6f8b825f5f
The `weknora` command-line client for the WeKnora RAG server. Full command surface: kb / doc / chunk / session / message / agent / model / search / chat / auth / profile / link / api / mcp / skills / config / doctor / schema / exit-codes. Agent-first wire contract: JSON envelope by default, typed error codes mapped to stable exit codes, error.retry_argv / retryable / partial-failure status, global --dry-run preview, the exit-10 confirmation protocol for writes, and control/ANSI/Bidi input hygiene. Stateless env-credential auth (WEKNORA_API_KEY / WEKNORA_TOKEN + WEKNORA_HOST) for headless/CI/agent use. A curated read-only MCP tool surface (`mcp serve`) and embedded Agent Skills (`skills install`). Extensive unit + contract-golden tests and CI.
103 lines
4.1 KiB
Go
103 lines
4.1 KiB
Go
// Package sse provides helpers for consuming server-sent event streams from
|
|
// the WeKnora SDK (KnowledgeQAStream, ContinueStream).
|
|
//
|
|
// Accumulator is the canonical sink: every callback event appends to a
|
|
// buffered Content string and updates terminal-state fields like References
|
|
// and SessionID. The non-streaming JSON mode reads .Result() once .Done()
|
|
// is true; streaming mode writes Content tokens directly to stdout and
|
|
// only consults the accumulator for the final References footer.
|
|
package sse
|
|
|
|
import (
|
|
"errors"
|
|
"strings"
|
|
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
// ErrTerminate is the sentinel a stream callback returns to stop consuming the
|
|
// stream immediately after a terminal error frame (response_type=error). The
|
|
// server holds the SSE connection open after such a frame, so a callback that
|
|
// keeps returning nil blocks the SDK read until a ~30s transport timeout —
|
|
// turning a sub-second server error into a 30s hang for the (agent) caller.
|
|
// Callers derive the real result from the captured error message / accumulator
|
|
// and unwrap this sentinel (errors.Is) to a clean stop.
|
|
var ErrTerminate = errors.New("sse: stream terminated by terminal error event")
|
|
|
|
// Accumulator buffers a KnowledgeQAStream callback sequence.
|
|
//
|
|
// Zero value is ready to use. Not safe for concurrent Append calls - the SDK
|
|
// invokes its callback sequentially on a single goroutine, so this matches
|
|
// the only contract that exists today.
|
|
//
|
|
// Demuxes by ResponseType so the answer string is not polluted by thinking
|
|
// or reflection fragments - the model layer (internal/models/chat/
|
|
// remote_api.go) emits ResponseTypeThinking events whenever the upstream
|
|
// LLM produces reasoning_content frames, and without demux those would
|
|
// be silently concatenated into Result().
|
|
type Accumulator struct {
|
|
answer strings.Builder
|
|
thinking strings.Builder
|
|
References []*sdk.SearchResult
|
|
SessionID string
|
|
AssistantMessageID string
|
|
finished bool
|
|
}
|
|
|
|
// Append consumes one StreamResponse event. Safe to call multiple times;
|
|
// idempotent post-Done so callers do not need to special-case late events.
|
|
func (a *Accumulator) Append(r *sdk.StreamResponse) {
|
|
if r == nil || a.finished {
|
|
return
|
|
}
|
|
switch r.ResponseType {
|
|
case sdk.ResponseTypeAnswer:
|
|
if r.Content != "" {
|
|
a.answer.WriteString(r.Content)
|
|
}
|
|
case sdk.ResponseTypeThinking, sdk.ResponseTypeReflection:
|
|
if r.Content != "" {
|
|
a.thinking.WriteString(r.Content)
|
|
}
|
|
default:
|
|
// Frames without a typed ResponseType (legacy / metadata-only
|
|
// payloads) that still carry an answer fragment fall through here.
|
|
// Preserve the legacy contract by treating untyped Content as
|
|
// answer text.
|
|
if r.ResponseType == "" && r.Content != "" {
|
|
a.answer.WriteString(r.Content)
|
|
}
|
|
}
|
|
if r.SessionID != "" && a.SessionID == "" {
|
|
a.SessionID = r.SessionID
|
|
}
|
|
if r.AssistantMessageID != "" && a.AssistantMessageID == "" {
|
|
a.AssistantMessageID = r.AssistantMessageID
|
|
}
|
|
// Capture references whenever they arrive - they may land on a
|
|
// dedicated `references` event before the terminal `complete`.
|
|
if r.KnowledgeReferences != nil {
|
|
a.References = r.KnowledgeReferences
|
|
}
|
|
// Stream is only truly done on response_type=complete. Other events
|
|
// (notably the leading agent_query metadata frame) carry done=true to
|
|
// mark their own per-event completion, but the answer fragments arrive
|
|
// in subsequent response_type=answer events. Gating on response_type
|
|
// avoids the off-by-one termination that would discard the entire
|
|
// answer.
|
|
if r.ResponseType == sdk.ResponseTypeComplete {
|
|
a.finished = true
|
|
}
|
|
}
|
|
|
|
// Done reports whether a terminal event was observed.
|
|
func (a *Accumulator) Done() bool { return a.finished }
|
|
|
|
// Result returns the accumulated answer-event content.
|
|
func (a *Accumulator) Result() string { return a.answer.String() }
|
|
|
|
// Thinking returns the accumulated reasoning / reflection content surfaced
|
|
// by the upstream LLM (only populated when the active model produces
|
|
// reasoning_content). Empty for non-reasoning models.
|
|
func (a *Accumulator) Thinking() string { return a.thinking.String() }
|