d3c03b2f34
A hardening + finalization pass over the agent-first CLI: correctness fixes,
richer machine-readable signals, flag/naming consistency, and a symmetric
config surface. Pre-1.0, so it includes breaking renames.
Correctness:
- agent update: resolve/validate --model/--rerank-model (was storing a bogus
name verbatim, corrupting config.model_id).
- doctor: honor WEKNORA_HOST / WEKNORA_API_KEY (headless path no longer reports
"no host configured").
- session ask / MCP session_ask: text answer was empty on non-TTY — the agent
stream sets Done=true on an intermediate agent_query frame before the answer,
and AgentAccumulator treated the first Done as terminal. Terminate on the
`complete` event (new sdk.AgentResponseTypeComplete), not a per-frame Done.
- batch exit codes: any per-item failure collapses to operation.failed (exit 1),
including `doc upload --recursive` partial failures — a permanent per-file
failure (e.g. a duplicate) no longer surfaces as a retryable exit 7 an agent
would loop on; per-item typed errors stay in the envelope.
Agent-first signals & discovery:
- error.exit_code in the envelope (type + exit_code disambiguate the
input.invalid_argument exit-2-vs-5 split in one JSON read).
- meta.hint on empty content search and on draft doc create; doc wait fails fast
on a never-parsing draft instead of hanging to --timeout.
- retrieval-readiness is visible in the natural flow: kb status / kb check emit
retrieval_ready, and kb create hints the fix when no embedding model is bound
— an unconfigured KB no longer looks silently healthy.
- schema contract completeness: every leaf declares output + >=1 example
(drift-guarded); output strings match the meta actually emitted; chunk list
and search docs now emit meta.total_count (both previously dropped it).
- schema tolerates a quoted multi-word command label; zero-state auth — and
`link` with no profile — point at profile setup / the headless WEKNORA_KB_ID
path instead of looping on `auth login`.
- id-addressed reads tolerate a redundant --kb (doc view/wait, chunk list/view
accept and ignore it, declared in schema) so a carried-over --kb doesn't
exit 2; streaming commands warn that --jq does not apply to an NDJSON stream.
- keep JSON-always as the default; --jq hints spell out the .data path.
Consistency & gating:
- doc create: drop the deprecated --name alias (--title only; pre-1.0 break).
- chunk list --limit aligned to 1..10000; model list --limit/-L with
has_more/total_count; api write-gates -X PUT/PATCH (exit 10); skills install
expands a leading ~.
- docs corrected: search docs / doc list --keyword help is case-insensitive
(server does LOWER LIKE); AGENTS.md risk-action list (no phantom kb.init; add
model.update / kb.config.set) and batch example (failed item carries `error`);
session resume --message id comes from `message list`, not the stream.
- auth/profile ergonomics: env credentials are now first-class — `auth token`
prints the active WEKNORA_API_KEY / WEKNORA_TOKEN, and auth login/logout/refresh
give an env-aware message instead of looping on "run auth login". `auth logout`
clears credentials but keeps the profile registered (host preserved for
re-login); deleting a profile is `profile remove`'s job (clean logout/remove
separation, matching gh / lark).
Config surface (symmetric read/write, in-place model edits):
- kb config now returns a secret-free KBModelConfigView (was {}); `kb config`
reads, new `kb config set` writes; `kb init` removed (misnomer).
- kb create --chat-model: retrieval-ready in one step.
- model update: edit a model in place (id preserved, references survive) —
rotate --api-key-stdin, change base-url / display-name / etc.
- session continue-stream renamed to session resume.
Docs: AGENTS.md is the single wire-contract source; CHANGELOG slimmed; stale
kb-init / continue-stream references removed; skill wire-vocab guard extended.
AGENTS.md / weknora-shared SKILL document retrieval_ready (a KB needs an
embedding model to be searchable), that --jq does not apply to NDJSON
streams, and the env-credential-first auth path; the KB quickstart example
now creates a retrieval-ready KB.
93 lines
3.5 KiB
Go
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() }
|