Files
ragflow/internal/agent/canvas/canvas.go

149 lines
5.3 KiB
Go
Raw Normal View History

feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952) Ports the agent canvas subsystem from Python to Go. ## What's included ### Canvas Engine (Phase 0/1) - State engine, scheduler, variable resolver, Redis checkpoint store, cancel protocol - **209 tests** across canvas / component / io packages ### 22 Components (P0–P4) | Tier | Components | |---|---| | P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin, Message, Invoke | | P1 T3 | VariableAggregator, VariableAssigner, StringTransform, ListOperations, DataOperations | | P2 T3 | Iteration, IterationItem, Loop, LoopItem | | P3 T3 | UserFillUp, Fillup | | P4 T5 | Browser, ExcelProcessor, DocsGenerator | ### DSL v2 Schema (Phase 2.5) - Typed v2 in-memory model with v1-to-v2 auto-detect converter - v1 legacy field stripping per plan §2.11.7 ### HTTP Endpoints & Bug Fixes (Plans PR1–PR3) - **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)` pattern - **CreateAgent validation**: title/DSL required, duplicate check, 103 envelope - **13 new endpoints**: templates, prompts, tags, sessions CRUD, chat/completions (SSE + non-stream stubs), rerun, test_db_connection, logs, webhook/logs - **756 Go unit tests** (745 → 756, +18) - **17 → 0 Python integration test failures** (test_agents.py + test_session_management/) ### Tools 21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory stubs ### Infrastructure OTel observability, NATS message queue, DeepDoc gRPC client, SSRF guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
// Package canvas implements the RAGFlow agent canvas Go port.
//
// Shared runtime contracts (CanvasState, Component, ComponentFactory,
// state context plumbing, template helpers) live in
// internal/agent/runtime. Canvas re-exports them through thin aliases
// so existing call sites keep working while breaking the historic
// canvas <-> component import cycle.
package canvas
import (
"ragflow/internal/agent/runtime"
"ragflow/internal/common"
"go.uber.org/zap"
feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952) Ports the agent canvas subsystem from Python to Go. ## What's included ### Canvas Engine (Phase 0/1) - State engine, scheduler, variable resolver, Redis checkpoint store, cancel protocol - **209 tests** across canvas / component / io packages ### 22 Components (P0–P4) | Tier | Components | |---|---| | P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin, Message, Invoke | | P1 T3 | VariableAggregator, VariableAssigner, StringTransform, ListOperations, DataOperations | | P2 T3 | Iteration, IterationItem, Loop, LoopItem | | P3 T3 | UserFillUp, Fillup | | P4 T5 | Browser, ExcelProcessor, DocsGenerator | ### DSL v2 Schema (Phase 2.5) - Typed v2 in-memory model with v1-to-v2 auto-detect converter - v1 legacy field stripping per plan §2.11.7 ### HTTP Endpoints & Bug Fixes (Plans PR1–PR3) - **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)` pattern - **CreateAgent validation**: title/DSL required, duplicate check, 103 envelope - **13 new endpoints**: templates, prompts, tags, sessions CRUD, chat/completions (SSE + non-stream stubs), rerun, test_db_connection, logs, webhook/logs - **756 Go unit tests** (745 → 756, +18) - **17 → 0 Python integration test failures** (test_agents.py + test_session_management/) ### Tools 21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory stubs ### Infrastructure OTel observability, NATS message queue, DeepDoc gRPC client, SSRF guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
)
// legacyNoOpNames is the set of component names that the Go port
// recognises for DSL v1 compatibility but does not ship a real
// implementation for. Encountering one of these in a DSL is mapped to
// the same no-op echo lambda used for placeholder bodies by the
// BuildWorkflow in scheduler.go. New DSLs should not use these names —
// they exist only so v1 DSLs that reference Python-era sentinel
// components ("ExitLoop") still compile and run in the Go port.
//
// Membership semantics inside a Loop's sub-graph: legacy names that
// appear as descendants of a Loop are absorbed as no-op members of the
// sub-graph; they do not contribute to loop control. Termination is
// driven by the Loop's loop_termination_condition predicate, not by
// reaching an ExitLoop node.
var legacyNoOpNames = map[string]bool{
"exitloop": true,
}
// CanvasState aliases runtime.CanvasState so existing canvas callers
// (and component tests that still import the canvas package) keep
// compiling without changes. The canonical definition lives in
// internal/agent/runtime/state.go.
type CanvasState = runtime.CanvasState
// NewCanvasState re-exports runtime.NewCanvasState.
func NewCanvasState(runID, sessionID string) *CanvasState {
return runtime.NewCanvasState(runID, sessionID)
feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952) Ports the agent canvas subsystem from Python to Go. ## What's included ### Canvas Engine (Phase 0/1) - State engine, scheduler, variable resolver, Redis checkpoint store, cancel protocol - **209 tests** across canvas / component / io packages ### 22 Components (P0–P4) | Tier | Components | |---|---| | P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin, Message, Invoke | | P1 T3 | VariableAggregator, VariableAssigner, StringTransform, ListOperations, DataOperations | | P2 T3 | Iteration, IterationItem, Loop, LoopItem | | P3 T3 | UserFillUp, Fillup | | P4 T5 | Browser, ExcelProcessor, DocsGenerator | ### DSL v2 Schema (Phase 2.5) - Typed v2 in-memory model with v1-to-v2 auto-detect converter - v1 legacy field stripping per plan §2.11.7 ### HTTP Endpoints & Bug Fixes (Plans PR1–PR3) - **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)` pattern - **CreateAgent validation**: title/DSL required, duplicate check, 103 envelope - **13 new endpoints**: templates, prompts, tags, sessions CRUD, chat/completions (SSE + non-stream stubs), rerun, test_db_connection, logs, webhook/logs - **756 Go unit tests** (745 → 756, +18) - **17 → 0 Python integration test failures** (test_agents.py + test_session_management/) ### Tools 21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory stubs ### Infrastructure OTel observability, NATS message queue, DeepDoc gRPC client, SSRF guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
}
// Canvas is the in-memory DSL representation loaded from a user_canvas row.
// It is the input to compile.go which builds the eino Workflow.
type Canvas struct {
Components map[string]CanvasComponent `json:"components"`
Path []string `json:"path"`
History []map[string]any `json:"history,omitempty"`
Memory []map[string]any `json:"memory,omitempty"`
feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952) Ports the agent canvas subsystem from Python to Go. ## What's included ### Canvas Engine (Phase 0/1) - State engine, scheduler, variable resolver, Redis checkpoint store, cancel protocol - **209 tests** across canvas / component / io packages ### 22 Components (P0–P4) | Tier | Components | |---|---| | P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin, Message, Invoke | | P1 T3 | VariableAggregator, VariableAssigner, StringTransform, ListOperations, DataOperations | | P2 T3 | Iteration, IterationItem, Loop, LoopItem | | P3 T3 | UserFillUp, Fillup | | P4 T5 | Browser, ExcelProcessor, DocsGenerator | ### DSL v2 Schema (Phase 2.5) - Typed v2 in-memory model with v1-to-v2 auto-detect converter - v1 legacy field stripping per plan §2.11.7 ### HTTP Endpoints & Bug Fixes (Plans PR1–PR3) - **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)` pattern - **CreateAgent validation**: title/DSL required, duplicate check, 103 envelope - **13 new endpoints**: templates, prompts, tags, sessions CRUD, chat/completions (SSE + non-stream stubs), rerun, test_db_connection, logs, webhook/logs - **756 Go unit tests** (745 → 756, +18) - **17 → 0 Python integration test failures** (test_agents.py + test_session_management/) ### Tools 21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory stubs ### Infrastructure OTel observability, NATS message queue, DeepDoc gRPC client, SSRF guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
Retrieval map[string]any `json:"retrieval,omitempty"`
Globals map[string]any `json:"globals,omitempty"`
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
// NodeParents preserves the front-end graph's grouping metadata
// (graph.nodes[*].parentId) for runtime-only subgraph expansion.
// The backend treats the incoming DSL as read-only; this is a
// decoder-side mirror used only to decide which nodes belong to a
// Loop / Parallel body during compilation.
NodeParents map[string]string `json:"-"`
feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952) Ports the agent canvas subsystem from Python to Go. ## What's included ### Canvas Engine (Phase 0/1) - State engine, scheduler, variable resolver, Redis checkpoint store, cancel protocol - **209 tests** across canvas / component / io packages ### 22 Components (P0–P4) | Tier | Components | |---|---| | P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin, Message, Invoke | | P1 T3 | VariableAggregator, VariableAssigner, StringTransform, ListOperations, DataOperations | | P2 T3 | Iteration, IterationItem, Loop, LoopItem | | P3 T3 | UserFillUp, Fillup | | P4 T5 | Browser, ExcelProcessor, DocsGenerator | ### DSL v2 Schema (Phase 2.5) - Typed v2 in-memory model with v1-to-v2 auto-detect converter - v1 legacy field stripping per plan §2.11.7 ### HTTP Endpoints & Bug Fixes (Plans PR1–PR3) - **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)` pattern - **CreateAgent validation**: title/DSL required, duplicate check, 103 envelope - **13 new endpoints**: templates, prompts, tags, sessions CRUD, chat/completions (SSE + non-stream stubs), rerun, test_db_connection, logs, webhook/logs - **756 Go unit tests** (745 → 756, +18) - **17 → 0 Python integration test failures** (test_agents.py + test_session_management/) ### Tools 21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory stubs ### Infrastructure OTel observability, NATS message queue, DeepDoc gRPC client, SSRF guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
}
// CanvasComponent is the in-memory DSL node. The Obj.ComponentName
// matches agent/component/<name>.py's class name (case-insensitive,
// per Python v1 DSL semantics).
feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952) Ports the agent canvas subsystem from Python to Go. ## What's included ### Canvas Engine (Phase 0/1) - State engine, scheduler, variable resolver, Redis checkpoint store, cancel protocol - **209 tests** across canvas / component / io packages ### 22 Components (P0–P4) | Tier | Components | |---|---| | P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin, Message, Invoke | | P1 T3 | VariableAggregator, VariableAssigner, StringTransform, ListOperations, DataOperations | | P2 T3 | Iteration, IterationItem, Loop, LoopItem | | P3 T3 | UserFillUp, Fillup | | P4 T5 | Browser, ExcelProcessor, DocsGenerator | ### DSL v2 Schema (Phase 2.5) - Typed v2 in-memory model with v1-to-v2 auto-detect converter - v1 legacy field stripping per plan §2.11.7 ### HTTP Endpoints & Bug Fixes (Plans PR1–PR3) - **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)` pattern - **CreateAgent validation**: title/DSL required, duplicate check, 103 envelope - **13 new endpoints**: templates, prompts, tags, sessions CRUD, chat/completions (SSE + non-stream stubs), rerun, test_db_connection, logs, webhook/logs - **756 Go unit tests** (745 → 756, +18) - **17 → 0 Python integration test failures** (test_agents.py + test_session_management/) ### Tools 21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory stubs ### Infrastructure OTel observability, NATS message queue, DeepDoc gRPC client, SSRF guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
type CanvasComponent struct {
Obj CanvasComponentObj `json:"obj"`
Downstream []string `json:"downstream"`
Upstream []string `json:"upstream"`
}
type CanvasComponentObj struct {
ComponentName string `json:"component_name"`
Params map[string]any `json:"params"`
}
// Close releases resources held by components referenced in the canvas
// DSL. It walks every component's params map and calls Close() on any
// value that implements a Close() method (MCPToolAdapters, HTTP
// clients, etc.). Mirrors Python's Graph.close() in agent/canvas.py.
//
// In Go's architecture MCP sessions are per-invocation and auto-torn
// down; Close() is a best-effort hook that ensures idle HTTP
// connections are released even when adapters outlive a single call.
func (c *Canvas) Close() {
if c == nil {
return
}
seen := make(map[any]bool)
for _, comp := range c.Components {
for _, v := range comp.Obj.Params {
walkAndClose(v, seen)
}
}
}
// walkAndClose recursively walks a value and calls Close() on any
// objects that implement a Close() method. Maps, slices, and pointers
// are recursed into; other types are skipped. Already-seen objects
// (by interface identity) are skipped to avoid double-close.
func walkAndClose(v any, seen map[any]bool) {
if v == nil {
return
}
if closer, ok := v.(interface{ Close() }); ok {
if !seen[closer] {
seen[closer] = true
safeClose(closer)
}
return
}
switch val := v.(type) {
case map[string]any:
for _, child := range val {
walkAndClose(child, seen)
}
case []any:
for _, child := range val {
walkAndClose(child, seen)
}
}
}
// safeClose calls Close() on a closer value, swallowing panics so a
// misbehaving resource doesn't crash the canvas tear-down path.
func safeClose(closer interface{ Close() }) {
defer func() {
if rec := recover(); rec != nil {
common.Warn("canvas: Close() panicked", zap.Any("recover", rec))
}
}()
closer.Close()
}
feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952) Ports the agent canvas subsystem from Python to Go. ## What's included ### Canvas Engine (Phase 0/1) - State engine, scheduler, variable resolver, Redis checkpoint store, cancel protocol - **209 tests** across canvas / component / io packages ### 22 Components (P0–P4) | Tier | Components | |---|---| | P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin, Message, Invoke | | P1 T3 | VariableAggregator, VariableAssigner, StringTransform, ListOperations, DataOperations | | P2 T3 | Iteration, IterationItem, Loop, LoopItem | | P3 T3 | UserFillUp, Fillup | | P4 T5 | Browser, ExcelProcessor, DocsGenerator | ### DSL v2 Schema (Phase 2.5) - Typed v2 in-memory model with v1-to-v2 auto-detect converter - v1 legacy field stripping per plan §2.11.7 ### HTTP Endpoints & Bug Fixes (Plans PR1–PR3) - **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)` pattern - **CreateAgent validation**: title/DSL required, duplicate check, 103 envelope - **13 new endpoints**: templates, prompts, tags, sessions CRUD, chat/completions (SSE + non-stream stubs), rerun, test_db_connection, logs, webhook/logs - **756 Go unit tests** (745 → 756, +18) - **17 → 0 Python integration test failures** (test_agents.py + test_session_management/) ### Tools 21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory stubs ### Infrastructure OTel observability, NATS message queue, DeepDoc gRPC client, SSRF guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
// Component is an alias for runtime.Component — the minimal runtime
// surface BuildWorkflow needs at sub-graph build time. The canonical
// definition (and the SetDefaultFactory / DefaultFactory plumbing)
// lives in internal/agent/runtime/component.go.
type Component = runtime.Component
// ComponentFactory aliases runtime.ComponentFactory.
type ComponentFactory = runtime.ComponentFactory
// SetDefaultFactory re-exports runtime.SetDefaultFactory. The
// orchestrator's main.go can call either entry point; new code
// should prefer the runtime package directly.
func SetDefaultFactory(f ComponentFactory) {
runtime.SetDefaultFactory(f)
}