Files

228 lines
6.7 KiB
JSON
Raw Permalink Normal View History

feat(agent): align Go agent behavior with Python (except retrieval component) (#16225) ## Summary Aligns the **Go agent runtime/canvas/components/tools** behavior with the **Python `agent/` implementation** so the same stored canvas DSL produces the same execution result on either side. Every component, tool, and runtime primitive in `internal/agent/` is now driven by the same semantics as its Python counterpart — variable resolution, template substitution, control flow, error reporting, retry/cancel, and stream event shapes. The **retrieval component is the one explicit exception** in this PR. It is being reworked in a separate change and is excluded from this alignment pass; the wrapper slot (`universe_a_wrappers.go → newRetrievalComponent`) is preserved. ## Scope of alignment ### Components (all aligned with `agent/component/`) `Begin` · `Message` · `LLM` (incl. ChatTemplateKwargs, MessageHistoryWindowSize, VisualFiles, Cite, OutputStructure, JSONOutput, TopP, MaxRetries, DelayAfterError, credentials) · `Agent` (react + tool artifact capture + `Reset()` interface-assert) · `Switch` (12/12 operators, Python-equivalent semantics) · `Categorize` · `Invoke` · `Iteration` · `Loop` (macro-expansion through `workflowx.AddLoopNode`) · `UserFillUp` (Python-equivalent interrupt/resume via eino `compose.Interrupt`/`ResumeWithData`) · `FillUp` · `DataOperations` · `ListOperations` · `StringTransform` · `VariableAggregator` · `VariableAssigner` · `Browser` (full stagehand runtime parity) · `DocsGenerator` · `ExcelProcessor`. ### Tools (all aligned with `agent/tools/`) `Retrieval` (wrapper slot only — logic out of scope) · `MCPToolAdapter` (streamable-HTTP) · `CodeExec` (sandbox bridge with `code_exec_contract.go` matching Python contract) · `AkShare` · `ArXiv` · `Crawler` · `DeepL` · `DuckDuckGo` · `Email` · `ExeSQL` · `GitHub` · `Google` · `GoogleScholar` · `Jin10` · `PubMed` · `QWeather` · `SearXNG` · `Tavily` · `Tushare` · `Wencai` · `Wikipedia` · `YahooFinance` — uniform `eino tool.InvokableTool` interface, SSRF protection, shared HTTP client. ### Canvas execution engine (`internal/agent/canvas/`) Aligned with Python's `agent/canvas.py`: - **Scheduler** (`scheduler.go`): state pre/post handlers, node lambdas, per-component timeout resolver (4-level: per-class env → per-class table → uniform env → 600s fallback), `legacyNoOpNames`. - **Loop subgraph** (`loop_subgraph.go`): Python-equivalent `AddLoopNode` macro expansion + condition translation. - **Multibranch** (`multibranch.go`): `Switch` / `Categorize` routing via `compose.NewGraphMultiBranch` — same branch selection semantics as Python. - **Parallel subgraph** (`parallel_subgraph.go`): matches Python's parallel fan-out contract. - **Interrupt/Resume** (`interrupt_resume.go`): `UserFillUpNodeBody` / `IsInterruptError` / `ExtractInterruptContexts` — replaces the deprecated Python sentinel chain with eino's native interrupt API, preserving the same external behavior. - **Checkpoint** (`checkpoint_store.go`): `RedisCheckPointStore` Get/Set/Delete, with business metadata (status / canvas_id / parent_run_id) on a parallel Redis Hash. - **RunTracker** (`run_tracker.go`): Start / MarkSucceeded / MarkFailed / MarkCancelled / AttachCheckpoint — same lifecycle as the Python run record. - **Cancel** (`cancel.go`): Redis pub/sub watch. - **Stream** (`stream.go`): SSE channel with `messages` / `waiting` / `errors` / `done` events, same shape as Python's `agent.canvas.RunEvent` payload. ### DSL bridge (`internal/agent/dsl/`) - `normalize.go`: v1↔v2 collapsed into a single wire format — Python and Go consume the same stored JSON. - `reset.go`: per-run state reset matches Python's `Canvas.reset()` semantics. - Testdata mirrors Python's `agent_msg.json` / `all.json` / etc. ### Runtime (`internal/agent/runtime/`) - `CanvasState` / `NewCanvasState` / `GetVar` / `SetVar` / `ReadVars`: same `{{cpn_id@param}}` resolution model. - `ResolveTemplate` (regex fast path + gonja fallback) — Python Jinja-style semantics. - `selector.go`, `metrics.go`, `component.go`: shared runtime contracts. ## Out of scope (intentionally) - **`Retrieval` component logic** — wrapped only; full parity lands in a follow-up PR. - **Frontend** — only minor dsl-bridge / canvas UX fixes ride along. - **CLI / admin / model registry** — orthogonal to agent behavior. ## How alignment is verified `internal/service/agent_run_e2e_test.go` exercises the **full production chain** against real Python-shaped DSL fixtures: ``` loadCanvasForUser → versionDAO.GetLatest → decodeCanvasFromDSL → canvas.Compile → cc.Workflow.Invoke → answer extraction ``` using in-memory SQLite + miniredis (no Docker). Covers: - `TestRunAgent_RealCanvas_BeginMessage` — happy path, `{{sys.query}}` resolution - `TestRunAgent_RealCanvas_WaitForUserResume` — two-run resume cycle (Python-equivalent) - `TestRunAgent_RealCanvas_CompileFails` — unknown component name → sanitized error (Python-equivalent) - `TestRunAgent_RealCanvas_InvokeFails` — unresolvable template ref (Python-equivalent) - `TestRunAgent_RunTracker_AttachCheckpoint_CallSequence` — Start→AttachCheckpoint→MarkSucceeded lifecycle `internal/handler/agent_test.go` — SSE streaming parity (`Content-Type: text/event-stream`, `data: {…}\n\n`, trailing `data: [DONE]\n\n`, OpenAI-compatible non-stream `choices`). `internal/agent/canvas/fixture_compile_test.go` + per-component tests pin the Python-equivalent outputs. ``` go test -count=1 -v -run 'TestRunAgent_RealCanvas|TestRunAgent_RunTracker' ./internal/service/ ``` ## Design reference `docs/develop/agent-go-port-design.md` (1329 lines, last cross-checked 2026-06-17) — module layout, per-component / per-tool inventory, corner-case catalogue, and the actionable backlog (Section 14, including the retrieval alignment follow-up). --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-06-22 11:58:29 +08:00
{
"components": {
"Agent:TenderSpidersStick": {
"downstream": [
"Message:MajorNumbersPlay"
],
"obj": {
"component_name": "Agent",
"params": {
"cite": true,
"delay_after_error": 1,
"description": "",
"exception_default_value": "",
"exception_goto": [],
"exception_method": "",
"frequencyPenaltyEnabled": true,
"frequency_penalty": 0.7,
"llm_id": "glm-4.7-flashx@zz@ZHIPU-AI",
"maxTokensEnabled": false,
"max_retries": 3,
"max_rounds": 1,
"max_tokens": 256,
"mcp": [],
"message_history_window_size": 12,
"outputs": {
"content": {
"type": "string",
"value": ""
}
},
"presencePenaltyEnabled": true,
"presence_penalty": 0.4,
"prompts": [
{
"content": "{sys.query}",
"role": "user"
}
],
"showStructuredOutput": false,
"sys_prompt": "\n <role>\n You are a helpful assistant, an AI assistant specialized in problem-solving for the user.\n If a specific domain is provided, adapt your expertise to that domain; otherwise, operate as a generalist.\n </role>\n <instructions>\n 1. Understand the users request.\n 2. Decompose it into logical subtasks.\n 3. Execute each subtask step by step, reasoning transparently.\n 4. Validate accuracy and consistency.\n 5. Summarize the final result clearly.\n </instructions>",
"temperature": 0.1,
"temperatureEnabled": true,
"tools": [],
"topPEnabled": true,
"top_p": 0.3,
"user_prompt": "",
"visual_files_var": ""
}
},
"upstream": [
"begin"
]
},
"Message:MajorNumbersPlay": {
"downstream": [],
"obj": {
"component_name": "Message",
"params": {
"content": [
"{Agent:TenderSpidersStick@content}"
]
}
},
"upstream": [
"Agent:TenderSpidersStick"
]
},
"begin": {
"downstream": [
"Agent:TenderSpidersStick"
],
"obj": {
"component_name": "Begin",
"params": {
"mode": "conversational",
"prologue": "Hi! I'm your assistant. What can I do for you?"
}
},
"upstream": []
}
},
"globals": {
"sys.conversation_turns": 0,
"sys.date": "",
"sys.files": [],
"sys.history": [],
"sys.query": "",
"sys.user_id": ""
},
"graph": {
"edges": [
{
"id": "xy-edge__beginstart-Agent:TenderSpidersStickend",
"source": "begin",
"sourceHandle": "start",
"target": "Agent:TenderSpidersStick",
"targetHandle": "end"
},
{
"data": {
"isHovered": false
},
"id": "xy-edge__Agent:TenderSpidersStickstart-Message:MajorNumbersPlayend",
"source": "Agent:TenderSpidersStick",
"sourceHandle": "start",
"target": "Message:MajorNumbersPlay",
"targetHandle": "end"
}
],
"nodes": [
{
"data": {
"form": {
"mode": "conversational",
"prologue": "Hi! I'm your assistant. What can I do for you?"
},
"label": "Begin",
"name": "begin"
},
"dragging": false,
"id": "begin",
"measured": {
"height": 81,
"width": 200
},
"position": {
"x": -173.77599999999995,
"y": -145.59999999999994
},
"selected": false,
"sourcePosition": "left",
"targetPosition": "right",
"type": "beginNode"
},
{
"data": {
"form": {
"cite": true,
"delay_after_error": 1,
"description": "",
"exception_default_value": "",
"exception_goto": [],
"exception_method": "",
"frequencyPenaltyEnabled": true,
"frequency_penalty": 0.7,
"llm_id": "glm-4.7-flashx@zz@ZHIPU-AI",
"maxTokensEnabled": false,
"max_retries": 3,
"max_rounds": 1,
"max_tokens": 256,
"mcp": [],
"message_history_window_size": 12,
"outputs": {
"content": {
"type": "string",
"value": ""
}
},
"presencePenaltyEnabled": true,
"presence_penalty": 0.4,
"prompts": [
{
"content": "{sys.query}",
"role": "user"
}
],
"showStructuredOutput": false,
"sys_prompt": "\n <role>\n You are a helpful assistant, an AI assistant specialized in problem-solving for the user.\n If a specific domain is provided, adapt your expertise to that domain; otherwise, operate as a generalist.\n </role>\n <instructions>\n 1. Understand the users request.\n 2. Decompose it into logical subtasks.\n 3. Execute each subtask step by step, reasoning transparently.\n 4. Validate accuracy and consistency.\n 5. Summarize the final result clearly.\n </instructions>",
"temperature": 0.1,
"temperatureEnabled": true,
"tools": [],
"topPEnabled": true,
"top_p": 0.3,
"user_prompt": "",
"visual_files_var": ""
},
"label": "Agent",
"name": "Agent_0"
},
"dragging": false,
"id": "Agent:TenderSpidersStick",
"measured": {
"height": 79,
"width": 200
},
"position": {
"x": 92.03339543909598,
"y": -132.31937403691842
},
"selected": true,
"sourcePosition": "right",
"targetPosition": "left",
"type": "agentNode"
},
{
"data": {
"form": {
"content": [
"{Agent:TenderSpidersStick@content}"
]
},
"label": "Message",
"name": "Message_0"
},
"dragging": false,
"id": "Message:MajorNumbersPlay",
"measured": {
"height": 85,
"width": 200
},
"position": {
"x": 336.5453954390959,
"y": -120.22337403691841
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "messageNode"
}
]
},
"history": [],
"memory": [],
"messages": [],
"path": [],
"retrieval": [],
"variables": []
}