mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-14 17:08:31 +08:00
## 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>
248 lines
7.2 KiB
Go
248 lines
7.2 KiB
Go
// Package canvas — scheduler unit tests.
|
|
package canvas
|
|
|
|
import (
|
|
"context"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
// TestBuildWorkflow_3NodeLinear exercises a trivial Begin → LLM → Message
|
|
// chain. Verifies the workflow compiles and the runtime paths exist.
|
|
func TestBuildWorkflow_3NodeLinear(t *testing.T) {
|
|
c := &Canvas{
|
|
Components: map[string]CanvasComponent{
|
|
"begin_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Begin", Params: map[string]any{}},
|
|
Downstream: []string{"llm_0"},
|
|
Upstream: []string{},
|
|
},
|
|
"llm_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "LLM", Params: map[string]any{"prompt": "hi"}},
|
|
Downstream: []string{"message_0"},
|
|
Upstream: []string{"begin_0"},
|
|
},
|
|
"message_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Message", Params: map[string]any{}},
|
|
Downstream: []string{},
|
|
Upstream: []string{"llm_0"},
|
|
},
|
|
},
|
|
Path: []string{"begin_0", "llm_0", "message_0"},
|
|
}
|
|
|
|
wf, err := BuildWorkflow(context.Background(), c)
|
|
if err != nil {
|
|
t.Fatalf("BuildWorkflow: %v", err)
|
|
}
|
|
if wf == nil {
|
|
t.Fatal("nil workflow")
|
|
}
|
|
|
|
// Compile to a Runnable to confirm the topology is internally consistent.
|
|
cc, err := Compile(context.Background(), c)
|
|
if err != nil {
|
|
t.Fatalf("Compile: %v", err)
|
|
}
|
|
if cc.Workflow == nil {
|
|
t.Fatal("nil compiled workflow")
|
|
}
|
|
}
|
|
|
|
// TestBuildWorkflow_5NodeDiamond exercises a diamond: A → B, A → C,
|
|
// B → D, C → D. The two parallel branches converge at D.
|
|
func TestBuildWorkflow_5NodeDiamond(t *testing.T) {
|
|
c := &Canvas{
|
|
Components: map[string]CanvasComponent{
|
|
"begin_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Begin", Params: map[string]any{}},
|
|
Downstream: []string{"a_0"},
|
|
Upstream: []string{},
|
|
},
|
|
"a_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Categorize", Params: map[string]any{}},
|
|
Downstream: []string{"b_0", "c_0"},
|
|
Upstream: []string{"begin_0"},
|
|
},
|
|
"b_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "LLM", Params: map[string]any{}},
|
|
Downstream: []string{"d_0"},
|
|
Upstream: []string{"a_0"},
|
|
},
|
|
"c_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "LLM", Params: map[string]any{}},
|
|
Downstream: []string{"d_0"},
|
|
Upstream: []string{"a_0"},
|
|
},
|
|
"d_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Message", Params: map[string]any{}},
|
|
Downstream: []string{},
|
|
Upstream: []string{"b_0", "c_0"},
|
|
},
|
|
},
|
|
Path: []string{"begin_0", "a_0", "b_0", "c_0", "d_0"},
|
|
}
|
|
|
|
cc, err := Compile(context.Background(), c)
|
|
if err != nil {
|
|
t.Fatalf("Compile diamond: %v", err)
|
|
}
|
|
if cc.Workflow == nil {
|
|
t.Fatal("nil compiled diamond workflow")
|
|
}
|
|
}
|
|
|
|
// TestBuildWorkflow_MultiTerminalSucceeds verifies that canvases with
|
|
// more than one terminal component still compile cleanly. The scheduler
|
|
// normalizes multiple terminal outputs through an internal merge node so
|
|
// eino's END node only sees one mapped input.
|
|
func TestBuildWorkflow_MultiTerminalSucceeds(t *testing.T) {
|
|
c := &Canvas{
|
|
Components: map[string]CanvasComponent{
|
|
"begin_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Begin", Params: map[string]any{}},
|
|
Downstream: []string{"a_0"},
|
|
Upstream: []string{},
|
|
},
|
|
"a_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Categorize", Params: map[string]any{}},
|
|
Downstream: []string{"b_0", "c_0"},
|
|
Upstream: []string{"begin_0"},
|
|
},
|
|
"b_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Message", Params: map[string]any{}},
|
|
Downstream: []string{},
|
|
Upstream: []string{"a_0"},
|
|
},
|
|
"c_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Message", Params: map[string]any{}},
|
|
Downstream: []string{},
|
|
Upstream: []string{"a_0"},
|
|
},
|
|
},
|
|
Path: []string{"begin_0", "a_0", "b_0", "c_0"},
|
|
}
|
|
|
|
cc, err := Compile(context.Background(), c)
|
|
if err != nil {
|
|
t.Fatalf("Compile multi-terminal canvas: %v", err)
|
|
}
|
|
if cc.Workflow == nil {
|
|
t.Fatal("nil compiled multi-terminal workflow")
|
|
}
|
|
}
|
|
|
|
func TestBuildWorkflow_ParallelGroupWithOuterFollowerSucceeds(t *testing.T) {
|
|
c := &Canvas{
|
|
Components: map[string]CanvasComponent{
|
|
"begin": {
|
|
Obj: CanvasComponentObj{ComponentName: "Begin", Params: map[string]any{}},
|
|
Downstream: []string{"split"},
|
|
},
|
|
"split": {
|
|
Obj: CanvasComponentObj{
|
|
ComponentName: "StringTransform",
|
|
Params: map[string]any{
|
|
"method": "split",
|
|
"split_ref": "sys.query",
|
|
"delimiters": []any{","},
|
|
},
|
|
},
|
|
Downstream: []string{"parallel"},
|
|
Upstream: []string{"begin"},
|
|
},
|
|
"parallel": {
|
|
Obj: CanvasComponentObj{
|
|
ComponentName: "Parallel",
|
|
Params: map[string]any{
|
|
"items_ref": "split@result",
|
|
"outputs": map[string]any{
|
|
"lines": map[string]any{"ref": "fmt@result"},
|
|
},
|
|
},
|
|
},
|
|
Downstream: []string{"done"},
|
|
Upstream: []string{"split"},
|
|
},
|
|
"iter_start": {
|
|
Obj: CanvasComponentObj{ComponentName: "IterationItem", Params: map[string]any{}},
|
|
Downstream: []string{"fmt"},
|
|
Upstream: []string{"parallel"},
|
|
},
|
|
"fmt": {
|
|
Obj: CanvasComponentObj{
|
|
ComponentName: "StringTransform",
|
|
Params: map[string]any{
|
|
"method": "merge",
|
|
"script": "{{item}}",
|
|
"delimiters": []any{"|"},
|
|
},
|
|
},
|
|
Upstream: []string{"iter_start"},
|
|
},
|
|
"done": {
|
|
Obj: CanvasComponentObj{ComponentName: "Message", Params: map[string]any{"content": []any{"{parallel@lines}"}}},
|
|
Upstream: []string{"parallel"},
|
|
},
|
|
},
|
|
NodeParents: map[string]string{
|
|
"iter_start": "parallel",
|
|
"fmt": "parallel",
|
|
},
|
|
}
|
|
|
|
cc, err := Compile(context.Background(), c)
|
|
if err != nil {
|
|
t.Fatalf("Compile parallel canvas: %v", err)
|
|
}
|
|
if cc.Workflow == nil {
|
|
t.Fatal("nil compiled parallel workflow")
|
|
}
|
|
}
|
|
|
|
// TestBuildWorkflow_ErrorsOnUnknownUpstream covers the "edge to unknown
|
|
// cpn" guard — a DSL bug should fail at compile-time, not silently skip.
|
|
func TestBuildWorkflow_ErrorsOnUnknownUpstream(t *testing.T) {
|
|
c := &Canvas{
|
|
Components: map[string]CanvasComponent{
|
|
"begin_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Begin", Params: map[string]any{}},
|
|
Downstream: []string{"message_0"},
|
|
Upstream: []string{},
|
|
},
|
|
"message_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "Message", Params: map[string]any{}},
|
|
Downstream: []string{},
|
|
Upstream: []string{"unknown_0"}, // <-- bad
|
|
},
|
|
},
|
|
}
|
|
_, err := BuildWorkflow(context.Background(), c)
|
|
if err == nil {
|
|
t.Fatal("expected error for unknown upstream")
|
|
}
|
|
if !strings.Contains(err.Error(), "unknown upstream") {
|
|
t.Fatalf("expected 'unknown upstream' in error, got: %v", err)
|
|
}
|
|
}
|
|
|
|
// TestBuildWorkflow_ErrorsOnSelfEdge catches the simplest DSL mistake.
|
|
func TestBuildWorkflow_ErrorsOnSelfEdge(t *testing.T) {
|
|
c := &Canvas{
|
|
Components: map[string]CanvasComponent{
|
|
"a_0": {
|
|
Obj: CanvasComponentObj{ComponentName: "LLM", Params: map[string]any{}},
|
|
Downstream: []string{},
|
|
Upstream: []string{"a_0"}, // <-- self
|
|
},
|
|
},
|
|
}
|
|
_, err := BuildWorkflow(context.Background(), c)
|
|
if err == nil {
|
|
t.Fatal("expected error for self-edge")
|
|
}
|
|
if !strings.Contains(err.Error(), "self-edge") {
|
|
t.Fatalf("expected 'self-edge' in error, got: %v", err)
|
|
}
|
|
}
|