY: ghcr.io/aquasecurity/trivy-db:2
- name: Upload Trivy results
uses: github/codeql-action/upload-sarif@f205ea1c3313d32999d8d6a48b4f6530d4437b38 # v4.37.4
uses: github/codeql-action/upload-sarif@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v4.36.2
with:
sarif_file: trivy-results.sarif
category: trivy-image
+3 -3
View File
@@ -36,7 +36,7 @@ jobs:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
@@ -55,12 +55,12 @@ jobs:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
with:
python-version: '3.12'
+8 -8
View File
@@ -45,20 +45,20 @@ jobs:
arch: arm64
runner: ubuntu-24.04-arm
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Set up Buildx
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
- name: Log in to GHCR
uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Build and push by digest
id: build
uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf # v7.2.0
with:
context: .
platforms: ${{ matrix.platform }}
@@ -86,7 +86,7 @@ jobs:
contents: read
packages: write
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Read APP_VERSION + short sha
@@ -103,16 +103,16 @@ jobs:
pattern: digest-*
merge-multiple: true
- name: Set up Buildx
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
- name: Log in to GHCR
uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Compute tags
id: meta
uses: docker/metadata-action@dc802804100637a589fabce1cb79ff13a1411302 # v6.2.0
uses: docker/metadata-action@80c7e94dd9b9319bd5eb7a0e0fe9291e23a2a2e9 # v6.1.0
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
tags: |
@@ -2,7 +2,7 @@ name: ci / issue description check
on:
issues:
types: [opened, edited, reopened, closed]
types: [opened, edited, reopened]
permissions:
issues: write
@@ -14,7 +14,7 @@ jobs:
# Skip bots (Dependabot, release-drafter, etc.)
if: ${{ github.event.issue.user.type != 'Bot' }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
sparse-checkout: .github/scripts
persist-credentials: false
+1 -1
View File
@@ -23,7 +23,7 @@ jobs:
# Skip bots: they open PRs programmatically and have their own process.
if: github.event.pull_request.user.type != 'Bot'
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
ref: ${{ github.base_ref }}
sparse-checkout: .github/scripts
+1 -1
View File
@@ -35,7 +35,7 @@ jobs:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
# Full history so a secret committed in an earlier commit (and later
# deleted) is still caught -- deletion does not remove it from Git.
+3 -3
View File
@@ -36,7 +36,7 @@ jobs:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
@@ -61,12 +61,12 @@ jobs:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
with:
python-version: '3.12'
+1 -1
View File
@@ -692,7 +692,7 @@ from routes.history.history_routes import setup_history_routes
app.include_router(setup_history_routes(session_manager, upload_handler=upload_handler))
# Search
from routes.search.search_routes import setup_search_routes
from routes.search_routes import setup_search_routes
app.include_router(setup_search_routes(config))
# Presets
-1
View File
@@ -67,7 +67,6 @@ services:
- ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=${ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES:-26214400}
- ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
- ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
- ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
- DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
- GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
- GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
-1
View File
@@ -66,7 +66,6 @@ services:
- ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=${ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES:-26214400}
- ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
- ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
- ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
- DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
- GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
- GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
-1
View File
@@ -55,7 +55,6 @@ services:
- ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES=${ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES:-26214400}
- ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
- ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
- ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
- DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
- GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
- GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
+1 -4
View File
@@ -38,10 +38,7 @@ python-dateutil
caldav
cryptography
bcrypt
# Built-in servers use the v1 low-level Server decorator API. MCP SDK v2 is a
# breaking rewrite, so keep fresh installs on the maintained v1 line until the
# servers are migrated together.
mcp<2
mcp
pyotp
qrcode[pil]
croniter
+61 -18
View File
@@ -1,11 +1,13 @@
# routes/personal_routes.py
"""Routes for personal documents management."""
import asyncio
import os
import logging
import shutil
import uuid
from typing import Any, Dict, List, Tuple
from fastapi import APIRouter, HTTPException, Query, Request, UploadFile, File, Depends
from fastapi.concurrency import run_in_threadpool
from src.request_models import DirectoryRequest
from core.constants import BASE_DIR, PERSONAL_DIR, PERSONAL_UPLOADS_DIR
from src.rag_singleton import get_rag_manager
@@ -18,7 +20,6 @@ UPLOADS_DIR = PERSONAL_UPLOADS_DIR
logger = logging.getLogger(__name__)
def _personal_upload_dir_for_owner(owner: str | None, *, create: bool = True) -> str:
"""Return the per-owner upload directory used for direct RAG uploads."""
owner_segment = secure_filename((owner or "local").strip())[:80] or "local"
@@ -141,6 +142,22 @@ def setup_personal_routes(personal_docs_manager, rag_manager, rag_available):
"""
router = APIRouter(prefix="/api/personal")
# Serializes directory index jobs across requests. Indexing runs in the
# threadpool (#5558), so concurrent requests would otherwise run in parallel
# and race PersonalDocsManager's unsynchronized list mutations and file
# writes; before the threadpool move they serialized on the blocked event
# loop, so one-at-a-time is behavior parity.
#
# An asyncio.Lock acquired in the async handler BEFORE offloading: a waiting
# request parks on the event loop instead of pinning a threadpool worker (an
# earlier threading.Lock taken INSIDE the worker meant queued jobs held pool
# tokens while blocked, starving every other run_in_threadpool caller).
# add/remove/reload all take this lock, so their mutations never interleave.
# Per-router (not module-global) so each app binds it to its own event loop.
# Scope is the single process: multi-worker deployments would need a shared
# lock (out of scope for #5558).
_index_job_lock = asyncio.Lock()
def _rag():
"""Get the current RAG manager, retrying init if needed."""
return get_rag_manager()
@@ -172,8 +189,12 @@ def setup_personal_routes(personal_docs_manager, rag_manager, rag_available):
return {"files": files, "directories": directories}
@router.post("/reload")
def api_personal_reload(owner: str = Depends(require_user), _admin: None = Depends(require_admin)):
personal_docs_manager.refresh_index()
async def api_personal_reload(owner: str = Depends(require_user), _admin: None = Depends(require_admin)):
# refresh_index() re-extracts text across every tracked directory —
# blocking work. Take the shared job lock (so it cannot race an add /
# remove) and run it off the event loop.
async with _index_job_lock:
await run_in_threadpool(personal_docs_manager.refresh_index)
return {"ok": True, "count": len(personal_docs_manager.index)}
@router.post("/add_directory")
@@ -207,12 +228,26 @@ def setup_personal_routes(personal_docs_manager, rag_manager, rag_available):
# Use the RAGManager to index the directory
rag = _rag()
if rag:
result = rag.index_personal_documents(directory, owner=owner)
def _index_directory():
result = rag.index_personal_documents(directory, owner=owner)
if result["success"]:
# Also update the personal_docs_manager to track this
# directory. Kept inside the offloaded call: it triggers
# refresh_index(), which re-extracts text across tracked
# directories.
personal_docs_manager.add_directory(directory, index=False)
return result
# Indexing walks, embeds, and stores the whole tree — minutes
# on a real directory. The handler is async, so calling it
# inline runs it on the event loop and every other request
# queues behind it until it finishes (#5558). Serialize on the
# async job lock BEFORE offloading so a queued request parks on
# the loop instead of pinning a threadpool worker.
async with _index_job_lock:
result = await run_in_threadpool(_index_directory)
if result["success"]:
# Also update the personal_docs_manager to track this directory
personal_docs_manager.add_directory(directory, index=False)
return {
"success": True,
"message": f"Successfully indexed {result['indexed_count']} chunks from {directory}",
@@ -251,17 +286,25 @@ def setup_personal_routes(personal_docs_manager, rag_manager, rag_available):
logger.info(f"Removing directory from RAG: {directory}")
# Always remove from personal_docs_manager tracking
if hasattr(personal_docs_manager, 'remove_directory'):
personal_docs_manager.remove_directory(directory)
# Remove from RAG vector store (best-effort)
rag = _rag()
if rag:
try:
rag.remove_directory(directory)
except Exception as e:
logger.warning(f"RAG removal failed for directory {directory}: {e}")
def _remove_directory():
# Always remove from personal_docs_manager tracking. This
# mutates the same unsynchronized list/index an add job touches
# and re-extracts text (refresh_index), so it is blocking work.
if hasattr(personal_docs_manager, 'remove_directory'):
personal_docs_manager.remove_directory(directory)
# Remove from RAG vector store (best-effort).
if rag:
try:
rag.remove_directory(directory)
except Exception as e:
logger.warning(f"RAG removal failed for directory {directory}: {e}")
# Same job lock as add/reload so remove cannot interleave with an
# in-flight add; offloaded off the event loop.
async with _index_job_lock:
await run_in_threadpool(_remove_directory)
return {
"success": True,
-5
View File
@@ -1,5 +0,0 @@
"""Search route domain package (slice 2j, #4082/#4071).
Contains search_routes.py, migrated from the flat routes/ directory.
Backward-compat shim at routes/search_routes.py re-exports from here.
"""
-111
View File
@@ -1,111 +0,0 @@
"""Search routes — /api/search/config GET, /api/search POST."""
import logging
from typing import Dict, Any
from fastapi import APIRouter, Request
import time
from services.search import get_search_config, comprehensive_web_search, PROVIDER_INFO
from services.search.core import _call_provider
from services.search.providers import _get_provider_key, _get_search_instance
logger = logging.getLogger(__name__)
async def _request_values(request: Request) -> Dict[str, Any]:
"""Accept JSON, form data, or query params for search endpoints.
The browser UI posts FormData, while the agent's generic app_api tool
posts JSON. FastAPI Form(...) rejects JSON with a 422 before our handler
runs, which made the model think SearXNG was broken.
"""
values: Dict[str, Any] = dict(request.query_params)
content_type = (request.headers.get("content-type") or "").lower()
try:
if "application/json" in content_type:
body = await request.json()
if isinstance(body, dict):
values.update(body)
else:
form = await request.form()
values.update(dict(form))
except Exception:
pass
return values
def setup_search_routes(config) -> APIRouter:
router = APIRouter(tags=["search"])
@router.get("/api/search/config")
async def get_search_settings() -> Dict[str, Any]:
return get_search_config()
@router.post("/api/search")
async def do_web_search(request: Request) -> Dict[str, Any]:
"""Standalone web search — returns context string + source list.
Used by Compare mode to pre-search once and share results across panes.
"""
values = await _request_values(request)
query = str(values.get("query") or values.get("q") or "").strip()
if not query:
return {"context": "", "sources": [], "error": "query is required"}
time_filter = values.get("time_filter") or values.get("freshness")
if time_filter is not None:
time_filter = str(time_filter).strip() or None
try:
context, sources = comprehensive_web_search(
query, return_sources=True, time_filter=time_filter,
)
return {"context": context, "sources": sources}
except Exception as e:
logger.error(f"Standalone web search failed: {e}")
return {"context": "", "sources": [], "error": str(e)}
@router.get("/api/search/providers")
async def list_search_providers():
"""Return available search providers with config status."""
providers = []
for pid, (label, needs_key, needs_url) in PROVIDER_INFO.items():
if pid == "disabled":
continue
available = True
if needs_key and not _get_provider_key(pid):
available = False
if needs_url and pid == "searxng" and not _get_search_instance():
available = False
providers.append({
"id": pid,
"label": label,
"available": available,
})
return providers
@router.post("/api/search/query")
async def search_with_provider(request: Request) -> Dict[str, Any]:
"""Search using a specific provider. Used by compare search mode."""
values = await _request_values(request)
query = str(values.get("query") or values.get("q") or "").strip()
provider = str(values.get("provider") or "").strip()
try:
count = int(values.get("count") or values.get("limit") or 10)
except Exception:
count = 10
if not query:
return {"results": [], "provider": provider, "error": "query is required"}
if provider not in PROVIDER_INFO or provider == "disabled":
return {"results": [], "provider": provider, "error": "Unknown provider"}
t0 = time.time()
try:
results = _call_provider(provider, query, min(count, 20))
elapsed = round(time.time() - t0, 2)
return {"results": results, "provider": provider, "time": elapsed}
except Exception as e:
elapsed = round(time.time() - t0, 2)
logger.error(f"Search provider {provider} failed: {e}")
return {"results": [], "provider": provider, "time": elapsed, "error": str(e)}
return router
+107 -9
View File
@@ -1,13 +1,111 @@
"""Backward-compat shim — canonical location is routes/search/search_routes.py.
"""Search routes — /api/search/config GET, /api/search POST."""
This module is replaced in ``sys.modules`` by the canonical module object so
that ``import routes.search_routes`` and ``from routes.search_routes import X``
keep resolving to the canonical module. Keeps existing import paths working
after slice 2j (#4082/#4071).
"""
import logging
from typing import Dict, Any
import sys as _sys
from fastapi import APIRouter, Request
from routes.search import search_routes as _canonical # noqa: F401
import time
_sys.modules[__name__] = _canonical
from services.search import get_search_config, comprehensive_web_search, PROVIDER_INFO
from services.search.core import _call_provider
from services.search.providers import _get_provider_key, _get_search_instance
logger = logging.getLogger(__name__)
async def _request_values(request: Request) -> Dict[str, Any]:
"""Accept JSON, form data, or query params for search endpoints.
The browser UI posts FormData, while the agent's generic app_api tool
posts JSON. FastAPI Form(...) rejects JSON with a 422 before our handler
runs, which made the model think SearXNG was broken.
"""
values: Dict[str, Any] = dict(request.query_params)
content_type = (request.headers.get("content-type") or "").lower()
try:
if "application/json" in content_type:
body = await request.json()
if isinstance(body, dict):
values.update(body)
else:
form = await request.form()
values.update(dict(form))
except Exception:
pass
return values
def setup_search_routes(config) -> APIRouter:
router = APIRouter(tags=["search"])
@router.get("/api/search/config")
async def get_search_settings() -> Dict[str, Any]:
return get_search_config()
@router.post("/api/search")
async def do_web_search(request: Request) -> Dict[str, Any]:
"""Standalone web search — returns context string + source list.
Used by Compare mode to pre-search once and share results across panes.
"""
values = await _request_values(request)
query = str(values.get("query") or values.get("q") or "").strip()
if not query:
return {"context": "", "sources": [], "error": "query is required"}
time_filter = values.get("time_filter") or values.get("freshness")
if time_filter is not None:
time_filter = str(time_filter).strip() or None
try:
context, sources = comprehensive_web_search(
query, return_sources=True, time_filter=time_filter,
)
return {"context": context, "sources": sources}
except Exception as e:
logger.error(f"Standalone web search failed: {e}")
return {"context": "", "sources": [], "error": str(e)}
@router.get("/api/search/providers")
async def list_search_providers():
"""Return available search providers with config status."""
providers = []
for pid, (label, needs_key, needs_url) in PROVIDER_INFO.items():
if pid == "disabled":
continue
available = True
if needs_key and not _get_provider_key(pid):
available = False
if needs_url and pid == "searxng" and not _get_search_instance():
available = False
providers.append({
"id": pid,
"label": label,
"available": available,
})
return providers
@router.post("/api/search/query")
async def search_with_provider(request: Request) -> Dict[str, Any]:
"""Search using a specific provider. Used by compare search mode."""
values = await _request_values(request)
query = str(values.get("query") or values.get("q") or "").strip()
provider = str(values.get("provider") or "").strip()
try:
count = int(values.get("count") or values.get("limit") or 10)
except Exception:
count = 10
if not query:
return {"results": [], "provider": provider, "error": "query is required"}
if provider not in PROVIDER_INFO or provider == "disabled":
return {"results": [], "provider": provider, "error": "Unknown provider"}
t0 = time.time()
try:
results = _call_provider(provider, query, min(count, 20))
elapsed = round(time.time() - t0, 2)
return {"results": results, "provider": provider, "time": elapsed}
except Exception as e:
elapsed = round(time.time() - t0, 2)
logger.error(f"Search provider {provider} failed: {e}")
return {"results": [], "provider": provider, "time": elapsed, "error": str(e)}
return router
+1 -1
View File
@@ -1409,7 +1409,7 @@ def setup_skills_routes(skills_manager: SkillsManager) -> APIRouter:
# Prefer the configured DEFAULT (→ Utility) model — not the current chat
# session's model. Fall back to the caller's session model only if unset.
url, model, headers = resolve_endpoint("utility", owner=user)
url, model, headers = resolve_endpoint("default", owner=user)
if not url or not model:
url = url or ((body.get("endpoint_url") or "").strip() or None)
model = model or ((body.get("model") or "").strip() or None)
+2 -2
View File
@@ -50,7 +50,7 @@ import json
import logging
import re
from dataclasses import dataclass, field
from datetime import datetime, timezone
from datetime import datetime
from typing import Any, Dict, List, Optional
logger = logging.getLogger(__name__)
@@ -441,4 +441,4 @@ class Skill:
def _now_iso() -> str:
return datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
return datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
-53
View File
@@ -2,7 +2,6 @@
"""Multi-provider TTS service — dispatches to local Kokoro, OpenAI-compatible API, or browser."""
import io
import os
import wave
import logging
import hashlib
@@ -42,11 +41,6 @@ class TTSService:
self.cache_dir = Path(cache_dir)
self.cache_dir.mkdir(parents=True, exist_ok=True)
self._kokoro = None # lazy-init
try:
self.max_cache_bytes = int(os.getenv("ODYSSEUS_TTS_CACHE_MAX_BYTES", 500 * 1024 * 1024))
except ValueError:
self.max_cache_bytes = 500 * 1024 * 1024
# ── Settings ──
@@ -95,53 +89,6 @@ class TTSService:
ext = ".mp3" if (len(data) >= 3 and (data[:3] == b'ID3' or (data[0] == 0xff and (data[1] & 0xe0) == 0xe0))) else ".wav"
(self.cache_dir / f"{key}{ext}").write_bytes(data)
self._enforce_cache_limit()
def _enforce_cache_limit(self):
"""Evicts oldest files if the cache exceeds the configured byte limit."""
if self.max_cache_bytes <= 0:
return
try:
files = []
total_size = 0
# Safely scan files and sum sizes, ignoring files deleted mid-scan
for f in self.cache_dir.iterdir():
try:
if f.is_file() and f.suffix.lower() in (".mp3", ".wav"):
files.append(f)
total_size += f.stat().st_size
except OSError:
continue
if total_size > self.max_cache_bytes:
logger.info(
f"TTS cache ({total_size} bytes) exceeded limit ({self.max_cache_bytes} bytes). Evicting oldest files."
)
# Sort files by modification time (oldest first)
try:
files.sort(key=lambda f: f.stat().st_mtime)
except OSError as e:
logger.warning(f"Failed to sort cache files by mtime: {e}")
# Trim down to 80% of max capacity
target_size = self.max_cache_bytes * 0.8
while files and total_size > target_size:
f = files.pop(0)
try:
size = f.stat().st_size
f.unlink()
total_size -= size
except OSError as e:
logger.warning(f"Failed to evict cache file {f}: {e}")
continue
except Exception as e:
logger.warning(f"Error enforcing TTS cache limit: {e}", exc_info=True)
def clear_cache(self):
count = 0
for f in self.cache_dir.glob("*.*"):
+7 -19
View File
@@ -1237,27 +1237,15 @@ def _anthropic_rejects_temperature(model: str) -> bool:
return False
# `(?<![a-z])` anchors "opus" to a word boundary so a substring match like
# `oct-opus`/`octopus-4-8` can't be read as Opus (it would otherwise strip
# temperature). Both version components are capped at 1-2 digits and forbid a
# trailing digit, so an 8-digit date can never be read as a version number:
# `claude-opus-4-20250514` (Opus 4.0) parses as major-only rather than reading
# `20250514` as a giant minor, and `claude-3-opus-20240229` (legacy Claude 3
# Opus, date directly after "opus-") fails to match at all rather than reading
# the date as a giant major. Dated 4.7+ snapshots (`claude-opus-4-7-20260201`)
# keep their explicit minor and are still matched.
#
# The minor is optional and a missing minor reads as `.0`, so major-only ids
# like `claude-opus-5` are correctly treated as >= 4.7 (issue #5753). Without
# this, every Opus 5 call kept `temperature` and failed with HTTP 400 — visible
# only on paths that pass a temperature, e.g. scheduled tasks inheriting
# `stream_agent_loop`'s 0.3 default, which returned empty responses.
match = re.search(
r"(?<![a-z])opus[-_]?(\d{1,2})(?!\d)(?:[-_.](\d{1,2})(?!\d))?", model.lower()
)
# temperature). Cap the minor at 1-2 digits and forbid a trailing digit so a
# dated id like `claude-opus-4-20250514` (Opus 4.0) parses as major-only (no
# minor match, kept) instead of reading the date `20250514` as a giant minor
# that would falsely test >= 4.7. Dated 4.7+ snapshots (`claude-opus-4-7-
# 20260201`) keep their explicit minor and are still matched.
match = re.search(r"(?<![a-z])opus[-_]?(\d+)[-_.](\d{1,2})(?!\d)", model.lower())
if not match:
return False
major = int(match.group(1))
minor = int(match.group(2)) if match.group(2) else 0
return (major, minor) >= (4, 7)
return (int(match.group(1)), int(match.group(2))) >= (4, 7)
# Reasoning effort level sent to Mistral thinking-capable models. Mistral's
# API accepts "high", "medium", "low", "none" — see
+7 -13
View File
@@ -758,36 +758,30 @@ export function mdToHtml(src, opts) {
// Remove empty paragraphs
s = s.replace(/<p><\/p>/g, '');
// Every restore below passes a function replacer rather than the block string
// itself. With a string replacement, `String.replace` reads `$&`, `` $` ``,
// `$'` and `$$` in the *replacement* as substitution patterns, so a restored
// block containing them is corrupted: `$&` re-inserts the placeholder, `` $` ``
// and `$'` splice in the surrounding document, and `$$` collapses to `$`. Those
// sequences are ordinary content in fenced code (`perl -pe 's/x/$& y/'`,
// `echo "$$USD"`). A function replacer inserts its return value verbatim.
// CRITICAL: Restore allowed HTML blocks first
allowedHtmlBlocks.forEach((block, index) => {
s = s.replace(`___ALLOWED_HTML_${index}___`, () => block);
s = s.replace(`___ALLOWED_HTML_${index}___`, block);
});
// Restore math blocks
mathBlocks.forEach((block, index) => {
s = s.replace(`___MATH_BLOCK_${index}___`, () => block);
s = s.replace(`___MATH_BLOCK_${index}___`, block);
});
// Restore mermaid diagram blocks
mermaidBlocks.forEach((block, index) => {
s = s.replace(`___MERMAID_BLOCK_${index}___`, () => block);
s = s.replace(`___MERMAID_BLOCK_${index}___`, block);
});
// CRITICAL: Restore code blocks at the end
codeBlocks.forEach((block, index) => {
s = s.replace(`___CODE_BLOCK_${index}___`, () => block);
s = s.replace(`___CODE_BLOCK_${index}___`, block);
});
// Restore inline code spans last, so placeholders carried inside restored
// <a>/allowed-HTML blocks are resolved too.
// <a>/allowed-HTML blocks are resolved too. The function replacer keeps the
// escaped code literal — e.g. a shell snippet like `echo $1` is not treated
// as a regex back-reference.
inlineCodeBlocks.forEach((block, index) => {
s = s.replace(`___INLINE_CODE_${index}___`, () => block);
});
+22 -25
View File
@@ -3031,14 +3031,12 @@ async function initEmailAccountsSettings() {
const body = {
name: el('eaf-name').value.trim() || el('eaf-from').value.trim(),
from_address: el('eaf-from').value.trim(),
display_name: el('eaf-display-name').value.trim(),
imap_host: el('eaf-imap-host').value.trim(),
imap_port: parseInt(el('eaf-imap-port').value) || 993,
imap_user: el('eaf-imap-user').value.trim(),
imap_starttls: el('eaf-imap-starttls').checked,
smtp_host: el('eaf-smtp-host').value.trim(),
smtp_port: parseInt(el('eaf-smtp-port').value) || 587,
smtp_security: el('eaf-smtp-security').value,
smtp_user: el('eaf-imap-user').value.trim(),
};
if (!body.name) { el('eaf-msg').textContent = 'Enter a Name or Email first'; el('eaf-msg').style.color = 'var(--red)'; return; }
@@ -5790,30 +5788,29 @@ export function close() {
window.history.replaceState(null, '', clean);
const success = sp.has('email_oauth_success');
const errMsg = sp.get('email_oauth_error') || '';
// Open settings → integrations once the document is ready. This module owns
// the open() API, so it does not need to wait for a window-level alias.
function _showResult() {
open('integrations');
// Brief toast-style banner.
const banner = document.createElement('div');
banner.textContent = success
? 'Google account connected — email is ready'
: `Google OAuth failed: ${errMsg || 'unknown error'}`;
Object.assign(banner.style, {
position: 'fixed', bottom: '24px', left: '50%', transform: 'translateX(-50%)',
background: success ? 'var(--accent, #50fa7b)' : 'var(--red, #ff5555)',
color: '#000', padding: '8px 18px', borderRadius: '6px', fontSize: '12px',
fontWeight: '600', zIndex: '99999', pointerEvents: 'none',
boxShadow: '0 2px 12px rgba(0,0,0,0.3)',
});
document.body.appendChild(banner);
setTimeout(() => banner.remove(), 4000);
}
if (document.readyState === 'loading') {
document.addEventListener('DOMContentLoaded', _showResult, { once: true });
} else {
_showResult();
// Open settings → integrations after the app has initialised.
function _tryOpen() {
if (window.settingsModule && typeof window.settingsModule.open === 'function') {
window.settingsModule.open('integrations');
// Brief toast-style banner.
const banner = document.createElement('div');
banner.textContent = success
? 'Google account connected — email is ready'
: `Google OAuth failed: ${errMsg || 'unknown error'}`;
Object.assign(banner.style, {
position: 'fixed', bottom: '24px', left: '50%', transform: 'translateX(-50%)',
background: success ? 'var(--accent, #50fa7b)' : 'var(--red, #ff5555)',
color: '#000', padding: '8px 18px', borderRadius: '6px', fontSize: '12px',
fontWeight: '600', zIndex: '99999', pointerEvents: 'none',
boxShadow: '0 2px 12px rgba(0,0,0,0.3)',
});
document.body.appendChild(banner);
setTimeout(() => banner.remove(), 4000);
} else {
setTimeout(_tryOpen, 100);
}
}
_tryOpen();
})();
const settingsModule = { open, close, initIntegrations, initUnifiedIntegrations, syncAdminVisibility, refreshAiModelEndpoints };
+253
View File
@@ -0,0 +1,253 @@
"""Regression guard for #5558 — POST /api/personal/add_directory must not run
the indexing job on the event loop.
The handler is ``async def`` but called ``rag.index_personal_documents``
(os.walk + file reads + per-chunk embedding + Chroma inserts) inline, so
FastAPI ran the whole job on the event loop and every other request queued
behind it: indexing a real directory froze the UI and API for 25+ minutes.
``personal_docs_manager.add_directory`` sits in the same blocking section it
triggers ``refresh_index()``, which re-extracts text across tracked dirs.
These tests build the real router with fake managers and compare the thread
the indexing work runs on against the event loop's thread.
"""
import asyncio
import os
import threading
os.environ.setdefault("DATABASE_URL", "sqlite:///:memory:")
import httpx
from fastapi import FastAPI
from fastapi.testclient import TestClient
def _serialization_probe():
"""Shared counter proving two critical sections never overlap."""
state = {"active": 0, "max_active": 0}
lock = threading.Lock()
def enter():
with lock:
state["active"] += 1
state["max_active"] = max(state["max_active"], state["active"])
def leave():
with lock:
state["active"] -= 1
return state, enter, leave
# Concurrency tests are `async def` (pyproject asyncio_mode="auto") and drive the
# ASGI app through httpx.ASGITransport + AsyncClient + asyncio.gather, NOT starlette
# TestClient + ThreadPoolExecutor: the job lock is an asyncio.Lock acquired in the
# async handler, and TestClient's portal-thread dispatch deadlocks against it (same
# reason test_notes_fail_closed_auth.py uses ASGITransport). asyncio.gather runs both
# requests on the test's own loop.
def _async_client(app):
return httpx.AsyncClient(transport=httpx.ASGITransport(app=app), base_url="http://t")
import routes.personal_routes as personal_routes
from core.middleware import require_admin
from src.auth_helpers import require_user
class _FakeRag:
def __init__(self, record):
self._record = record
def index_personal_documents(self, directory, owner=None):
self._record["index_thread"] = threading.get_ident()
return {"success": True, "indexed_count": 3, "failed_count": 0}
class _FakeDocsManager:
def __init__(self, record):
self._record = record
self.index = []
def add_directory(self, directory, *, index=True, owner=None):
self._record["bookkeeping_thread"] = threading.get_ident()
self._record["bookkeeping_index_flag"] = index
def _build_app(tmp_path, monkeypatch, record):
monkeypatch.setattr(personal_routes, "PERSONAL_DIR", str(tmp_path))
monkeypatch.setattr(personal_routes, "get_rag_manager", lambda: _FakeRag(record))
app = FastAPI()
app.include_router(
personal_routes.setup_personal_routes(_FakeDocsManager(record), None, True)
)
app.dependency_overrides[require_user] = lambda: "tester"
app.dependency_overrides[require_admin] = lambda: None
@app.get("/loop-thread")
async def loop_thread_probe():
return {"thread": threading.get_ident()}
return app
def test_indexing_runs_off_the_event_loop(tmp_path, monkeypatch):
record = {}
app = _build_app(tmp_path, monkeypatch, record)
target = tmp_path / "docs"
target.mkdir()
# Context-manager client: one portal/event loop serves both requests, so
# the probe and the POST are guaranteed to see the same loop thread.
with TestClient(app) as client:
loop_thread = client.get("/loop-thread").json()["thread"]
resp = client.post(
"/api/personal/add_directory", json={"directory": str(target)}
)
assert resp.status_code == 200
assert record["index_thread"] != loop_thread, (
"index_personal_documents ran on the event loop thread — every other "
"request queues behind the indexing job (#5558)"
)
assert record["bookkeeping_thread"] != loop_thread, (
"personal_docs_manager.add_directory (refresh_index) ran on the event "
"loop thread"
)
def test_response_and_bookkeeping_unchanged(tmp_path, monkeypatch):
record = {}
app = _build_app(tmp_path, monkeypatch, record)
target = tmp_path / "docs"
target.mkdir()
client = TestClient(app)
resp = client.post("/api/personal/add_directory", json={"directory": str(target)})
assert resp.status_code == 200
body = resp.json()
assert body["success"] is True
assert body["indexed_count"] == 3
assert body["failed_count"] == 0
assert body["directory"] == os.path.realpath(str(target))
assert record["bookkeeping_index_flag"] is False
async def test_concurrent_add_directory_requests_serialize_indexing(tmp_path, monkeypatch):
"""Off-loop execution must not mean parallel index jobs: concurrent
requests would race PersonalDocsManager's unsynchronized list mutations
and file writes (save_directories/_save_excluded are plain open('w'))."""
import time
state, enter, leave = _serialization_probe()
def _slow_index(self, directory, owner=None):
enter(); time.sleep(0.2); leave()
return {"success": True, "indexed_count": 1, "failed_count": 0}
monkeypatch.setattr(_FakeRag, "index_personal_documents", _slow_index)
record = {}
app = _build_app(tmp_path, monkeypatch, record)
for name in ("docs_a", "docs_b"):
(tmp_path / name).mkdir()
async with _async_client(app) as ac:
results = await asyncio.gather(
ac.post("/api/personal/add_directory", json={"directory": str(tmp_path / "docs_a")}),
ac.post("/api/personal/add_directory", json={"directory": str(tmp_path / "docs_b")}),
)
assert all(r.status_code == 200 for r in results)
assert state["max_active"] == 1, (
f"{state['max_active']} index jobs ran in parallel — concurrent "
"add_directory requests must serialize"
)
def test_failed_indexing_still_returns_500(tmp_path, monkeypatch):
record = {}
app = _build_app(tmp_path, monkeypatch, record)
target = tmp_path / "docs"
target.mkdir()
def _fail(directory, owner=None):
return {"success": False, "message": "boom"}
monkeypatch.setattr(_FakeRag, "index_personal_documents", staticmethod(_fail))
client = TestClient(app)
resp = client.post("/api/personal/add_directory", json={"directory": str(target)})
assert resp.status_code == 500
assert "boom" in resp.json()["detail"]
async def test_add_and_remove_serialize(tmp_path, monkeypatch):
"""#5634: remove must hold the SAME job lock as add. Otherwise a remove
running while an add job is in flight races PersonalDocsManager's
unsynchronized list/index mutations the inconsistent state the PR's
'add/remove are serialized' guarantee claims to prevent."""
import time
state, enter, leave = _serialization_probe()
def _slow_index(self, directory, owner=None):
enter(); time.sleep(0.25); leave()
return {"success": True, "indexed_count": 1, "failed_count": 0}
def _slow_remove(self, directory):
enter(); time.sleep(0.25); leave()
monkeypatch.setattr(_FakeRag, "index_personal_documents", _slow_index)
monkeypatch.setattr(_FakeDocsManager, "remove_directory", _slow_remove, raising=False)
record = {}
app = _build_app(tmp_path, monkeypatch, record)
(tmp_path / "docs_a").mkdir()
(tmp_path / "docs_b").mkdir()
async with _async_client(app) as ac:
results = await asyncio.gather(
ac.post("/api/personal/add_directory", json={"directory": str(tmp_path / "docs_a")}),
ac.delete("/api/personal/remove_directory", params={"directory": str(tmp_path / "docs_b")}),
)
assert all(r.status_code == 200 for r in results)
assert state["max_active"] == 1, (
f"{state['max_active']} add/remove critical sections overlapped — "
"remove must hold the same index job lock as add"
)
async def test_reload_serializes_with_add(tmp_path, monkeypatch):
"""#5634: POST /reload rebuilds the index via refresh_index(); it must hold
the same job lock so it cannot race an in-flight add job."""
import time
state, enter, leave = _serialization_probe()
def _slow_index(self, directory, owner=None):
enter(); time.sleep(0.25); leave()
return {"success": True, "indexed_count": 1, "failed_count": 0}
def _slow_refresh(self):
enter(); time.sleep(0.25); leave()
monkeypatch.setattr(_FakeRag, "index_personal_documents", _slow_index)
monkeypatch.setattr(_FakeDocsManager, "refresh_index", _slow_refresh, raising=False)
record = {}
app = _build_app(tmp_path, monkeypatch, record)
(tmp_path / "docs_a").mkdir()
async with _async_client(app) as ac:
results = await asyncio.gather(
ac.post("/api/personal/add_directory", json={"directory": str(tmp_path / "docs_a")}),
ac.post("/api/personal/reload"),
)
assert all(r.status_code == 200 for r in results)
assert state["max_active"] == 1, (
f"{state['max_active']} add/reload critical sections overlapped — "
"reload must hold the same index job lock as add"
)
@@ -1,15 +0,0 @@
"""Regression coverage for SMTP security saved before Google OAuth."""
from pathlib import Path
_REPO = Path(__file__).resolve().parents[1]
def test_email_tab_oauth_connect_persists_selected_smtp_security():
source = (_REPO / "static" / "js" / "settings.js").read_text(encoding="utf-8")
start = source.index("el('eaf-oauth-btn').addEventListener")
handler_body = source[start:source.index("if (!body.name)", start)]
assert "smtp_security: el('eaf-smtp-security').value" in handler_body
assert "display_name: el('eaf-display-name').value.trim()" in handler_body
@@ -1,19 +0,0 @@
"""Regression coverage for the settings UI after Google OAuth redirects."""
from pathlib import Path
_REPO = Path(__file__).resolve().parents[1]
def test_oauth_redirect_uses_the_module_local_settings_api():
source = (_REPO / "static" / "js" / "settings.js").read_text(encoding="utf-8")
handler = source[
source.index("(function _handleOauthRedirect"):
source.index("const settingsModule =")
]
assert "open('integrations');" in handler
assert "window.settingsModule" not in handler
assert "window.__odysseusAppStarted" not in handler
assert "document.addEventListener('DOMContentLoaded', _showResult, { once: true })" in handler
-86
View File
@@ -1,86 +0,0 @@
"""Regression coverage for issue-description label lifecycle events."""
import json
import shutil
import subprocess
from pathlib import Path
import pytest
_REPO = Path(__file__).resolve().parent.parent
_CHECKER = _REPO / ".github" / "scripts" / "check-issue-description.js"
_WORKFLOW = _REPO / ".github" / "workflows" / "issue-description-check.yml"
pytestmark = pytest.mark.skipif(not shutil.which("node"), reason="node not on PATH")
def _run_closed_issue(action):
harness = r"""
const checkIssueDescription = require(process.argv[1]);
const action = process.argv[2];
const calls = [];
const unexpected = (name) => async () => {
throw new Error(`${name} should not be called for a closed issue`);
};
const github = {
rest: {
issues: {
removeLabel: async (params) => calls.push({ method: 'removeLabel', params }),
getLabel: unexpected('getLabel'),
addLabels: unexpected('addLabels'),
listComments: unexpected('listComments'),
createComment: unexpected('createComment'),
updateComment: unexpected('updateComment'),
deleteComment: unexpected('deleteComment'),
},
},
};
const context = {
payload: {
action,
issue: { number: 42, state: 'closed', body: '', labels: [] },
},
repo: { owner: 'odysseus-dev', repo: 'odysseus' },
};
const core = {
warning: unexpected('core.warning'),
setFailed: unexpected('core.setFailed'),
};
checkIssueDescription({ github, context, core })
.then(() => process.stdout.write(JSON.stringify(calls)))
.catch((error) => {
console.error(error);
process.exitCode = 1;
});
"""
proc = subprocess.run(
["node", "-e", harness, str(_CHECKER), action],
capture_output=True,
text=True,
cwd=str(_REPO),
timeout=30,
)
assert proc.returncode == 0, proc.stderr
return json.loads(proc.stdout)
def test_workflow_handles_issue_closures():
workflow = _WORKFLOW.read_text()
assert "types: [opened, edited, reopened, closed]" in workflow
@pytest.mark.parametrize("action", ["closed", "edited"])
def test_closed_issue_only_drops_ready_for_review(action):
assert _run_closed_issue(action) == [
{
"method": "removeLabel",
"params": {
"owner": "odysseus-dev",
"repo": "odysseus",
"issue_number": 42,
"name": "ready for review",
},
}
]
+1 -25
View File
@@ -29,13 +29,6 @@ from src.llm_core import _anthropic_rejects_temperature, _build_anthropic_payloa
"anthropic/claude-opus-4-7", # tolerate a provider-prefixed id
"claude-opus-4-10", # future minor still >= 4.7
"claude-opus-5-0", # future major
# Major-only ids: a missing minor reads as `.0`, so these are >= 4.7 too
# (issue #5753). Before the fix the version pattern required a minor, so
# these fell through to "accepts temperature" and every call 400'd.
"claude-opus-5",
"claude-opus-5-20260101", # major-only + dated snapshot
"anthropic/claude-opus-5", # major-only behind a provider prefix
"claude-opus-6", # future major-only
],
)
def test_opus_47_plus_rejects_temperature(model):
@@ -55,10 +48,7 @@ def test_opus_47_plus_rejects_temperature(model):
"claude-opus-4-6-20251201", # dated 4.6 snapshot — older, still keeps temperature
"claude-sonnet-4-6",
"claude-3-5-sonnet",
"claude-3-opus-20240229", # legacy Claude 3 Opus — date directly after
# "opus-", so the major must not swallow it as version 20240229 (that is
# what makes capping the major at 1-2 digits necessary once the minor
# became optional in #5753).
"claude-3-opus-20240229", # legacy Claude 3 Opus — no opus-N-M pattern, kept
"claude-haiku-4-5",
"claude-x",
"octopus-4-8", # "opus" only as a substring of another word — must not match
@@ -97,20 +87,6 @@ def test_payload_keeps_temperature_for_older_models():
assert _payload("claude-3-5-sonnet", 1.2)["temperature"] == 1.0
def test_payload_omits_temperature_for_major_only_opus_5():
# Issue #5753: the scheduled-task path calls stream_agent_loop() without a
# temperature and inherits its 0.3 default, so `claude-opus-5` 400'd on every
# run and surfaced as "the model returned an empty response". Interactive chat
# leaves temperature None and never hit it.
assert "temperature" not in _payload("claude-opus-5", 0.3)
def test_payload_keeps_temperature_for_legacy_claude_3_opus():
# Guards the major-digit cap: `opus-20240229` must not parse as version
# 20240229, or Claude 3 Opus would silently lose the caller's temperature.
assert _payload("claude-3-opus-20240229", 0.5)["temperature"] == 0.5
def test_payload_keeps_temperature_for_dated_opus_4_0():
# Anthropic's dated id for Opus 4.0 (claude-opus-4-20250514) is in this repo's
# ANTHROPIC_MODELS list. The date must not be misread as a >= 4.7 minor, or the
-44
View File
@@ -214,50 +214,6 @@ def test_inline_code_content_is_html_escaped(node_available):
assert "<b>" not in html
def test_fenced_code_keeps_dollar_ampersand(node_available):
# Issue #5663: the block-restore pass used a string replacement, so `$&` in a
# restored block was read as "the matched text" and re-inserted the
# placeholder. `perl -pe 's/world/$& again/'` rendered as
# "s/world/___CODE_BLOCK_0___amp; again/" — the trailing "amp;" is the orphan
# left behind after `$&` consumed the `$&` of the escaped `$&amp;`.
html = _run_markdown_case(
"```sh\necho \"hello world\" | perl -pe 's/world/$& again/'\n```"
)
assert "___CODE_BLOCK_" not in html
assert "s/world/$&amp; again/" in html
assert "amp; again" not in html.replace("$&amp; again", "")
def test_fenced_code_keeps_dollar_backtick_and_quote(node_available):
# `` $` `` and `$'` splice the text before/after the placeholder into the
# block. Unlike `$&` these leave no placeholder behind — the characters just
# vanish — so assert the content survives verbatim.
html = _run_markdown_case("```sh\nsed \"s/$`/x/\" && sed \"s/$'/y/\"\n```")
assert "___CODE_BLOCK_" not in html
assert "s/$`/x/" in html
assert "s/$&#39;/y/" in html
def test_fenced_code_keeps_double_dollar(node_available):
# `$$` collapsed to a single `$` in the restored block.
html = _run_markdown_case('```sh\necho "$$USD and $$"\n```')
assert "$$USD and $$" in html
def test_mermaid_block_keeps_dollar_ampersand(node_available):
# The mermaid restore site had the same hazard: a node label containing `$&`
# re-inserted the ___MERMAID_BLOCK_n___ placeholder into the diagram source,
# which then fails to parse. The math and allowed-HTML sites are fixed the
# same way; they need KaTeX/sanitizer conditions this harness doesn't set up.
html = _run_markdown_case('```mermaid\ngraph TD; A["$&"] --> B;\n```')
assert "___MERMAID_BLOCK_" not in html
assert "$&amp;" in html
def test_currency_dollar_amounts_are_not_rendered_as_math(node_available):
# "$5 to $10" used to pair the two dollar signs as inline-math delimiters
# and render "5 to" through KaTeX. Pandoc-style rules now reject it: the
@@ -1,15 +0,0 @@
"""Regression coverage for the built-in MCP servers' SDK compatibility line."""
from pathlib import Path
REQUIREMENTS = Path(__file__).resolve().parents[1] / "requirements.txt"
def test_mcp_requirement_excludes_breaking_v2_sdk():
requirements = [
line.split("#", 1)[0].strip().replace(" ", "")
for line in REQUIREMENTS.read_text(encoding="utf-8").splitlines()
]
assert "mcp<2" in requirements
-11
View File
@@ -1,11 +0,0 @@
"""Regression test for the search route shim (slice 2j, #4082/#4071)."""
import importlib
import routes.search_routes as _shim_search # noqa: F401
def test_legacy_and_canonical_search_module_are_same_object():
legacy = importlib.import_module("routes.search_routes")
canonical = importlib.import_module("routes.search.search_routes")
assert legacy is canonical
-58
View File
@@ -1,58 +0,0 @@
"""Regression for issue #5697 — skill timestamps must not use ``datetime.utcnow()``.
``_now_iso()`` builds the ``created`` value in skill frontmatter. ``utcnow()``
returns a *naive* datetime and has been deprecated since Python 3.12, scheduled
for removal. The replacement must stay timezone-aware while keeping the
serialized ``YYYY-MM-DDTHH:MM:SSZ`` shape, so skill files written by older
versions keep parsing.
The UTC check matters on its own: a bare ``datetime.now()`` also produces the
right shape, but emits local wall time, which would silently backdate or
postdate skills for every user outside UTC.
"""
import os
import re
import time
import warnings
from datetime import datetime, timezone
import pytest
from services.memory.skill_format import _now_iso
_ISO_Z = re.compile(r"^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z$")
def test_now_iso_keeps_serialized_shape():
assert _ISO_Z.match(_now_iso())
def test_now_iso_emits_no_deprecation_warning():
with warnings.catch_warnings(record=True) as caught:
warnings.simplefilter("always")
_now_iso()
assert not [w for w in caught if issubclass(w.category, DeprecationWarning)]
@pytest.mark.skipif(
not hasattr(time, "tzset"),
reason="time.tzset is unavailable on this platform",
)
def test_now_iso_is_utc_not_local_time():
"""Pin UTC under a non-UTC local timezone, where the two visibly diverge."""
original_tz = os.environ.get("TZ")
os.environ["TZ"] = "Asia/Amman" # UTC+3, never UTC
time.tzset()
try:
emitted = datetime.strptime(_now_iso(), "%Y-%m-%dT%H:%M:%SZ").replace(
tzinfo=timezone.utc
)
drift = abs((emitted - datetime.now(timezone.utc)).total_seconds())
assert drift < 60, f"timestamp is {drift}s off UTC — local time leaked in"
finally:
if original_tz is None:
os.environ.pop("TZ", None)
else:
os.environ["TZ"] = original_tz
time.tzset()
@@ -1,97 +0,0 @@
import os
import time
from pathlib import Path
import pytest
# Adjust the import path if your file is directly in ./services instead of ./services/tts
from services.tts.tts_service import TTSService
def test_cache_under_limit(tmp_path, monkeypatch):
"""Test that writing a file under the size limit does not trigger eviction."""
# Set a tiny limit: 100 bytes
monkeypatch.setenv("ODYSSEUS_TTS_CACHE_MAX_BYTES", "100")
# Initialize service with pytest's temporary directory
service = TTSService(cache_dir=str(tmp_path))
# Write a 40-byte file (under the 100-byte limit)
service._put_cache("test_key", b"x" * 40)
# Verify the file was written and nothing was deleted
files = list(tmp_path.glob("*.*"))
assert len(files) == 1
assert sum(f.stat().st_size for f in files) == 40
def test_cache_exceeds_limit_triggers_eviction(tmp_path, monkeypatch):
"""Test that exceeding the limit evicts the oldest files down to 80% capacity."""
# Set limit to 100 bytes. 80% target capacity will be 80 bytes.
monkeypatch.setenv("ODYSSEUS_TTS_CACHE_MAX_BYTES", "100")
service = TTSService(cache_dir=str(tmp_path))
# 1. Setup: Manually create two older files (40 bytes each)
file1 = tmp_path / "oldest.wav"
file2 = tmp_path / "middle.wav"
file1.write_bytes(b"a" * 40)
file2.write_bytes(b"b" * 40)
# Spoof timestamps so file1 is explicitly older than file2
now = time.time()
os.utime(file1, (now - 100, now - 100)) # 100 seconds ago
os.utime(file2, (now - 50, now - 50)) # 50 seconds ago
# 2. Action: Write a 3rd file using the service method (40 bytes)
# Total cache is now 120 bytes, which exceeds 100.
# It should delete oldest (file1) to drop to 80 bytes (which matches the 80% target).
service._put_cache("newest", b"c" * 40)
# 3. Assertions
# The newest file should exist (saved as .wav because it lacks MP3 magic bytes)
newest_file = tmp_path / "newest.wav"
assert not file1.exists(), "The oldest file should have been evicted."
assert file2.exists(), "The middle file should still exist."
assert newest_file.exists(), "The newest file should have been saved."
# Verify the final directory size is <= 80 bytes
total_size = sum(f.stat().st_size for f in tmp_path.glob("*.*"))
assert total_size <= 80
def test_cache_limit_disabled(tmp_path, monkeypatch):
"""Test that setting max bytes to 0 disables eviction."""
monkeypatch.setenv("ODYSSEUS_TTS_CACHE_MAX_BYTES", "0")
service = TTSService(cache_dir=str(tmp_path))
# Write 3 large files that would normally trigger eviction
service._put_cache("file1", b"x" * 1000)
service._put_cache("file2", b"x" * 1000)
service._put_cache("file3", b"x" * 1000)
# Ensure nothing was deleted
files = list(tmp_path.glob("*.*"))
assert len(files) == 3
assert sum(f.stat().st_size for f in files) == 3000
def test_cache_eviction_handles_unlink_error_gracefully(tmp_path, monkeypatch):
"""Test that if unlinking a file fails, _put_cache still succeeds without raising."""
service = TTSService(cache_dir=str(tmp_path))
service.max_cache_bytes = 50
# Create a file to evict
old_file = tmp_path / "old.wav"
old_file.write_bytes(b"x" * 40)
# Monkeypatch unlink on Path objects to simulate a PermissionError / file-lock failure
def mock_unlink(self_path):
raise OSError("Permission denied / file locked")
monkeypatch.setattr(Path, "unlink", mock_unlink)
# Writing a new file triggers eviction which encounters the mocked unlink error
try:
service._put_cache("new_key", b"y" * 40)
except Exception as e:
pytest.fail(f"_put_cache raised an exception during failed eviction: {e}")
# The new file should still be written successfully
assert (tmp_path / "new_key.wav").exists()