mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-06-04 13:30:32 +08:00
Adds the structured-output and agent-help surface plus root-level signal
handling so AI agents (and humans working through pipes) get a stable
wire contract.
* --format text|json|ndjson flag, registered per-command on outputs that
need it; default text on TTY, json on pipe. --jq <expr> pairs with json
/ ndjson to filter or project. FormatOptions absorbs JQ; WantsJSON()
helper for the JSON dispatch.
* WriteNDJSON helper in internal/format/ (per ndjson.org: one JSON value
per line, arrays split element-per-line, empty slice → zero bytes).
* chat / agent invoke wire --format ndjson via SDK StreamResponse /
AgentStreamResponse 1:1 passthrough. Both commands detect ctx.Cancelled
in every stream + session-create path and emit a stable
"operation.cancelled" code on Ctrl-C / SIGTERM.
* main.go wires signal.NotifyContext(SIGINT, SIGTERM) into the root
context so long-running commands run their cancellation cleanup
(re-emit auto-created session id, etc); the process exits 130 when
the context was signal-cancelled, matching Unix convention.
* MCP chat / agent_invoke output schemas extended with thinking /
tool_calls / assistant_message_id (server-side accumulated; MCP
tools/call has no standard partial-response). doc_view and doc_download
now use doc_id (not knowledge_id) so agents see a single id naming
convention across all tools — matches the chunk_list / search_chunks
schemas and the CLI's <doc-id> positional.
* SetAgentHelp(cmd, AgentHelp{...}) — opt-in machine-friendly --help
payload activated by WEKNORA_AGENT_HELP=1. Applied to chat / kb list.
* kb create --storage-provider <local|minio|cos|tos|s3|oss|ks3> — sets
the new KB's storage_provider_config.provider at creation time (server
does not expose it on update). Required on self-hosted deployments
where the server-side default doesn't pre-populate a provider —
without it, subsequent doc upload returns a misleading "kb not found".
38 lines
1.4 KiB
Go
38 lines
1.4 KiB
Go
// Package client uses an opt-in slog logger for SDK-internal trace output.
|
|
// Default behavior writes to io.Discard so SDK consumers (CLI, server) never
|
|
// see SDK trace output on stdout/stderr. Embedders enable debug output by
|
|
// calling SetDebugLevel("debug") at startup.
|
|
package client
|
|
|
|
import (
|
|
"io"
|
|
"log/slog"
|
|
"os"
|
|
"strings"
|
|
)
|
|
|
|
var debugLogger = slog.New(slog.NewTextHandler(io.Discard, nil))
|
|
|
|
// SetDebugLevel replaces the SDK's internal debug logger so callers can
|
|
// programmatically control SDK trace output (e.g., the CLI's --log-level
|
|
// flag). Accepted levels: "debug" / "info" / "warn" / "error" (case-
|
|
// insensitive); any other value (including "") disables output entirely
|
|
// (writes to io.Discard).
|
|
//
|
|
// Not safe for concurrent use while SDK calls are in flight — call once
|
|
// at startup before any client method is invoked.
|
|
func SetDebugLevel(level string) {
|
|
switch strings.ToLower(level) {
|
|
case "debug":
|
|
debugLogger = slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelDebug}))
|
|
case "info":
|
|
debugLogger = slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelInfo}))
|
|
case "warn":
|
|
debugLogger = slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelWarn}))
|
|
default:
|
|
// "error" or unrecognized → silent. SDK only emits Debug calls today,
|
|
// so error-level discards everything in practice.
|
|
debugLogger = slog.New(slog.NewTextHandler(io.Discard, nil))
|
|
}
|
|
}
|