mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-11-02 05:03:00 +08:00
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.
119 lines
4.5 KiB
Go
119 lines
4.5 KiB
Go
// stop.go implements `weknora session stop` — cancel server-side generation
|
|
// for a specific assistant message under a known session.
|
|
//
|
|
// Unlike Ctrl-C (which only drops the local connection while the server keeps
|
|
// generating and billing tokens), this tells the server to stop.
|
|
//
|
|
// This is the symmetric counterpart to `session resume`: both key on
|
|
// (session_id, message_id). The message_id comes from the init event of the
|
|
// original chat / session ask / resume stream.
|
|
package sessioncmd
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
|
|
"github.com/Tencent/WeKnora/cli/internal/iostreams"
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
var stopFields = []string{"session_id", "message_id", "stopped"}
|
|
|
|
// StopOptions captures `session stop` flag/arg state.
|
|
type StopOptions struct {
|
|
SessionID string
|
|
MessageID string
|
|
DryRun bool
|
|
}
|
|
|
|
// StopService is the narrow SDK surface this command depends on.
|
|
// *sdk.Client satisfies it; tests substitute a fake. Compile-time check
|
|
// at the bottom of this file.
|
|
type StopService interface {
|
|
StopSession(ctx context.Context, sessionID, messageID string) error
|
|
}
|
|
|
|
type stopResult struct {
|
|
SessionID string `json:"session_id"`
|
|
MessageID string `json:"message_id"`
|
|
Stopped bool `json:"stopped"`
|
|
}
|
|
|
|
// NewCmdStop builds `weknora session stop <session-id> --message <id>`.
|
|
func NewCmdStop(f *cmdutil.Factory) *cobra.Command {
|
|
opts := &StopOptions{}
|
|
cmd := &cobra.Command{
|
|
Use: "stop <session-id>",
|
|
Short: "Stop in-flight generation for an assistant message in a session",
|
|
Long: `Cancel server-side generation for a specific assistant message under a
|
|
session. Unlike Ctrl-C (which only drops the local connection while the server
|
|
keeps generating and billing tokens), this tells the server to stop.
|
|
|
|
Symmetric with 'session resume': both key on (session_id, message_id).`,
|
|
Example: ` weknora session stop sess_xyz --message msg_abc`,
|
|
Args: cobra.ExactArgs(1),
|
|
RunE: func(c *cobra.Command, args []string) error {
|
|
opts.SessionID = args[0]
|
|
fopts, err := cmdutil.CheckFormatFlag(c)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
fopts.ResolveDefault(iostreams.IO.IsStdoutTTY())
|
|
if handled, err := cmdutil.HandleDryRun(c, opts.DryRun, cmdutil.DryRunPlan{
|
|
Action: "session.stop",
|
|
Args: map[string]any{"session": opts.SessionID, "message": opts.MessageID},
|
|
}); handled {
|
|
return err
|
|
}
|
|
cli, err := f.Client()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return runStop(c.Context(), opts, fopts, cli)
|
|
},
|
|
}
|
|
cmd.Flags().StringVarP(&opts.MessageID, "message", "m", "",
|
|
"Assistant message id to stop (from the init event of the stream you're stopping)")
|
|
_ = cmd.MarkFlagRequired("message")
|
|
cmdutil.AddFormatFlag(cmd, stopFields...)
|
|
cmdutil.AddDryRunFlag(cmd, &opts.DryRun)
|
|
cmdutil.SetAgentHelp(cmd, cmdutil.AgentHelp{
|
|
UsedFor: "Stop server-side generation for an in-flight assistant message (counterpart to resume). The message_id comes from the init event of the chat / session ask / resume stream you're stopping.",
|
|
RequiredFlags: []string{"<session-id> (positional)", "--message (message_id from the init event of the stream you're stopping)"},
|
|
Examples: []string{"weknora session stop sess_xyz --message msg_abc"},
|
|
Output: "envelope {session_id, message_id, stopped:true}",
|
|
})
|
|
return cmd
|
|
}
|
|
|
|
// runStop is the testable core: validate, dispatch the stop, and emit the
|
|
// result envelope. Returns a typed error.
|
|
func runStop(ctx context.Context, opts *StopOptions, fopts *cmdutil.FormatOptions, svc StopService) error {
|
|
if opts.SessionID == "" {
|
|
return cmdutil.NewError(cmdutil.CodeInputInvalidArgument, "session-id argument cannot be empty")
|
|
}
|
|
if opts.MessageID == "" {
|
|
return cmdutil.NewError(cmdutil.CodeInputInvalidArgument, "--message cannot be empty")
|
|
}
|
|
if svc == nil {
|
|
return cmdutil.NewError(cmdutil.CodeServerError, "session stop: no SDK client available")
|
|
}
|
|
if err := svc.StopSession(ctx, opts.SessionID, opts.MessageID); err != nil {
|
|
if cmdutil.IsCancelled(ctx, err) {
|
|
return cmdutil.Wrapf(cmdutil.CodeOperationCancelled, err, "session stop cancelled")
|
|
}
|
|
return cmdutil.WrapHTTP(err, "stop session")
|
|
}
|
|
if fopts.WantsJSON() {
|
|
return fopts.Emit(iostreams.IO.Out, stopResult{SessionID: opts.SessionID, MessageID: opts.MessageID, Stopped: true}, nil)
|
|
}
|
|
fmt.Fprintf(iostreams.IO.Out, "✓ Stopped generation for message %s\n", opts.MessageID)
|
|
return nil
|
|
}
|
|
|
|
// compile-time check: production SDK client satisfies StopService.
|
|
var _ StopService = (*sdk.Client)(nil)
|