mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-06 19:38:36 +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>
131 lines
3.3 KiB
Go
131 lines
3.3 KiB
Go
package canvas
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"os"
|
|
"path/filepath"
|
|
"testing"
|
|
|
|
_ "ragflow/internal/agent/component" // blank import: registers factories via component.init()
|
|
dslpkg "ragflow/internal/agent/dsl"
|
|
)
|
|
|
|
// TestAllFixture_NormalizeAndCompile ensures the largest legacy fixture
|
|
// remains compilable through the runtime normalization boundary. This
|
|
// is the cross-layer regression pin for cases where `all.json` carries
|
|
// both `components` and `graph`, but a later canvas/runtime bridge
|
|
// still rejects a legacy alias or grouped-subgraph shape.
|
|
func TestAllFixture_NormalizeAndCompile(t *testing.T) {
|
|
raw, err := os.ReadFile(filepath.Join("..", "dsl", "testdata", "all.json"))
|
|
if err != nil {
|
|
t.Fatalf("read all.json: %v", err)
|
|
}
|
|
|
|
var fixture map[string]any
|
|
if err := json.Unmarshal(raw, &fixture); err != nil {
|
|
t.Fatalf("parse all.json: %v", err)
|
|
}
|
|
|
|
normalized := dslpkg.NormalizeForRun(fixture)
|
|
rawComponents, _ := normalized["components"].(map[string]any)
|
|
if len(rawComponents) == 0 {
|
|
t.Fatal("normalized all.json has no components")
|
|
}
|
|
|
|
c := &Canvas{
|
|
Components: make(map[string]CanvasComponent, len(rawComponents)),
|
|
NodeParents: make(map[string]string),
|
|
}
|
|
if path, ok := normalized["path"].([]any); ok {
|
|
c.Path = make([]string, 0, len(path))
|
|
for _, item := range path {
|
|
if s, ok := item.(string); ok {
|
|
c.Path = append(c.Path, s)
|
|
}
|
|
}
|
|
}
|
|
if globals, ok := normalized["globals"].(map[string]any); ok {
|
|
c.Globals = globals
|
|
}
|
|
if graph, ok := normalized["graph"].(map[string]any); ok {
|
|
if nodes, ok := graph["nodes"].([]any); ok {
|
|
for _, rawNode := range nodes {
|
|
node, ok := rawNode.(map[string]any)
|
|
if !ok || node == nil {
|
|
continue
|
|
}
|
|
id, _ := node["id"].(string)
|
|
parentID, _ := node["parentId"].(string)
|
|
if id != "" && parentID != "" {
|
|
c.NodeParents[id] = parentID
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
for cpnID, rawComp := range rawComponents {
|
|
comp, ok := rawComp.(map[string]any)
|
|
if !ok || comp == nil {
|
|
continue
|
|
}
|
|
name, params := extractFixtureComponentFields(comp)
|
|
if name == "" {
|
|
t.Fatalf("component %q missing component_name", cpnID)
|
|
}
|
|
if parentID, _ := comp["parent_id"].(string); parentID != "" {
|
|
c.NodeParents[cpnID] = parentID
|
|
}
|
|
c.Components[cpnID] = CanvasComponent{
|
|
Obj: CanvasComponentObj{
|
|
ComponentName: name,
|
|
Params: params,
|
|
},
|
|
Downstream: stringSliceFromAny(comp["downstream"]),
|
|
Upstream: stringSliceFromAny(comp["upstream"]),
|
|
}
|
|
}
|
|
cc, err := Compile(context.Background(), c)
|
|
if err != nil {
|
|
t.Fatalf("Compile(all.json): %v", err)
|
|
}
|
|
if cc == nil || cc.Workflow == nil {
|
|
t.Fatal("Compile(all.json) returned nil workflow")
|
|
}
|
|
}
|
|
|
|
func extractFixtureComponentFields(comp map[string]any) (name string, params map[string]any) {
|
|
if obj, ok := comp["obj"].(map[string]any); ok && obj != nil {
|
|
name, _ = obj["component_name"].(string)
|
|
if p, ok := obj["params"].(map[string]any); ok {
|
|
params = p
|
|
}
|
|
}
|
|
if name == "" {
|
|
name, _ = comp["name"].(string)
|
|
}
|
|
if params == nil {
|
|
if p, ok := comp["params"].(map[string]any); ok {
|
|
params = p
|
|
}
|
|
}
|
|
return
|
|
}
|
|
|
|
func stringSliceFromAny(v any) []string {
|
|
switch x := v.(type) {
|
|
case []string:
|
|
return x
|
|
case []any:
|
|
out := make([]string, 0, len(x))
|
|
for _, item := range x {
|
|
if s, ok := item.(string); ok {
|
|
out = append(out, s)
|
|
}
|
|
}
|
|
return out
|
|
default:
|
|
return nil
|
|
}
|
|
}
|