Restructure the persistence layer from horizontal "models/ + repositories/"
split into vertical entity-aligned directories. Each entity (thread_meta,
run, feedback) now owns its ORM model, abstract interface (where applicable),
and concrete implementations under a single directory with an aggregating
__init__.py for one-line imports.
Layout:
persistence/thread_meta/{base,model,sql,memory}.py
persistence/run/{model,sql}.py
persistence/feedback/{model,sql}.py
models/__init__.py is kept as a facade so Alembic autogenerate continues to
discover all ORM tables via Base.metadata. RunEventRow remains under
models/run_event.py because its storage implementation lives in
runtime/events/store/db.py and has no matching repository directory.
The repositories/ directory is removed entirely. All call sites in
gateway/deps.py and tests are updated to import from the new entity
packages, e.g.:
from deerflow.persistence.thread_meta import ThreadMetaRepository
from deerflow.persistence.run import RunRepository
from deerflow.persistence.feedback import FeedbackRepository
Full test suite passes (1690 passed, 14 skipped).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
resolve_path() resolves relative to Paths.base_dir (.deer-flow),
which double-nested the path to .deer-flow/.deer-flow/data/app.db.
Use Path.resolve() (CWD-relative) instead.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- feedback.py: validate thread_id/run_id before deleting feedback
- jsonl.py: add path traversal protection with ID validation
- run_repo.py: parse `before` to datetime for PostgreSQL compat
- thread_meta_repo.py: fix pagination when metadata filter is active
- database_config.py: use resolve_path for sqlite_dir consistency
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add ThreadMetaStore abstract base class with create/get/search/update/delete
interface. ThreadMetaRepository (SQL) now inherits from it. New
MemoryThreadMetaStore wraps LangGraph BaseStore for memory-mode deployments.
deps.py now always provides a non-None thread_meta_repo, eliminating all
`if thread_meta_repo is not None` guards in services.py, worker.py, and
routers/threads.py. search_threads no longer needs a Store fallback branch.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(sandbox): add L2 input sanitisation to SandboxAuditMiddleware
Add _validate_input() to reject malformed bash commands before regex
classification: empty commands, oversized commands (>10 000 chars), and
null bytes that could cause detection/execution layer inconsistency.
* fix(sandbox): address Copilot review — type guard, log truncation, reject reason
- Coerce None/non-string command to str before validation
- Truncate oversized commands in audit logs to prevent log amplification
- Propagate reject_reason through _pre_process() to block message
- Remove L2 label from comments and test class names
* fix(sandbox): isinstance type guard + async input sanitisation tests
Address review comments:
- Replace str() coercion with isinstance(raw_command, str) guard so
non-string truthy values (0, [], False) fall back to empty string
instead of passing validation as "0"/"[]"/"False".
- Add TestInputSanitisationBlocksInAwrapToolCall with 4 async tests
covering empty, null-byte, oversized, and None command via
awrap_tool_call path.
support for vLLM 0.19.0 OpenAI-compatible chat endpoints and fixes the Qwen reasoning toggle so flash mode can actually disable thinking.
Co-authored-by: NmanQAQ <normangyao@qq.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
ls_tool was the only sandbox tool without output size limits, allowing
multi-MB results from large directories to blow up the model context
window. Add head-truncation (configurable via ls_output_max_chars,
default 20000) consistent with existing bash and read_file truncation.
Closes#1887
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add docstring clarifying that put() opens a per-call transaction with
FOR UPDATE and should only be used for infrequent writes (currently
just the initial human_message event). High-throughput callers should
use put_batch() instead.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace Python-side counting in FeedbackRepository.aggregate_by_run with
a single SELECT COUNT/SUM query. Add RunStore.aggregate_tokens_by_thread
abstract method with SQL GROUP BY implementation in RunRepository and
Python fallback in MemoryRunStore. Simplify the thread_token_usage
endpoint to delegate to the new method, eliminating the limit=10000
truncation risk.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extract checkpointer, store, event_store, run_events_config, thread_meta_repo,
and follow_up_to_run_id into a frozen RunContext dataclass. Add get_run_context()
in deps.py to build the base context from app.state singletons. start_run() uses
dataclasses.replace() to enrich per-run fields before passing ctx to run_agent.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bug fixes:
- Sanitize log params to prevent log injection (CodeQL)
- Reset threads_meta.status to idle/error when run completes
- Attach messages only to latest checkpoint in /history response
- Write threads_meta on POST /threads so new threads appear in search
Lint fixes:
- Remove unused imports (journal.py, migrations/env.py, test_converters.py)
- Convert lambda to named function (engine.py, Ruff E731)
- Remove unused logger definitions in repos (Ruff F841)
- Add logging to JSONL decode errors and empty except blocks
- Separate assert side-effects in tests (CodeQL)
- Remove unused local variables in tests (Ruff F841)
- Fix max_trace_content truncation to use byte length, not char length
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix naive datetime.now() → datetime.now(UTC) in all ORM models
- Fix seq race condition in DbRunEventStore.put() with FOR UPDATE
and UNIQUE(thread_id, seq) constraint
- Encapsulate _store access in RunManager.update_run_completion()
- Deduplicate _store.put() logic in RunManager via _persist_to_store()
- Add update_run_completion to RunStore ABC + MemoryRunStore
- Wire follow_up_to_run_id through the full create path
- Add error recovery to RunJournal._flush_sync() lost-event scenario
- Add migration note for search_threads breaking change
- Fix test_checkpointer_none_fix mock to set database=None
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(memory): case-insensitive fact deduplication and positive reinforcement detection
Two fixes to the memory system:
1. _fact_content_key() now lowercases content before comparison, preventing
semantically duplicate facts like "User prefers Python" and "user prefers
python" from being stored separately.
2. Adds detect_reinforcement() to MemoryMiddleware (closes#1719), mirroring
detect_correction(). When users signal approval ("yes exactly", "perfect",
"完全正确", etc.), the memory updater now receives reinforcement_detected=True
and injects a hint prompting the LLM to record confirmed preferences and
behaviors with high confidence.
Changes across the full signal path:
- memory_middleware.py: _REINFORCEMENT_PATTERNS + detect_reinforcement()
- queue.py: reinforcement_detected field in ConversationContext and add()
- updater.py: reinforcement_detected param in update_memory() and
update_memory_from_conversation(); builds reinforcement_hint alongside
the existing correction_hint
Tests: 11 new tests covering deduplication, hint injection, and signal
detection (Chinese + English patterns, window boundary, conflict with correction).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(memory): address Copilot review comments on reinforcement detection
- Tighten _REINFORCEMENT_PATTERNS: remove 很好, require punctuation/end-of-string boundaries on remaining patterns, split this-is-good into stricter variants
- Suppress reinforcement_detected when correction_detected is true to avoid mixed-signal noise
- Use casefold() instead of lower() for Unicode-aware fact deduplication
- Add missing test coverage for reinforcement_detected OR merge and forwarding in queue
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
sandbox_from_runtime() and ensure_sandbox_initialized() write
sandbox_id into runtime.context after acquiring a sandbox. When
lazy_init=True and no context is supplied to the graph run,
runtime.context is None (the LangGraph default), causing a TypeError
on the assignment.
Add `if runtime.context is not None` guards at all three write sites.
Reads already had equivalent guards (e.g. `runtime.context.get(...) if
runtime.context else None`); this brings writes into line.
Without the config, the middleware:title tag was not injected,
causing the LLM response to be recorded as a lead_agent ai_message
in run_events.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- POST /api/threads/search now queries threads_meta table directly,
removing the two-phase Store + Checkpointer scan approach
- Add ThreadMetaRepository.search() with metadata/status filters
- Add ThreadMetaRepository.update_display_name() for title sync
- Worker syncs checkpoint title to threads_meta.display_name on run completion
- Map display_name to values.title in search response for API compatibility
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Message events (ai_message, ai_tool_call, tool_result, human_message) now use
BaseMessage.model_dump() format, matching LangGraph checkpoint values.messages
- on_tool_end extracts tool_call_id/name/status from ToolMessage objects
- on_tool_error now emits tool_result message events with error status
- record_middleware uses middleware:{tag} event_type and middleware category
- Summarization custom events use middleware:summarize category
- TitleMiddleware injects middleware:title tag via get_config() inheritance
- SummarizationMiddleware model bound with middleware:summarize tag
- Worker writes human_message using HumanMessage.model_dump()
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(uploads): guide agent to use grep/glob/read_file for uploaded documents
Add workflow guidance to the <uploaded_files> context block so the agent
knows to use grep and glob (added in #1784) alongside read_file when
working with uploaded documents, rather than falling back to web search.
This is the final piece of the three-PR PDF agentic search pipeline:
- PR1 (#1727): pymupdf4llm converter produces structured Markdown with headings
- PR2 (#1738): document outline injected into agent context with line numbers
- PR3 (this): agent guided to use outline + grep + read_file workflow
* feat(uploads): add file-first priority and fallback guidance to uploaded_files context
* fix(uploads): handle split-bold headings and ** ** artefacts in extract_outline
- Add _clean_bold_title() to merge adjacent bold spans (** **) produced
by pymupdf4llm when bold text crosses span boundaries
- Add _SPLIT_BOLD_HEADING_RE (Style 3) to recognise **<num>** **<title>**
headings common in academic papers; excludes pure-number table headers
and rows with more than 4 bold blocks
- When outline is empty, read first 5 non-empty lines of the .md as a
content preview and surface a grep hint in the agent context
- Update _format_file_entry to render the preview + grep hint instead of
silently omitting the outline section
- Add 3 new extract_outline tests and 2 new middleware tests (65 total)
* fix(uploads): address Copilot review comments on extract_outline regex
- Replace ASCII [A-Za-z] guard with negative lookahead to support non-ASCII
titles (e.g. **1** **概述**); pure-numeric/punctuation blocks still excluded
- Replace .+ with [^*]+ and cap repetition at {0,2} (four blocks total) to
keep _SPLIT_BOLD_HEADING_RE linear and avoid ReDoS on malformed input
- Remove now-redundant len(blocks) <= 4 code-level check (enforced by regex)
- Log debug message with exc_info when preview extraction fails
* feat(uploads): guide agent to use grep/glob/read_file for uploaded documents
Add workflow guidance to the <uploaded_files> context block so the agent
knows to use grep and glob (added in #1784) alongside read_file when
working with uploaded documents, rather than falling back to web search.
This is the final piece of the three-PR PDF agentic search pipeline:
- PR1 (#1727): pymupdf4llm converter produces structured Markdown with headings
- PR2 (#1738): document outline injected into agent context with line numbers
- PR3 (this): agent guided to use outline + grep + read_file workflow
* feat(uploads): add file-first priority and fallback guidance to uploaded_files context
* fix: inject longTermBackground into memory prompt
The format_memory_for_injection function only processed recentMonths and
earlierContext from the history section, silently dropping longTermBackground.
The LLM writes longTermBackground correctly and it persists to memory.json,
but it was never injected into the system prompt — making the user's
long-term background invisible to the AI.
Add the missing field handling and a regression test.
* fix(middleware): handle list-type AIMessage.content in LoopDetectionMiddleware
LangChain AIMessage.content can be str | list. When using providers that
return structured content blocks (e.g. Anthropic thinking mode, certain
OpenAI-compatible gateways), content is a list of dicts like
[{"type": "text", "text": "..."}].
The hard_limit branch in _apply() concatenated content with a string via
(last_msg.content or "") + f"\n\n{_HARD_STOP_MSG}", which raises
TypeError when content is a non-empty list (list + str is invalid).
Add _append_text() static method that:
- Returns the text directly when content is None
- Appends a {"type": "text"} block when content is a list
- Falls back to string concatenation when content is a str
This is consistent with how other modules in the project already handle
list content (client.py._extract_text, memory_middleware, executor.py).
* test(middleware): add unit tests for _append_text and list content hard stop
Add regression tests to verify LoopDetectionMiddleware handles list-type
AIMessage.content correctly during hard stop:
- TestAppendText: unit tests for the new _append_text() static method
covering None, str, list (including empty list) content types
- TestHardStopWithListContent: integration tests verifying hard stop
works correctly with list content (Anthropic thinking mode), None
content, and str content
Requested by reviewer in PR #1823.
* fix(middleware): improve _append_text robustness and test isolation
- Add explicit isinstance(content, str) check with fallback for
unexpected types (coerce to str) to prevent TypeError on edge cases
- Deep-copy list content in _make_state() test helper to prevent
shared mutable references across test iterations
- Add test_unexpected_type_coerced_to_str: verify fallback for
non-str/list/None content types
- Add test_list_content_not_mutated_in_place: verify _append_text
does not modify the original list
* style: fix ruff format whitespace in test file
---------
Co-authored-by: ppyt <14163465+ppyt@users.noreply.github.com>
Add on_chat_model_start to capture structured prompt messages as llm_request events.
Replace llm_end trace events with llm_response using OpenAI Chat Completions format.
Track llm_call_index to pair request/response events.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Cache tool_call_id from on_tool_start keyed by run_id as fallback for on_tool_end,
then emit a tool_result message event (role=tool, tool_call_id, content) after each
successful tool completion.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- ai_message content now uses {"role": "assistant", "content": "..."} format
- New ai_tool_call message event emitted when lead_agent LLM responds with tool_calls
- ai_tool_call uses langchain_to_openai_message converter for consistent format
- Both events include finish_reason in metadata ("stop" or "tool_calls")
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Pure functions langchain_to_openai_message, langchain_to_openai_completion,
langchain_messages_to_openai, and _infer_finish_reason for converting
LangChain BaseMessage objects to OpenAI Chat Completions format, used by
RunJournal for event storage. 15 unit tests added.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Allow event content to be a dict (for structured OpenAI-format messages)
in addition to plain strings. Dict values are JSON-serialized for the DB
backend and deserialized on read; memory and JSONL backends handle dicts
natively. Trace truncation now serializes dicts to JSON before measuring.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(uploads): add pymupdf4llm PDF converter with auto-fallback and async offload
- Introduce pymupdf4llm as an optional PDF converter with better heading
detection and table preservation than MarkItDown
- Auto mode: prefer pymupdf4llm when installed; fall back to MarkItDown
when output is suspiciously sparse (image-based / scanned PDFs)
- Sparsity check uses chars-per-page (< 50 chars/page) rather than an
absolute threshold, correctly handling both short and long documents
- Large files (> 1 MB) are offloaded to asyncio.to_thread() to avoid
blocking the event loop (related: #1569)
- Add UploadsConfig with pdf_converter field (auto/pymupdf4llm/markitdown)
- Add pymupdf4llm as optional dependency: pip install deerflow-harness[pymupdf]
- Add 14 unit tests covering sparsity heuristic, routing logic, and async path
* fix(uploads): address Copilot review comments on PDF converter
- Fix docstring: MIN_CHARS_PYMUPDF -> _MIN_CHARS_PER_PAGE (typo)
- Fix file handle leak: wrap pymupdf.open in try/finally to ensure doc.close()
- Fix silent fallback gap: _convert_pdf_with_pymupdf4llm now catches all
conversion exceptions (not just ImportError), so encrypted/corrupt PDFs
fall back to MarkItDown instead of propagating
- Tighten type: pdf_converter field changed from str to Literal[auto|pymupdf4llm|markitdown]
- Normalize config value: _get_pdf_converter() strips and lowercases the raw
config string, warns and falls back to 'auto' on unknown values
