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.
144 lines
5.4 KiB
Go
144 lines
5.4 KiB
Go
package messagecmd
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"text/tabwriter"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
|
|
"github.com/Tencent/WeKnora/cli/internal/iostreams"
|
|
"github.com/Tencent/WeKnora/cli/internal/output"
|
|
"github.com/Tencent/WeKnora/cli/internal/text"
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
// messageSearchFields enumerates the projectable fields of MessageSearchGroupItem.
|
|
var messageSearchFields = []string{
|
|
"request_id", "session_id", "session_title", "query_content",
|
|
"answer_content", "score", "match_type", "created_at",
|
|
}
|
|
|
|
// messageSearchModes is the closed set the server accepts for --mode, sourced
|
|
// from the SDK enumerator so it can't drift from the server vocabulary.
|
|
var messageSearchModes = cmdutil.EnumStrings(sdk.AllMessageSearchModes())
|
|
|
|
// SearchOptions holds the parsed flag values for `message search`.
|
|
type SearchOptions struct {
|
|
Query string
|
|
Mode string // server-defined search mode, passed through verbatim
|
|
Limit int
|
|
SessionIDs []string
|
|
}
|
|
|
|
// SearchService is the narrow SDK surface this command depends on.
|
|
type SearchService interface {
|
|
SearchMessages(ctx context.Context, req *sdk.SearchMessagesRequest) (*sdk.MessageSearchResult, error)
|
|
}
|
|
|
|
// NewCmdSearch builds `weknora message search "<query>"`.
|
|
func NewCmdSearch(f *cmdutil.Factory) *cobra.Command {
|
|
opts := &SearchOptions{}
|
|
cmd := &cobra.Command{
|
|
Use: `search "<query>"`,
|
|
Short: "Search chat history across sessions (question/answer pairs)",
|
|
Args: cobra.ExactArgs(1),
|
|
RunE: func(c *cobra.Command, args []string) error {
|
|
fopts, err := cmdutil.CheckFormatFlag(c)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
fopts.ResolveDefault(iostreams.IO.IsStdoutTTY())
|
|
opts.Query = args[0]
|
|
// Validate static input (--limit / --mode) before building the
|
|
// client so a bad value returns input.invalid_argument (exit 5)
|
|
// instead of an auth error (exit 3) when the profile is
|
|
// unconfigured — an agent must see the real, fixable problem.
|
|
if err := validateSearchOpts(opts); err != nil {
|
|
return err
|
|
}
|
|
cli, err := f.Client()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return runSearch(c.Context(), opts, fopts, cli)
|
|
},
|
|
}
|
|
cmd.Flags().IntVarP(&opts.Limit, "limit", "L", 20, "Maximum results to return — server-side limit (1..1000; default 20 mirrors the server default)")
|
|
cmd.Flags().StringVar(&opts.Mode, "mode", "", "Search mode: keyword | vector | hybrid (omit for server default: hybrid)")
|
|
cmd.Flags().StringArrayVar(&opts.SessionIDs, "session", nil, "Restrict search to these session ids (repeatable)")
|
|
cmdutil.AddFormatFlag(cmd, messageSearchFields...)
|
|
cmdutil.SetAgentHelp(cmd, cmdutil.AgentHelp{
|
|
UsedFor: "Search past Q&A pairs across chat history. This searches conversation messages — for RAG retrieval over documents use `weknora search chunks` instead.",
|
|
RequiredFlags: []string{"<query> (positional)"},
|
|
Examples: []string{
|
|
`weknora message search "deploy steps"`,
|
|
`weknora message search "deploy steps" --session sess_abc --limit 5`,
|
|
},
|
|
Output: "envelope.data is an array of grouped results (request_id, session_id, query_content, answer_content, score); meta.count is the returned count, meta.total_count is the server-side total. --mode accepts keyword | vector | hybrid (server default: hybrid)",
|
|
})
|
|
return cmd
|
|
}
|
|
|
|
// validateSearchOpts checks --limit / --mode and normalizes --mode to the
|
|
// canonical form. Called from RunE before the client is built (so bad input
|
|
// surfaces as exit 5, not an auth error) and again at the top of runSearch
|
|
// for direct callers; it is idempotent.
|
|
func validateSearchOpts(opts *SearchOptions) error {
|
|
// 1..1000 mirrors `search chunks` (the sibling search command); the
|
|
// server itself does not cap limit (handler passes it through).
|
|
if opts.Limit < 1 || opts.Limit > 1000 {
|
|
return &cmdutil.Error{
|
|
Code: cmdutil.CodeInputInvalidArgument,
|
|
Message: fmt.Sprintf("--limit must be in 1..1000, got %d", opts.Limit),
|
|
}
|
|
}
|
|
// Validate --mode against the closed server enum and normalize to the
|
|
// canonical (lowercase) form the server matches. An unrecognised mode
|
|
// matches no channel server-side and returns an empty set with no error —
|
|
// which an agent cannot tell apart from a genuine no-match — so reject it.
|
|
mode, err := cmdutil.ValidateEnum("mode", opts.Mode, messageSearchModes)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
opts.Mode = mode
|
|
return nil
|
|
}
|
|
|
|
func runSearch(ctx context.Context, opts *SearchOptions, fopts *cmdutil.FormatOptions, svc SearchService) error {
|
|
if err := validateSearchOpts(opts); err != nil {
|
|
return err
|
|
}
|
|
res, err := svc.SearchMessages(ctx, &sdk.SearchMessagesRequest{
|
|
Query: opts.Query,
|
|
Mode: opts.Mode,
|
|
Limit: opts.Limit,
|
|
SessionIDs: opts.SessionIDs,
|
|
})
|
|
if err != nil {
|
|
return cmdutil.WrapHTTP(err, "search messages")
|
|
}
|
|
if res == nil {
|
|
res = &sdk.MessageSearchResult{}
|
|
}
|
|
items := res.Items
|
|
if items == nil {
|
|
items = []*sdk.MessageSearchGroupItem{}
|
|
}
|
|
if fopts.WantsJSON() {
|
|
meta := &output.Meta{Count: output.IntPtr(len(items)), TotalCount: output.IntPtr(res.Total)}
|
|
return fopts.Emit(iostreams.IO.Out, items, meta)
|
|
}
|
|
if len(items) == 0 {
|
|
fmt.Fprintln(iostreams.IO.Out, "(no matches)")
|
|
return nil
|
|
}
|
|
tw := tabwriter.NewWriter(iostreams.IO.Out, 0, 0, 2, ' ', 0)
|
|
fmt.Fprintln(tw, "SESSION ID\tQUERY\tANSWER\tSCORE")
|
|
for _, it := range items {
|
|
fmt.Fprintf(tw, "%s\t%s\t%s\t%.2f\n", it.SessionID, text.OneLine(40, it.QueryContent), text.OneLine(40, it.AnswerContent), it.Score)
|
|
}
|
|
return tw.Flush()
|
|
}
|