mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-29 00:34:47 +08:00
feat(harness): integration ACP agent tool (#1344)
* 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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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> * feat(harness): add tool-first ACP agent invocation (#37) * feat(harness): add tool-first ACP agent invocation * build(harness): make ACP dependency required * fix(harness): address ACP review feedback * feat(harness): decouple ACP agent workspace from thread data ACP agents (codex, claude-code) previously used per-thread workspace directories, causing path resolution complexity and coupling task execution to DeerFlow's internal thread data layout. This change: - Replace _resolve_cwd() with a fixed _get_work_dir() that always uses {base_dir}/acp-workspace/, eliminating virtual path translation and thread_id lookups - Introduce /mnt/acp-workspace virtual path for lead agent read-only access to ACP agent output files (same pattern as /mnt/skills) - Add security guards: read-only validation, path traversal prevention, command path allowlisting, and output masking for acp-workspace - Update system prompt and tool description to guide LLM: send self-contained tasks to ACP agents, copy results via /mnt/acp-workspace - Add 11 new security tests for ACP workspace path handling Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(prompt): inject ACP section only when ACP agents are configured The ACP agent guidance in the system prompt is now conditionally built by _build_acp_section(), which checks get_acp_agents() and returns an empty string when no ACP agents are configured. This avoids polluting the prompt with irrelevant instructions for users who don't use ACP. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix lint * fix(harness): address Copilot review comments on sandbox path handling and ACP tool - local_sandbox: fix path-segment boundary bug in _resolve_path (== or startswith +"/") and add lookahead in _resolve_paths_in_command regex to prevent /mnt/skills matching inside /mnt/skills-extra - local_sandbox_provider: replace print() with logger.warning(..., exc_info=True) - invoke_acp_agent_tool: guard getattr(option, "optionId") with None default + continue; move full prompt from INFO to DEBUG level (truncated to 200 chars) - sandbox/tools: fix _get_acp_workspace_host_path docstring to match implementation; remove misleading "read-only" language from validate_local_bash_command_paths Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(acp): thread-isolated workspaces, permission guardrail, and ContextVar registry P1.1 – ACP workspace thread isolation - Add `Paths.acp_workspace_dir(thread_id)` for per-thread paths - `_get_work_dir(thread_id)` in invoke_acp_agent_tool now uses `{base_dir}/threads/{thread_id}/acp-workspace/`; falls back to global workspace when thread_id is absent or invalid - `_invoke` extracts thread_id from `RunnableConfig` via `Annotated[RunnableConfig, InjectedToolArg]` - `sandbox/tools.py`: `_get_acp_workspace_host_path(thread_id)`, `_resolve_acp_workspace_path(path, thread_id)`, and all callers (`replace_virtual_paths_in_command`, `mask_local_paths_in_output`, `ls_tool`, `read_file_tool`) now resolve ACP paths per-thread P1.2 – ACP permission guardrail - New `auto_approve_permissions: bool = False` field in `ACPAgentConfig` - `_build_permission_response(options, *, auto_approve: bool)` now defaults to deny; only approves when `auto_approve=True` - Document field in `config.example.yaml` P2 – Deferred tool registry race condition - Replace module-level `_registry` global with `contextvars.ContextVar` - Each asyncio request context gets its own registry; worker threads inherit the context automatically via `loop.run_in_executor` - Expose `get_deferred_registry` / `set_deferred_registry` / `reset_deferred_registry` helpers Tests: 831 pass (57 for affected modules, 3 new tests) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(sandbox): mount /mnt/acp-workspace in docker sandbox container The AioSandboxProvider was not mounting the ACP workspace into the sandbox container, so /mnt/acp-workspace was inaccessible when the lead agent tried to read ACP results in docker mode. Changes: - `ensure_thread_dirs`: also create `acp-workspace/` (chmod 0o777) so the directory exists before the sandbox container starts — required for Docker volume mounts - `_get_thread_mounts`: add read-only `/mnt/acp-workspace` mount using the per-thread host path (`host_paths.acp_workspace_dir(thread_id)`) - Update stale CLAUDE.md description (was "fixed global workspace") Tests: `test_aio_sandbox_provider.py` (4 new tests) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(lint): remove unused imports in test_aio_sandbox_provider Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix config --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
DanielWalnut
@@ -250,6 +250,7 @@ You: "Deploying to staging..." [proceed]
|
||||
- For PDF, PPT, Excel, and Word files, converted Markdown versions (*.md) are available alongside originals
|
||||
- All temporary work happens in `/mnt/user-data/workspace`
|
||||
- Final deliverables must be copied to `/mnt/user-data/outputs` and presented using `present_file` tool
|
||||
{acp_section}
|
||||
</working_directory>
|
||||
|
||||
<response_style>
|
||||
@@ -444,6 +445,26 @@ def get_deferred_tools_prompt_section() -> str:
|
||||
return f"<available-deferred-tools>\n{names}\n</available-deferred-tools>"
|
||||
|
||||
|
||||
def _build_acp_section() -> str:
|
||||
"""Build the ACP agent prompt section, only if ACP agents are configured."""
|
||||
try:
|
||||
from deerflow.config.acp_config import get_acp_agents
|
||||
|
||||
agents = get_acp_agents()
|
||||
if not agents:
|
||||
return ""
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
return (
|
||||
"\n**ACP Agent Tasks (invoke_acp_agent):**\n"
|
||||
"- ACP agents (e.g. codex, claude_code) run in their own independent workspace — NOT in `/mnt/user-data/`\n"
|
||||
"- When writing prompts for ACP agents, describe the task only — do NOT reference `/mnt/user-data` paths\n"
|
||||
"- ACP agent results are accessible at `/mnt/acp-workspace/` (read-only) — use `ls`, `read_file`, or `bash cp` to retrieve output files\n"
|
||||
"- To deliver ACP output to the user: copy from `/mnt/acp-workspace/<file>` to `/mnt/user-data/outputs/<file>`, then use `present_file`"
|
||||
)
|
||||
|
||||
|
||||
def apply_prompt_template(subagent_enabled: bool = False, max_concurrent_subagents: int = 3, *, agent_name: str | None = None, available_skills: set[str] | None = None) -> str:
|
||||
# Get memory context
|
||||
memory_context = _get_memory_context(agent_name)
|
||||
@@ -476,6 +497,9 @@ def apply_prompt_template(subagent_enabled: bool = False, max_concurrent_subagen
|
||||
# Get deferred tools section (tool_search)
|
||||
deferred_tools_section = get_deferred_tools_prompt_section()
|
||||
|
||||
# Build ACP agent section only if ACP agents are configured
|
||||
acp_section = _build_acp_section()
|
||||
|
||||
# Format the prompt with dynamic skills and memory
|
||||
prompt = SYSTEM_PROMPT_TEMPLATE.format(
|
||||
agent_name=agent_name or "DeerFlow 2.0",
|
||||
@@ -486,6 +510,7 @@ def apply_prompt_template(subagent_enabled: bool = False, max_concurrent_subagen
|
||||
subagent_section=subagent_section,
|
||||
subagent_reminder=subagent_reminder,
|
||||
subagent_thinking=subagent_thinking,
|
||||
acp_section=acp_section,
|
||||
)
|
||||
|
||||
return prompt + f"\n<current_date>{datetime.now().strftime('%Y-%m-%d, %A')}</current_date>"
|
||||
|
||||
@@ -238,13 +238,7 @@ def format_memory_for_injection(memory_data: dict[str, Any], max_tokens: int = 2
|
||||
facts_data = memory_data.get("facts", [])
|
||||
if isinstance(facts_data, list) and facts_data:
|
||||
ranked_facts = sorted(
|
||||
(
|
||||
f
|
||||
for f in facts_data
|
||||
if isinstance(f, dict)
|
||||
and isinstance(f.get("content"), str)
|
||||
and f.get("content").strip()
|
||||
),
|
||||
(f for f in facts_data if isinstance(f, dict) and isinstance(f.get("content"), str) and f.get("content").strip()),
|
||||
key=lambda fact: _coerce_confidence(fact.get("confidence"), default=0.0),
|
||||
reverse=True,
|
||||
)
|
||||
|
||||
@@ -392,14 +392,7 @@ class MemoryUpdater:
|
||||
current_memory["facts"] = [f for f in current_memory.get("facts", []) if f.get("id") not in facts_to_remove]
|
||||
|
||||
# Add new facts
|
||||
existing_fact_keys = {
|
||||
fact_key
|
||||
for fact_key in (
|
||||
_fact_content_key(fact.get("content"))
|
||||
for fact in current_memory.get("facts", [])
|
||||
)
|
||||
if fact_key is not None
|
||||
}
|
||||
existing_fact_keys = {fact_key for fact_key in (_fact_content_key(fact.get("content")) for fact in current_memory.get("facts", [])) if fact_key is not None}
|
||||
new_facts = update_data.get("newFacts", [])
|
||||
for fact in new_facts:
|
||||
confidence = fact.get("confidence", 0.5)
|
||||
|
||||
@@ -61,16 +61,9 @@ def _hash_tool_calls(tool_calls: list[dict]) -> str:
|
||||
return hashlib.md5(blob.encode()).hexdigest()[:12]
|
||||
|
||||
|
||||
_WARNING_MSG = (
|
||||
"[LOOP DETECTED] You are repeating the same tool calls. "
|
||||
"Stop calling tools and produce your final answer now. "
|
||||
"If you cannot complete the task, summarize what you accomplished so far."
|
||||
)
|
||||
_WARNING_MSG = "[LOOP DETECTED] You are repeating the same tool calls. Stop calling tools and produce your final answer now. If you cannot complete the task, summarize what you accomplished so far."
|
||||
|
||||
_HARD_STOP_MSG = (
|
||||
"[FORCED STOP] Repeated tool calls exceeded the safety limit. "
|
||||
"Producing final answer with results collected so far."
|
||||
)
|
||||
_HARD_STOP_MSG = "[FORCED STOP] Repeated tool calls exceeded the safety limit. Producing final answer with results collected so far."
|
||||
|
||||
|
||||
class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
|
||||
@@ -153,7 +146,7 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
|
||||
history = self._history[thread_id]
|
||||
history.append(call_hash)
|
||||
if len(history) > self.window_size:
|
||||
history[:] = history[-self.window_size:]
|
||||
history[:] = history[-self.window_size :]
|
||||
|
||||
count = history.count(call_hash)
|
||||
tool_names = [tc.get("name", "?") for tc in tool_calls]
|
||||
@@ -196,10 +189,12 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
|
||||
# Strip tool_calls from the last AIMessage to force text output
|
||||
messages = state.get("messages", [])
|
||||
last_msg = messages[-1]
|
||||
stripped_msg = last_msg.model_copy(update={
|
||||
"tool_calls": [],
|
||||
"content": (last_msg.content or "") + f"\n\n{_HARD_STOP_MSG}",
|
||||
})
|
||||
stripped_msg = last_msg.model_copy(
|
||||
update={
|
||||
"tool_calls": [],
|
||||
"content": (last_msg.content or "") + f"\n\n{_HARD_STOP_MSG}",
|
||||
}
|
||||
)
|
||||
return {"messages": [stripped_msg]}
|
||||
|
||||
if warning:
|
||||
|
||||
Reference in New Issue
Block a user