Files
deer-flow/backend/packages/harness/deerflow/agents/checkpointer/provider.py

204 lines
7.4 KiB
Python
Raw Normal View History

"""Sync checkpointer factory.
Provides a **sync singleton** and a **sync context manager** for LangGraph
graph compilation and CLI tools.
Supported backends: memory, sqlite, postgres.
Usage::
refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) * refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 22:55:52 +08:00
from deerflow.agents.checkpointer.provider import get_checkpointer, checkpointer_context
# Singleton — reused across calls, closed on process exit
cp = get_checkpointer()
# One-shot — fresh connection, closed on block exit
with checkpointer_context() as cp:
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
"""
from __future__ import annotations
import contextlib
import logging
from collections.abc import Iterator
from langgraph.types import Checkpointer
refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) * refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 22:55:52 +08:00
from deerflow.config.app_config import get_app_config
from deerflow.config.checkpointer_config import CheckpointerConfig
from deerflow.config.paths import resolve_path
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Error message constants — imported by aio.provider too
# ---------------------------------------------------------------------------
SQLITE_INSTALL = "langgraph-checkpoint-sqlite is required for the SQLite checkpointer. Install it with: uv add langgraph-checkpoint-sqlite"
POSTGRES_INSTALL = "langgraph-checkpoint-postgres is required for the PostgreSQL checkpointer. Install it with: uv add langgraph-checkpoint-postgres psycopg[binary] psycopg-pool"
POSTGRES_CONN_REQUIRED = "checkpointer.connection_string is required for the postgres backend"
# ---------------------------------------------------------------------------
# Sync factory
# ---------------------------------------------------------------------------
def _resolve_sqlite_conn_str(raw: str) -> str:
"""Return a SQLite connection string ready for use with ``SqliteSaver``.
SQLite special strings (``":memory:"`` and ``file:`` URIs) are returned
unchanged. Plain filesystem paths relative or absolute are resolved
to an absolute string via :func:`resolve_path`.
"""
if raw == ":memory:" or raw.startswith("file:"):
return raw
return str(resolve_path(raw))
@contextlib.contextmanager
def _sync_checkpointer_cm(config: CheckpointerConfig) -> Iterator[Checkpointer]:
"""Context manager that creates and tears down a sync checkpointer.
Returns a configured ``Checkpointer`` instance. Resource cleanup for any
underlying connections or pools is handled by higher-level helpers in
this module (such as the singleton factory or context manager); this
function does not return a separate cleanup callback.
"""
if config.type == "memory":
from langgraph.checkpoint.memory import InMemorySaver
logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
yield InMemorySaver()
return
if config.type == "sqlite":
try:
from langgraph.checkpoint.sqlite import SqliteSaver
except ImportError as exc:
raise ImportError(SQLITE_INSTALL) from exc
conn_str = _resolve_sqlite_conn_str(config.connection_string or "store.db")
with SqliteSaver.from_conn_string(conn_str) as saver:
saver.setup()
logger.info("Checkpointer: using SqliteSaver (%s)", conn_str)
yield saver
return
if config.type == "postgres":
try:
from langgraph.checkpoint.postgres import PostgresSaver
except ImportError as exc:
raise ImportError(POSTGRES_INSTALL) from exc
if not config.connection_string:
raise ValueError(POSTGRES_CONN_REQUIRED)
with PostgresSaver.from_conn_string(config.connection_string) as saver:
saver.setup()
logger.info("Checkpointer: using PostgresSaver")
yield saver
return
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
# ---------------------------------------------------------------------------
# Sync singleton
# ---------------------------------------------------------------------------
_checkpointer: Checkpointer | None = None
_checkpointer_ctx = None # open context manager keeping the connection alive
def get_checkpointer() -> Checkpointer:
"""Return the global sync checkpointer singleton, creating it on first call.
Returns an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
Raises:
ImportError: If the required package for the configured backend is not installed.
ValueError: If ``connection_string`` is missing for a backend that requires it.
"""
global _checkpointer, _checkpointer_ctx
if _checkpointer is not None:
return _checkpointer
# Ensure app config is loaded before checking checkpointer config
# This prevents returning InMemorySaver when config.yaml actually has a checkpointer section
# but hasn't been loaded yet
refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) * refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 22:55:52 +08:00
from deerflow.config.app_config import _app_config
from deerflow.config.checkpointer_config import get_checkpointer_config
fix: normalize structured LLM content in serialization and memory updater (#1215) * fix: normalize ToolMessage structured content in serialization When models return ToolMessage content as a list of content blocks (e.g. [{"type": "text", "text": "..."}]), the UI previously displayed the raw Python repr string instead of the extracted text. Replace str(msg.content) with the existing _extract_text() helper in both _serialize_message() and stream() to properly normalize list-of-blocks content to plain text. Fixes #1149 Also fixes the same root cause as #1188 (characters displayed one per line when tool response content is returned as structured blocks). Added 11 regression tests covering string, list-of-blocks, mixed, empty, and fallback content types. * fix(memory): extract text from structured LLM responses in memory updater When LLMs return response content as list of content blocks (e.g. [{"type": "text", "text": "..."}]) instead of plain strings, str() produces Python repr which breaks JSON parsing in the memory updater. This caused memory updates to silently fail. Changes: - Add _extract_text() helper in updater.py for safe content normalization - Use _extract_text() instead of str(response.content) in update_memory() - Fix format_conversation_for_update() to handle plain strings in list content - Fix subagent executor fallback path to extract text from list content - Replace print() with structured logging (logger.info/warning/error) - Add 13 regression tests covering _extract_text, format_conversation, and update_memory with structured LLM responses * fix: address Copilot review - defensive text extraction + logger.exception - client.py _extract_text: use block.get('text') + isinstance check (prevent KeyError/TypeError) - prompt.py format_conversation_for_update: same defensive check for dict text blocks - executor.py: type-safe text extraction in both code paths, fallback to placeholder instead of str(raw_content) - updater.py: use logger.exception() instead of logger.error() for traceback preservation * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: preserve chunked structured content without spurious newlines * fix: restore backend unit test compatibility --------- Co-authored-by: Exploreunive <Exploreunive@users.noreply.github.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-22 17:29:29 +08:00
config = get_checkpointer_config()
if config is None and _app_config is None:
# Only load app config lazily when neither the app config nor an explicit
# checkpointer config has been initialized yet. This keeps tests that
# intentionally set the global checkpointer config isolated from any
# ambient config.yaml on disk.
try:
get_app_config()
except FileNotFoundError:
fix: normalize structured LLM content in serialization and memory updater (#1215) * fix: normalize ToolMessage structured content in serialization When models return ToolMessage content as a list of content blocks (e.g. [{"type": "text", "text": "..."}]), the UI previously displayed the raw Python repr string instead of the extracted text. Replace str(msg.content) with the existing _extract_text() helper in both _serialize_message() and stream() to properly normalize list-of-blocks content to plain text. Fixes #1149 Also fixes the same root cause as #1188 (characters displayed one per line when tool response content is returned as structured blocks). Added 11 regression tests covering string, list-of-blocks, mixed, empty, and fallback content types. * fix(memory): extract text from structured LLM responses in memory updater When LLMs return response content as list of content blocks (e.g. [{"type": "text", "text": "..."}]) instead of plain strings, str() produces Python repr which breaks JSON parsing in the memory updater. This caused memory updates to silently fail. Changes: - Add _extract_text() helper in updater.py for safe content normalization - Use _extract_text() instead of str(response.content) in update_memory() - Fix format_conversation_for_update() to handle plain strings in list content - Fix subagent executor fallback path to extract text from list content - Replace print() with structured logging (logger.info/warning/error) - Add 13 regression tests covering _extract_text, format_conversation, and update_memory with structured LLM responses * fix: address Copilot review - defensive text extraction + logger.exception - client.py _extract_text: use block.get('text') + isinstance check (prevent KeyError/TypeError) - prompt.py format_conversation_for_update: same defensive check for dict text blocks - executor.py: type-safe text extraction in both code paths, fallback to placeholder instead of str(raw_content) - updater.py: use logger.exception() instead of logger.error() for traceback preservation * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: preserve chunked structured content without spurious newlines * fix: restore backend unit test compatibility --------- Co-authored-by: Exploreunive <Exploreunive@users.noreply.github.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-22 17:29:29 +08:00
# In test environments without config.yaml, this is expected.
pass
fix: normalize structured LLM content in serialization and memory updater (#1215) * fix: normalize ToolMessage structured content in serialization When models return ToolMessage content as a list of content blocks (e.g. [{"type": "text", "text": "..."}]), the UI previously displayed the raw Python repr string instead of the extracted text. Replace str(msg.content) with the existing _extract_text() helper in both _serialize_message() and stream() to properly normalize list-of-blocks content to plain text. Fixes #1149 Also fixes the same root cause as #1188 (characters displayed one per line when tool response content is returned as structured blocks). Added 11 regression tests covering string, list-of-blocks, mixed, empty, and fallback content types. * fix(memory): extract text from structured LLM responses in memory updater When LLMs return response content as list of content blocks (e.g. [{"type": "text", "text": "..."}]) instead of plain strings, str() produces Python repr which breaks JSON parsing in the memory updater. This caused memory updates to silently fail. Changes: - Add _extract_text() helper in updater.py for safe content normalization - Use _extract_text() instead of str(response.content) in update_memory() - Fix format_conversation_for_update() to handle plain strings in list content - Fix subagent executor fallback path to extract text from list content - Replace print() with structured logging (logger.info/warning/error) - Add 13 regression tests covering _extract_text, format_conversation, and update_memory with structured LLM responses * fix: address Copilot review - defensive text extraction + logger.exception - client.py _extract_text: use block.get('text') + isinstance check (prevent KeyError/TypeError) - prompt.py format_conversation_for_update: same defensive check for dict text blocks - executor.py: type-safe text extraction in both code paths, fallback to placeholder instead of str(raw_content) - updater.py: use logger.exception() instead of logger.error() for traceback preservation * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: preserve chunked structured content without spurious newlines * fix: restore backend unit test compatibility --------- Co-authored-by: Exploreunive <Exploreunive@users.noreply.github.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-22 17:29:29 +08:00
config = get_checkpointer_config()
if config is None:
from langgraph.checkpoint.memory import InMemorySaver
logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
_checkpointer = InMemorySaver()
return _checkpointer
_checkpointer_ctx = _sync_checkpointer_cm(config)
_checkpointer = _checkpointer_ctx.__enter__()
return _checkpointer
def reset_checkpointer() -> None:
"""Reset the sync singleton, forcing recreation on the next call.
Closes any open backend connections and clears the cached instance.
Useful in tests or after a configuration change.
"""
global _checkpointer, _checkpointer_ctx
if _checkpointer_ctx is not None:
try:
_checkpointer_ctx.__exit__(None, None, None)
except Exception:
logger.warning("Error during checkpointer cleanup", exc_info=True)
_checkpointer_ctx = None
_checkpointer = None
# ---------------------------------------------------------------------------
# Sync context manager
# ---------------------------------------------------------------------------
@contextlib.contextmanager
def checkpointer_context() -> Iterator[Checkpointer]:
"""Sync context manager that yields a checkpointer and cleans up on exit.
Unlike :func:`get_checkpointer`, this does **not** cache the instance
each ``with`` block creates and destroys its own connection. Use it in
CLI scripts or tests where you want deterministic cleanup::
with checkpointer_context() as cp:
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
"""
config = get_app_config()
if config.checkpointer is None:
from langgraph.checkpoint.memory import InMemorySaver
yield InMemorySaver()
return
with _sync_checkpointer_cm(config.checkpointer) as saver:
yield saver