agent-brain-rag 1.2.0__py3-none-any.whl → 3.0.0__py3-none-any.whl

{agent_brain_rag-1.2.0.dist-info → agent_brain_rag-3.0.0.dist-info}/METADATA

@@ -1,7 +1,8 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.1
 Name: agent-brain-rag
-Version: 1.2.0
+Version: 3.0.0
 Summary: Agent Brain RAG - Intelligent document indexing and semantic search server that gives AI agents long-term memory
+Home-page: https://github.com/SpillwaveSolutions/agent-brain
 License: MIT
 Keywords: agent-brain,rag,semantic-search,ai-memory,llm-memory,documentation,indexing,llama-index,chromadb,ai-agent,claude-code,agent-memory
 Author: Spillwave Solutions
@@ -13,15 +14,21 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development :: Documentation
 Classifier: Topic :: Text Processing :: Indexing
+Provides-Extra: graphrag
+Provides-Extra: graphrag-all
+Provides-Extra: graphrag-kuzu
 Requires-Dist: anthropic (>=0.40.0,<0.41.0)
 Requires-Dist: chromadb (>=0.5.0,<0.6.0)
 Requires-Dist: click (>=8.1.0,<9.0.0)
+Requires-Dist: cohere (>=5.0.0,<6.0.0)
 Requires-Dist: fastapi (>=0.115.0,<0.116.0)
+Requires-Dist: google-generativeai (>=0.8.0,<0.9.0)
+Requires-Dist: langextract (>=1.0.0,<2.0.0) ; extra == "graphrag" or extra == "graphrag-all"
 Requires-Dist: llama-index-core (>=0.14.0,<0.15.0)
 Requires-Dist: llama-index-embeddings-openai (>=0.5.0,<0.6.0)
+Requires-Dist: llama-index-graph-stores-kuzu (>=0.9.0,<0.10.0) ; extra == "graphrag-kuzu" or extra == "graphrag-all"
 Requires-Dist: llama-index-llms-openai (>=0.6.12,<0.7.0)
 Requires-Dist: llama-index-readers-file (>=0.5.0,<0.6.0)
 Requires-Dist: llama-index-retrievers-bm25 (>=0.6.0,<0.7.0)
@@ -29,18 +36,24 @@ Requires-Dist: openai (>=1.57.0,<2.0.0)
 Requires-Dist: pydantic (>=2.10.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.6.0,<3.0.0)
 Requires-Dist: python-dotenv (>=1.0.0,<2.0.0)
+Requires-Dist: pyyaml (>=6.0.0,<7.0.0)
 Requires-Dist: rank-bm25 (>=0.2.2,<0.3.0)
 Requires-Dist: tiktoken (>=0.8.0,<0.9.0)
 Requires-Dist: tree-sitter-language-pack (>=0.7.3,<0.8.0)
 Requires-Dist: uvicorn[standard] (>=0.32.0,<0.33.0)
-Project-URL: Documentation, https://github.com/SpillwaveSolutions/doc-serve#readme
-Project-URL: Homepage, https://github.com/SpillwaveSolutions/doc-serve
-Project-URL: Repository, https://github.com/SpillwaveSolutions/doc-serve
+Project-URL: Documentation, https://github.com/SpillwaveSolutions/agent-brain/wiki
+Project-URL: Repository, https://github.com/SpillwaveSolutions/agent-brain
 Description-Content-Type: text/markdown
 
 # Agent Brain RAG Server
 
-Intelligent document indexing and semantic search REST API service that gives AI agents long-term memory.
+> **Agent Brain** (formerly doc-serve) is an intelligent document indexing and semantic search system designed to give AI agents long-term memory.
+
+AI agents need persistent memory to be truly useful. Agent Brain provides the retrieval infrastructure that enables context-aware, knowledge-grounded AI interactions.
+
+[![PyPI version](https://badge.fury.io/py/agent-brain-rag.svg)](https://pypi.org/project/agent-brain-rag/)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 ## Installation
 
@@ -65,28 +78,37 @@ The server will start at `http://127.0.0.1:8000`.
 
 > **Note**: The legacy command `doc-serve` is still available but deprecated. Please use `agent-brain-serve` for new installations.
 
+## Search Capabilities
+
+Agent Brain provides multiple search strategies to match your retrieval needs:
+
+| Search Type | Description | Best For |
+|-------------|-------------|----------|
+| **Semantic Search** | Natural language queries using OpenAI embeddings (`text-embedding-3-large`) | Conceptual questions, finding related content |
+| **Keyword Search (BM25)** | Traditional keyword matching with TF-IDF ranking | Exact matches, technical terms, code identifiers |
+| **Hybrid Search** | Combines vector + BM25 for best of both approaches | General-purpose queries, balanced recall/precision |
+| **GraphRAG** | Knowledge graph-based retrieval for relationship-aware queries | Understanding connections, multi-hop reasoning |
+
 ## Features
 
 - **Document Indexing**: Load and index documents from folders (PDF, Markdown, TXT, DOCX, HTML)
 - **AST-Aware Code Ingestion**: Smart parsing for Python, TypeScript, JavaScript, Java, Go, Rust, C, C++
-- **Hybrid Search**: Combines BM25 keyword matching with semantic similarity
-- **Semantic Search**: Query indexed documents using natural language
+- **Multi-Strategy Retrieval**: Semantic, keyword, hybrid, and graph-based search
 - **OpenAI Embeddings**: Uses `text-embedding-3-large` for high-quality embeddings
+- **Claude Summarization**: AI-powered code summaries for better context
 - **Chroma Vector Store**: Persistent, thread-safe vector database
 - **FastAPI**: Modern, high-performance REST API with OpenAPI documentation
 
-## Quick Start
-
-### Prerequisites
+## Prerequisites
 
 - Python 3.10+
-- Poetry
-- OpenAI API key
+- OpenAI API key (for embeddings)
+- Anthropic API key (for summarization)
 
-### Installation
+## Development Installation
 
 ```bash
-cd doc-serve-server
+cd agent-brain-server
 poetry install
 ```
 
@@ -101,6 +123,7 @@ cp ../.env.example .env
 
 Required environment variables:
 - `OPENAI_API_KEY`: Your OpenAI API key for embeddings
+- `ANTHROPIC_API_KEY`: Your Anthropic API key for summarization
 
 ### Running the Server
 
@@ -112,8 +135,6 @@ poetry run uvicorn agent_brain_server.api.main:app --reload
 poetry run agent-brain-serve
 ```
 
-The server will start at `http://127.0.0.1:8000`.
-
 ### API Documentation
 
 Once running, visit:
@@ -199,6 +220,22 @@ poetry run ruff check agent_brain_server/
 poetry run mypy agent_brain_server/
 ```
 
+## Documentation
+
+- [User Guide](https://github.com/SpillwaveSolutions/agent-brain/wiki/User-Guide) - Getting started and usage
+- [Developer Guide](https://github.com/SpillwaveSolutions/agent-brain/wiki/Developer-Guide) - Contributing and development
+- [API Reference](https://github.com/SpillwaveSolutions/agent-brain/wiki/API-Reference) - Full API documentation
+
+## Release Information
+
+- **Current Version**: See [pyproject.toml](./pyproject.toml)
+- **Release Notes**: [GitHub Releases](https://github.com/SpillwaveSolutions/agent-brain/releases)
+- **Changelog**: [Latest Release](https://github.com/SpillwaveSolutions/agent-brain/releases/latest)
+
+## Related Packages
+
+- [agent-brain-cli](https://pypi.org/project/agent-brain-cli/) - Command-line interface for Agent Brain
+
 ## License
 
 MIT

agent_brain_rag-3.0.0.dist-info/RECORD

@@ -0,0 +1,56 @@
+agent_brain_server/__init__.py,sha256=Wjd2w3VnDYURTECaKxFQ5x324-7tZ_vK2Qv3yKfxRGg,95
+agent_brain_server/api/__init__.py,sha256=nvTvO_ahHAAsRDlV3dL_JlNruSdan4kav_P5sT_1PFk,93
+agent_brain_server/api/main.py,sha256=TEb4lMSFm8eqNYOhXvoF6Xwi_r20RMuO8HL0zQxKfhY,16086
+agent_brain_server/api/routers/__init__.py,sha256=EQ5xXSTEIqRaZu-CKiOxeR05BMzUVgATMir_PV6zJ-Q,313
+agent_brain_server/api/routers/health.py,sha256=lTk0VXvTIvAV8YyOKAcPvZXhBeZ8jnENCDkZG3xk9Bg,6015
+agent_brain_server/api/routers/index.py,sha256=89_SrTByqEhQuQxsP7SXWiocXgQh2sgJ9n0Y_kNEWjA,9397
+agent_brain_server/api/routers/jobs.py,sha256=GYoZtTUc2BE2_u1HoUSGqUVDg7MAjhs6dG9-gjKoztw,3329
+agent_brain_server/api/routers/query.py,sha256=TAbpuCybjacUo_-7Zm3Jt8EW8EMDTYJDLv6aGtjaUzQ,2793
+agent_brain_server/config/__init__.py,sha256=zzDErZGUBwUm5Fk43OHJN7eWpeIw_1kWdnhsN6QQqSc,84
+agent_brain_server/config/provider_config.py,sha256=-uHj28i8OvAhQxlZ0JudYPAyibdJWmEJfvOYuRAdSHw,11535
+agent_brain_server/config/settings.py,sha256=XfkAi-5aV_vqbk4ltkG8mkJnPARPwl5g6JxvE0ngDjo,3726
+agent_brain_server/indexing/__init__.py,sha256=tQiFW4945h-ENd0pmMoGhCbm1Fz3AaREKBgajHeW-Us,1169
+agent_brain_server/indexing/bm25_index.py,sha256=_CZdTF1zoLyILTJ1nTLSmovIqN2NVQuYUiMEWh4o3-o,5740
+agent_brain_server/indexing/chunking.py,sha256=kW-ZOdwOS-PfXuPAYb8qL4-7yAY-rpY9a1el2YCN9CA,29848
+agent_brain_server/indexing/document_loader.py,sha256=l43Z5xHEykr6hbQqkMWXZGlT_CDz_tdhkI3PsxTMsgQ,17543
+agent_brain_server/indexing/embedding.py,sha256=i3bN3SivvVB8iNiYDjrDeB8nF3WkFoOy5wHrDaNosGs,7410
+agent_brain_server/indexing/graph_extractors.py,sha256=XEWBqlqDffxbs5ZLaijGICXeaptGtkUGNEhJblP3jBU,19339
+agent_brain_server/indexing/graph_index.py,sha256=ZKwICIqR2stcPEqNQ_SSuSk-O0Hj1lUmiUMxm5udhjg,18584
+agent_brain_server/job_queue/__init__.py,sha256=8aUjeXygbB_u76AqPTrlrwFDVVdqfiaWM9ROUAslKM4,240
+agent_brain_server/job_queue/job_service.py,sha256=BAzG_NMCnbHNHluKtKI1lMJxl1MF03G7Rv9mKEcgkWc,10660
+agent_brain_server/job_queue/job_store.py,sha256=xHWZh9rITUeCIAZwWmoEYDtSGCEfQuveduB9ET3L4zU,13699
+agent_brain_server/job_queue/job_worker.py,sha256=bh7pV9XKiCrK_bc1jeESh35DEcgfsiiAsrXo_ihwcLw,17566
+agent_brain_server/locking.py,sha256=ANgzY8aczB6W9OeWEv8zEZ8iOhXlBCOYlZH60xZsiHU,6249
+agent_brain_server/models/__init__.py,sha256=8tCr8Gmx6ieVx-CgX6W_a7s8doqAzWtDs8Jk5lrYmRA,1105
+agent_brain_server/models/graph.py,sha256=YzdjJj_X7hueJt4v8Gsoly4C-qquJLZi1d9epIh_Mos,7973
+agent_brain_server/models/health.py,sha256=ppvDF_yUaddzYPe0BPc9emVDrR17TVlQLW6ggsOOzPo,4592
+agent_brain_server/models/index.py,sha256=pjDv7phLS6dpiHLlEtcAuXQN_aHIfA_4lMkAZ-NkXZQ,5400
+agent_brain_server/models/job.py,sha256=OkNO8tHFFyV82kLJAocs4jKKI7Hde93y7KH8q_mfVyI,11194
+agent_brain_server/models/query.py,sha256=hCdcXIOPhW4wXrSQGunEXkIgiugD3lBXnS4F6fOCe_Q,6613
+agent_brain_server/project_root.py,sha256=js9ju-AhQ2SyC6wlfFhbMHhkNMJ3VNDdGZ3OJONUFjs,2196
+agent_brain_server/providers/__init__.py,sha256=04wJ_QhGKRM55R4yrbw3J3kCtKX44_FHzh6xZq1xFdc,1670
+agent_brain_server/providers/base.py,sha256=yLIpz9W0xlilBXxuFJRNP_gbGDsZ9HeRSqEnIsVGQjU,6933
+agent_brain_server/providers/embedding/__init__.py,sha256=WRUAkOLLgQB9AR9I-_m3QWa55hSeC5tDdp3gZQFfMRM,982
+agent_brain_server/providers/embedding/cohere.py,sha256=9ktr0_ZHmocJE8sFqo1Ah68B9J0wgs9-pLS0aKmLtQE,5295
+agent_brain_server/providers/embedding/ollama.py,sha256=oXKbbEivY74ASVjayLdr3xfgXTMvFS_jAjZs5HqCHzc,4725
+agent_brain_server/providers/embedding/openai.py,sha256=B5F6OJ_PSpF7OLUlhhmqGWOvho3Kox29Lq52bvxrWWY,3576
+agent_brain_server/providers/exceptions.py,sha256=kYggL4lG1NmJrEyU040Al5rm3_nWmKROJemkjcdohCM,2836
+agent_brain_server/providers/factory.py,sha256=3sREN_VnTDam9MDQJzf7eYlX5k-tbzgWXHb7DQ6MhRw,5488
+agent_brain_server/providers/summarization/__init__.py,sha256=WfMXywPvY1uTbmy_Z5prK9FNNqv17TeEvdg2MqFyKAc,1545
+agent_brain_server/providers/summarization/anthropic.py,sha256=fZOUfxJCPRUxMdeakBAdw1FY6NaYhvlWBlheTJlyAtc,2704
+agent_brain_server/providers/summarization/gemini.py,sha256=t2pOC4R2ae7WQAq7WCy8ZD6Ku_RPjyqsktBZRuRwGi8,2960
+agent_brain_server/providers/summarization/grok.py,sha256=nK3i46NbUcVxBqWNbJ-IifahB450Blnqm0rBhSQnQOw,2875
+agent_brain_server/providers/summarization/ollama.py,sha256=mw4zvx6o2nC4xoz1W6F47x3fk7gidl7aeh1uAnSTHO8,3673
+agent_brain_server/providers/summarization/openai.py,sha256=HjZJIjwc0usHejRAFW3JT6a7cmM_Ib2FdC05y_iEwA4,2632
+agent_brain_server/runtime.py,sha256=SVQa-8rgNFBeHyJe23bvzZ49Gf-4PqkuSJ-kJ1FPkSM,3081
+agent_brain_server/services/__init__.py,sha256=E4VPN9Rqa2mxGQQEQn-5IYj63LSPTrA8aIx8ENO5xcc,296
+agent_brain_server/services/indexing_service.py,sha256=d_oj3n7gNgua7nmiLNTM-hDp4wvcrkos9kCRuOTzlpc,20338
+agent_brain_server/services/query_service.py,sha256=oc_BNqTNjAtz17y_F7r-egP7Z0GozmP_mlfSs1jKbMM,22910
+agent_brain_server/storage/__init__.py,sha256=xYk4MfrEj-IpGZ0n4myfy5dwyjKEvprS7h68bet0ooU,557
+agent_brain_server/storage/graph_store.py,sha256=boW6_L0suvHuOdfZdPMdSNSb8U-am7KLelsa3K2bKl4,18168
+agent_brain_server/storage/vector_store.py,sha256=rcI--g6g7mqUbZzewOsaMdb7uqw173bAZau1p0oYZ68,12135
+agent_brain_server/storage_paths.py,sha256=FOpcFu21mlxPY-TCjWg6bMmREYEYDkVru7NumztGZWw,1850
+agent_brain_rag-3.0.0.dist-info/METADATA,sha256=C5ad5HVow94PzzSYAYcHx2gR4z9NelnZk3D7SIqwC7g,8092
+agent_brain_rag-3.0.0.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+agent_brain_rag-3.0.0.dist-info/entry_points.txt,sha256=Ig6JVYNKNNNnE96d8LefHRUdg11HUIGWfVQ1sAYI47c,69
+agent_brain_rag-3.0.0.dist-info/RECORD,,

{agent_brain_rag-1.2.0.dist-info → agent_brain_rag-3.0.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.1.1
+Generator: poetry-core 1.8.1
 Root-Is-Purelib: true
 Tag: py3-none-any

{agent_brain_rag-1.2.0.dist-info → agent_brain_rag-3.0.0.dist-info}/entry_points.txt

@@ -1,4 +1,3 @@
 [console_scripts]
 agent-brain-serve=agent_brain_server.api.main:cli
-doc-serve=agent_brain_server.api.main:cli_deprecated
 

agent_brain_server/__init__.py

@@ -1,3 +1,3 @@
 """Doc-Serve Server - RAG-based document indexing and query service."""
 
-__version__ = "1.2.0"
+__version__ = "3.0.0"

agent_brain_server/api/main.py

@@ -1,15 +1,16 @@
 """FastAPI application entry point.
 
 This module provides the Agent Brain RAG server, a FastAPI application
-for document indexing and semantic search. The primary entry point is
-`agent-brain-serve`, with `doc-serve` provided for backward compatibility.
+for document indexing and semantic search.
+
+Note: This server assumes a single uvicorn worker process. If running
+multiple workers, ensure only one worker handles indexing jobs by using
+the single-worker model or a separate job processor service.
 """
 
 import logging
 import os
 import socket
-import sys
-import warnings
 from collections.abc import AsyncIterator
 from contextlib import asynccontextmanager
 from pathlib import Path
@@ -22,7 +23,13 @@ from fastapi.middleware.cors import CORSMiddleware
 
 from agent_brain_server import __version__
 from agent_brain_server.config import settings
+from agent_brain_server.config.provider_config import (
+    clear_settings_cache,
+    load_provider_settings,
+    validate_provider_config,
+)
 from agent_brain_server.indexing.bm25_index import BM25IndexManager
+from agent_brain_server.job_queue import JobQueueService, JobQueueStore, JobWorker
 from agent_brain_server.locking import (
     acquire_lock,
     cleanup_stale,
@@ -35,7 +42,7 @@ from agent_brain_server.services import IndexingService, QueryService
 from agent_brain_server.storage import VectorStoreManager
 from agent_brain_server.storage_paths import resolve_state_dir, resolve_storage_paths
 
-from .routers import health_router, index_router, query_router
+from .routers import health_router, index_router, jobs_router, query_router
 
 # Configure logging
 logging.basicConfig(
@@ -48,6 +55,9 @@ logger = logging.getLogger(__name__)
 _runtime_state: Optional[RuntimeState] = None
 _state_dir: Optional[Path] = None
 
+# Module-level reference to job worker for cleanup
+_job_worker: Optional[JobWorker] = None
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI) -> AsyncIterator[None]:
@@ -60,18 +70,51 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
     - Resolves project root and state directory
     - Acquires lock (with stale detection)
     - Writes runtime.json with server info
+    - Initializes job queue system
     - Cleans up on shutdown
     """
-    global _runtime_state, _state_dir
+    global _runtime_state, _state_dir, _job_worker
 
     logger.info("Starting Agent Brain RAG server...")
 
+    # Load and validate provider configuration
+    # Clear cache first to ensure we pick up env vars set by CLI
+    clear_settings_cache()
+    try:
+        provider_settings = load_provider_settings()
+        validation_errors = validate_provider_config(provider_settings)
+
+        if validation_errors:
+            for error in validation_errors:
+                logger.warning(f"Provider config warning: {error}")
+            # Log but don't fail - providers may work if keys are set later
+            # or if using Ollama which doesn't need keys
+
+        # Log active provider configuration
+        logger.info(
+            f"Embedding provider: {provider_settings.embedding.provider} "
+            f"(model: {provider_settings.embedding.model})"
+        )
+        logger.info(
+            f"Summarization provider: {provider_settings.summarization.provider} "
+            f"(model: {provider_settings.summarization.model})"
+        )
+    except Exception as e:
+        logger.error(f"Failed to load provider configuration: {e}")
+        # Continue with defaults - EmbeddingGenerator will handle provider creation
+
     if settings.OPENAI_API_KEY:
         os.environ["OPENAI_API_KEY"] = settings.OPENAI_API_KEY
 
     # Determine mode and resolve paths
-    mode = settings.DOC_SERVE_MODE
-    state_dir = _state_dir  # May be set by CLI
+    mode = settings.AGENT_BRAIN_MODE
+    state_dir = _state_dir  # May be set by run() function
+
+    # If not set via run(), check environment variable (set by CLI subprocess)
+    if state_dir is None and settings.AGENT_BRAIN_STATE_DIR:
+        state_dir = Path(settings.AGENT_BRAIN_STATE_DIR).resolve()
+        logger.info(f"Using state directory from environment: {state_dir}")
+
     storage_paths: Optional[dict[str, Path]] = None
 
     if state_dir is not None:
@@ -86,13 +129,19 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
         # Acquire exclusive lock
         if not acquire_lock(state_dir):
             raise RuntimeError(
-                f"Another doc-serve instance is already running for {state_dir}"
+                f"Another Agent Brain instance is already running for {state_dir}"
             )
 
         # Resolve storage paths (creates directories)
         storage_paths = resolve_storage_paths(state_dir)
         logger.info(f"State directory: {state_dir}")
 
+    # Determine project root for path validation
+    project_root: Optional[Path] = None
+    if state_dir is not None:
+        # Project root is 3 levels up from .claude/agent-brain
+        project_root = state_dir.parent.parent.parent
+
     try:
         # Determine persistence directories
         chroma_dir = (
@@ -121,10 +170,28 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
         app.state.bm25_manager = bm25_manager
         logger.info("BM25 index manager initialized")
 
+        # Load project config for exclude patterns
+        exclude_patterns = None
+        if state_dir:
+            from agent_brain_server.config.settings import load_project_config
+
+            project_config = load_project_config(state_dir)
+            exclude_patterns = project_config.get("exclude_patterns")
+            if exclude_patterns:
+                logger.info(
+                    f"Using exclude patterns from config: {exclude_patterns[:3]}..."
+                )
+
+        # Create document loader with exclude patterns
+        from agent_brain_server.indexing import DocumentLoader
+
+        document_loader = DocumentLoader(exclude_patterns=exclude_patterns)
+
         # Create indexing service with injected deps
         indexing_service = IndexingService(
             vector_store=vector_store,
             bm25_manager=bm25_manager,
+            document_loader=document_loader,
         )
         app.state.indexing_service = indexing_service
 
@@ -135,6 +202,57 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
         )
         app.state.query_service = query_service
 
+        # Initialize job queue system (Feature 115)
+        if state_dir is not None:
+            # Initialize job queue store
+            job_store = JobQueueStore(state_dir)
+            await job_store.initialize()
+            logger.info("Job queue store initialized")
+
+            # Initialize job queue service
+            job_service = JobQueueService(
+                store=job_store,
+                project_root=project_root,
+            )
+            app.state.job_service = job_service
+            logger.info("Job queue service initialized")
+
+            # Initialize and start job worker
+            _job_worker = JobWorker(
+                job_store=job_store,
+                indexing_service=indexing_service,
+                max_runtime_seconds=settings.AGENT_BRAIN_JOB_TIMEOUT,
+                progress_checkpoint_interval=settings.AGENT_BRAIN_CHECKPOINT_INTERVAL,
+            )
+            await _job_worker.start()
+            logger.info("Job worker started")
+        else:
+            # No state directory - create minimal job service for backward compat
+            # Jobs will not be persisted in this mode
+            logger.warning(
+                "No state directory configured - job queue persistence disabled"
+            )
+            # Create in-memory store with temp directory
+            import tempfile
+
+            temp_dir = Path(tempfile.mkdtemp(prefix="agent-brain-"))
+            job_store = JobQueueStore(temp_dir)
+            await job_store.initialize()
+
+            job_service = JobQueueService(
+                store=job_store,
+                project_root=project_root,
+            )
+            app.state.job_service = job_service
+
+            _job_worker = JobWorker(
+                job_store=job_store,
+                indexing_service=indexing_service,
+                max_runtime_seconds=settings.AGENT_BRAIN_JOB_TIMEOUT,
+                progress_checkpoint_interval=settings.AGENT_BRAIN_CHECKPOINT_INTERVAL,
+            )
+            await _job_worker.start()
+
         # Set multi-instance metadata on app.state for health endpoint
         app.state.mode = mode
         app.state.instance_id = _runtime_state.instance_id if _runtime_state else None
@@ -152,6 +270,12 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
 
     logger.info("Shutting down Agent Brain RAG server...")
 
+    # Stop job worker gracefully
+    if _job_worker is not None:
+        await _job_worker.stop()
+        logger.info("Job worker stopped")
+        _job_worker = None
+
     # Cleanup for per-project mode
     if state_dir is not None:
         delete_runtime(state_dir)
@@ -166,7 +290,7 @@ app = FastAPI(
         "RAG-based document indexing and semantic search API. "
         "Index documents from folders and query them using natural language."
     ),
-    version="1.2.0",
+    version=__version__,
     lifespan=lifespan,
     docs_url="/docs",
     redoc_url="/redoc",
@@ -185,6 +309,7 @@ app.add_middleware(
 # Include routers
 app.include_router(health_router, prefix="/health", tags=["Health"])
 app.include_router(index_router, prefix="/index", tags=["Indexing"])
+app.include_router(jobs_router, prefix="/index/jobs", tags=["Jobs"])
 app.include_router(query_router, prefix="/query", tags=["Querying"])
 
 
@@ -193,7 +318,7 @@ async def root() -> dict[str, str]:
     """Root endpoint redirects to docs."""
     return {
         "name": "Agent Brain RAG API",
-        "version": "1.2.0",
+        "version": __version__,
         "docs": "/docs",
         "health": "/health",
     }
@@ -243,7 +368,7 @@ def run(
         # Create runtime state
         _runtime_state = RuntimeState(
             mode="project",
-            project_root=str(_state_dir.parent.parent.parent),  # .claude/doc-serve
+            project_root=str(_state_dir.parent.parent.parent),  # .claude/agent-brain
             bind_host=resolved_host,
             port=resolved_port,
             pid=os.getpid(),
@@ -295,7 +420,7 @@ def run(
     "--project-dir",
     "-d",
     default=None,
-    help="Project directory (auto-resolves state-dir to .claude/doc-serve)",
+    help="Project directory (auto-resolves state-dir to .claude/agent-brain)",
 )
 def cli(
     host: Optional[str],
@@ -316,15 +441,15 @@ def cli(
       agent-brain-serve --host 0.0.0.0            # Bind to all interfaces
       agent-brain-serve --reload                  # Enable auto-reload
       agent-brain-serve --project-dir /my/project # Per-project mode
-      agent-brain-serve --state-dir /path/.claude/doc-serve  # Explicit state dir
+      agent-brain-serve --state-dir /path/.claude/agent-brain  # Explicit state dir
 
     \b
     Environment Variables:
-      API_HOST              Server host (default: 127.0.0.1)
-      API_PORT              Server port (default: 8000)
-      DEBUG                 Enable debug mode (default: false)
-      DOC_SERVE_STATE_DIR   Override state directory
-      DOC_SERVE_MODE        Instance mode: 'project' or 'shared'
+      API_HOST                Server host (default: 127.0.0.1)
+      API_PORT                Server port (default: 8000)
+      DEBUG                   Enable debug mode (default: false)
+      AGENT_BRAIN_STATE_DIR   Override state directory
+      AGENT_BRAIN_MODE        Instance mode: 'project' or 'shared'
     """
     # Resolve state directory from options
     resolved_state_dir = state_dir
@@ -333,36 +458,12 @@ def cli(
         # Auto-resolve state-dir from project directory
         project_root = resolve_project_root(Path(project_dir))
         resolved_state_dir = str(resolve_state_dir(project_root))
-    elif settings.DOC_SERVE_STATE_DIR and not state_dir:
+    elif settings.AGENT_BRAIN_STATE_DIR and not state_dir:
         # Use environment variable if set
-        resolved_state_dir = settings.DOC_SERVE_STATE_DIR
+        resolved_state_dir = settings.AGENT_BRAIN_STATE_DIR
 
     run(host=host, port=port, reload=reload, state_dir=resolved_state_dir)
 
 
-def cli_deprecated() -> None:
-    """Deprecated entry point for doc-serve command.
-
-    Shows a deprecation warning and then runs the main CLI.
-    """
-    warnings.warn(
-        "\n"
-        "WARNING: 'doc-serve' is deprecated and will be removed in v2.0.\n"
-        "Please use 'agent-brain-serve' instead.\n"
-        "\n"
-        "Migration guide: docs/MIGRATION.md\n"
-        "Online: https://github.com/SpillwaveSolutions/agent-brain/blob/main/docs/MIGRATION.md\n",
-        DeprecationWarning,
-        stacklevel=1,
-    )
-    # Print to stderr for visibility since warnings may be filtered
-    print(
-        "\033[93mWARNING: 'doc-serve' is deprecated. "
-        "Use 'agent-brain-serve' instead. See docs/MIGRATION.md\033[0m",
-        file=sys.stderr,
-    )
-    cli()
-
-
 if __name__ == "__main__":
     cli()

agent_brain_server/api/routers/__init__.py

@@ -2,10 +2,12 @@
 
 from .health import router as health_router
 from .index import router as index_router
+from .jobs import router as jobs_router
 from .query import router as query_router
 
 __all__ = [
     "health_router",
     "index_router",
+    "jobs_router",
     "query_router",
 ]