Files
Enterprise-Knowledge-Base/cli/internal/sse/accumulator.go
T
nullkey c87e35b34b chore(cli): polish + docs sync + pre-PR audit fixes
Code-reuse polish (post-implementation review pass):
- Extract text.OneLine(maxWidth, s) helper combining preview-row
  normalization (newline/CR/tab → space) with text.Truncate's
  UTF-8-safe truncation. Replaces agent/view.go truncate1Line (ASCII
  '...' + byte-slice CJK-unsafe) and chunk/list.go singleLine.
- Lift cmdutil.OpenInput(path) for the '-' = stdin / else os.Open
  pattern shared across agent create/edit and the api command.
  Replaces agent/create.go's private openInput.
- Strip inline doc-spec parentheticals from source comments — those
  belong in commit messages and project docs, not in source where
  they rot.

Pre-PR audit fixes:
- doc upload: reject `--metadata` paired with `--from-url` as
  input.invalid_argument up-front (the URL-ingest request type has
  no metadata field server-side, so the pair would otherwise silently
  drop). Long help and CHANGELOG updated to call out the asymmetry.
- doc upload (file path): map sdk.ErrDuplicateFile sentinel to
  resource.already_exists. The sentinel arrives with no "HTTP error <n>:"
  prefix because the SDK short-circuits on file-hash before reading the
  HTTP status, so the previous WrapHTTP fall-through misclassified it
  as network.error with a misleading "check base URL reachability" hint.
  The --from-url branch already handled ErrDuplicateURL this way; this
  closes the asymmetry. Caught by e2e re-upload of an already-ingested
  file; regression test added.
- README exit-10 enumeration adds `agent delete` and `chunk delete`
  (these were missing alongside the v0.5 destructive verbs they were
  meant to gate).

Docs sync:
- cli/README.md: command tree now includes the chunk subtree; adds
  agent / chunk lines to the 5-minute quickstart; adds a "Contributing
  / Reporting issues" section pointing at the repo's SECURITY.md and
  AGENTS.md; drops third-party CLI parallels from the surface
  description.
- cli/AGENTS.md: "Command surface design SOP" gains the
  flag-vs-escape-hatch step. "CRUD command flag canon" renamed to the
  hard-required-flags pattern with the contrast (TTY-prompts-fill)
  defined inline rather than via opaque shorthand.
- cli/CHANGELOG.md: search docs case-sensitivity shift promoted to its
  own #### Breaking changes subsection. MCP doc_list filter count
  corrected from 5 to 6. Drops the bogus go.mod yaml.v3 entry (yaml.v3
  was already a dependency on main; v0.5 added zero go.mod lines).
  Replaces internal-Go identifiers (fuzzyTime, NoOptDefVal) with
  user-language and drops the § section-symbol jargon.
2026-05-16 16:56:33 +08:00

93 lines
3.5 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 (
"strings"
sdk "github.com/Tencent/WeKnora/client"
)
// 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() }