feat(cli)!: v0.10 reliability, agent-UX, and command-surface hardening

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.
This commit is contained in:
nullkey
2026-07-02 15:53:51 +08:00
committed by lyingbug
parent 040a734766
commit d3c03b2f34
95 changed files with 1711 additions and 436 deletions
+28 -5
View File
@@ -9,6 +9,7 @@ import (
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
"github.com/Tencent/WeKnora/cli/internal/iostreams"
"github.com/Tencent/WeKnora/cli/internal/output"
sdk "github.com/Tencent/WeKnora/client"
)
@@ -29,6 +30,7 @@ type CreateOptions struct {
Name string
Description string
EmbeddingModel string
ChatModel string
StorageProvider string
DryRun bool
}
@@ -84,16 +86,23 @@ func NewCmdCreate(f *cmdutil.Factory) *cobra.Command {
}
// --embedding-model accepts a model id or name (a UUID passes
// through; a name resolves among Embedding models). Configuring a
// KB's models fully is `weknora kb init`; this just pre-sets the
// KB's models fully is `weknora kb config set`; this just pre-sets the
// embedding model at creation.
if opts.EmbeddingModel, err = cmdutil.ResolveModelRef(c.Context(), cli, opts.EmbeddingModel, "Embedding"); err != nil {
return err
}
// --chat-model (id or name) pre-sets the KB's LLM at creation, so a
// KB can be born retrieval-ready in one step. Full model config
// (rerank / multimodal) is still `weknora kb config set`.
if opts.ChatModel, err = cmdutil.ResolveModelRef(c.Context(), cli, opts.ChatModel, "KnowledgeQA"); err != nil {
return err
}
return runCreate(c.Context(), opts, fopts, cli)
},
}
cmd.Flags().StringVar(&opts.Description, "description", "", "Knowledge base description (optional)")
cmd.Flags().StringVar(&opts.EmbeddingModel, "embedding-model", "", "Embedding model id or name (optional; configure models fully with `weknora kb init`)")
cmd.Flags().StringVar(&opts.EmbeddingModel, "embedding-model", "", "Embedding model id or name (optional; makes the KB retrieval-ready at creation)")
cmd.Flags().StringVar(&opts.ChatModel, "chat-model", "", "Chat/LLM model id or name (optional; pre-set the KB's answer model at creation)")
cmd.Flags().StringVar(&opts.StorageProvider, "storage-provider", "",
"Storage provider for documents in this KB: "+strings.Join(storageProviderValues, " | ")+" (optional; server default when unset)")
cmdutil.AddFormatFlag(cmd, kbCreateFields...)
@@ -103,10 +112,10 @@ func NewCmdCreate(f *cmdutil.Factory) *cobra.Command {
RequiredFlags: []string{"<name> (positional)"},
Examples: []string{
`weknora kb create "Eng Docs"`,
`weknora kb create "Eng Docs" --description "engineering knowledge base"`,
`weknora kb create "Eng Docs" --embedding-model text-embedding-3-small --chat-model gpt-4o-mini # retrieval-ready in one step`,
`weknora kb create "Eng Docs" --jq .data.id # capture id to chain into doc upload --kb`,
},
Output: "envelope.data is the created KnowledgeBase object with id, name, type, embedding_model_id",
Output: "envelope.data is the created KnowledgeBase object with id, name, type, embedding_model_id, summary_model_id",
})
return cmd
}
@@ -125,6 +134,9 @@ func runCreate(ctx context.Context, opts *CreateOptions, fopts *cmdutil.FormatOp
if opts.EmbeddingModel != "" {
req.EmbeddingModelID = opts.EmbeddingModel
}
if opts.ChatModel != "" {
req.SummaryModelID = opts.ChatModel
}
if opts.StorageProvider != "" {
canonSP, err := cmdutil.ValidateEnum("storage-provider", opts.StorageProvider, storageProviderValues)
if err != nil {
@@ -138,9 +150,20 @@ func runCreate(ctx context.Context, opts *CreateOptions, fopts *cmdutil.FormatOp
return cmdutil.WrapHTTP(err, "create knowledge base")
}
// A KB with no embedding model can hold documents but never index/retrieve
// them — surface the next step at the point of creation instead of leaving
// the agent to discover a silent-draft KB via a later empty search.
var meta *output.Meta
if created.EmbeddingModelID == "" {
meta = &output.Meta{Hint: "retrieval_ready=false: no embedding model bound. Uploaded docs will not be searchable until you run `weknora kb config set " + created.ID + " --embedding-model <id> --chat-model <id>` (create the KB with --embedding-model/--chat-model to skip this step)."}
}
if fopts.WantsJSON() {
return fopts.Emit(iostreams.IO.Out, created, nil)
return fopts.Emit(iostreams.IO.Out, created, meta)
}
fmt.Fprintf(iostreams.IO.Out, "✓ Created knowledge base %q (id: %s)\n", created.Name, created.ID)
if meta != nil {
fmt.Fprintf(iostreams.IO.Out, "⚠ %s\n", meta.Hint)
}
return nil
}