mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-09-01 14:53:07 +08:00
nullkey
da9faa9e07
Borrows the lark-cli agent-affordance model (https://github.com/larksuite/cli/blob/main/AGENTS.md + skills/lark-shared/SKILL.md) so weknora is designed to be agent-friendly: error messages, output format, and flag design follow conventions agents can rely on. cli/AGENTS.md (operational reference for LLM agents invoking weknora): Public document covering envelope schema, exit-code protocol (0/1/2/10/130), stdout/stderr separation, and behavioral rules. Sensitive commands (\`context use\`, \`kb delete\`, \`doc delete\`, \`init\`) gain "AI agents:" paragraphs in their cobra Long descriptions so guidance shows in --help. format.Envelope schema additions: Risk per-operation classification (read / write / high-risk-write + action description), populated by write commands on both success and failure paths. Notice system advisories (CLI update available, server-CLI version skew); type defined, emit sites land in v0.3. DryRun marker for envelopes returned from --dry-run preview paths. RiskLevel constants realigned to lark's taxonomy: read / write / high-risk-write (was: read / mutating / destructive — not yet wired by any command). cmdutil.Error gains OperationRisk; PrintErrorEnvelope auto-attaches it to envelope.Risk so destructive failure paths surface uniformly. Exit-10 confirmation protocol: New ErrorCode \`input.confirmation_required\` mapped to exit code 10 in cmdutil.ExitCode. ConfirmDestructive now returns this code (with OperationRisk attached) when stdout is non-TTY or --json was set, with -y/--yes absent. Previous behavior — silent proceed in non-TTY — was unsafe: scripts and agents could delete resources with no explicit approval. Three test cases re-pinned around the new contract. This is a wire-contract change for any caller who relied on silent proceed; v0.0/v0.1 had no destructive commands, so the blast radius is contained to v0.2 itself. --dry-run global flag: cmd write paths (kb create/delete, doc upload/delete, api POST/PUT/PATCH/ DELETE) check cmdutil.IsDryRun(cmd) and skip the SDK call, emitting an envelope with dry_run=true plus a Risk classification. Read commands ignore --dry-run by design (no side effect to preview). Human-mode prints \`[dry-run] would <action>\` to stdout. Command discovery: agents introspect via the existing \`--help\` surface (consistent with gh / kubectl / aws / gcloud / terraform — none of them ship a CLI-tree self-description command). An earlier draft added a \`weknora schema\` reflection command; dropped after a mainstream survey found it has no stable analog (lark-cli's schema describes Lark API methods, not its own CLI tree). Tests: 27 cli packages pass at this commit. Added two new tests covering envelope.risk and envelope._notice serialization.
51 lines
2.0 KiB
Go
51 lines
2.0 KiB
Go
// Package agent handles AI agent integration: env-based detection (used to
|
|
// trigger AGENT-targeted help text) and per-command help annotations.
|
|
//
|
|
// v0.2 ADR-3: removed the omnibus `--agent` flag + ApplyAgentSugar
|
|
// mode-switch as over-design. Mainstream CLIs (gh / kubectl / aws / docker /
|
|
// flyctl) deliberately don't have a single mode-switch flag; per-command
|
|
// --json + TTY auto-detect cover 95% of cases. WeKnora now follows that
|
|
// convention. See cli/AGENTS.md for the full agent contract.
|
|
//
|
|
// What remains here: a small env-detect for known coding agents, used purely
|
|
// to render the AGENT-targeted help section (no behavior change). Patterned
|
|
// after Stripe's DetectAIAgent (https://github.com/stripe/stripe-cli/tree/master/pkg/useragent),
|
|
// which Stripe uses only for User-Agent telemetry tagging.
|
|
package agent
|
|
|
|
import "os"
|
|
|
|
// AIAgentName identifies the detected coding agent invoking the CLI. Empty
|
|
// string means no agent detected (or detection is disabled).
|
|
type AIAgentName string
|
|
|
|
// aiAgentEnvs maps environment variable presence to a coding agent name.
|
|
// Cropped to the entries the Stripe CLI also recognizes (verified against
|
|
// stripe-cli/pkg/useragent/useragent.go). The earlier 7-entry list (CODEX_*,
|
|
// AIDER_PROMPT, CONTINUE_GLOBAL_DIR, OPENCODE_RUNNING, GEMINICODER_PROFILE)
|
|
// did not have official agent docs backing those env names; removed in v0.2
|
|
// to avoid maintaining an unverified hardcoded list. New entries should
|
|
// document the source URL.
|
|
var aiAgentEnvs = []struct {
|
|
env string
|
|
name AIAgentName
|
|
}{
|
|
{"CLAUDECODE", "claude-code"},
|
|
{"CURSOR_AGENT", "cursor"},
|
|
}
|
|
|
|
// DetectAIAgent returns the first known agent name whose env var is set to a
|
|
// non-empty value, or "" if none are present. Detection is suppressed when
|
|
// WEKNORA_NO_AGENT_AUTODETECT is truthy. Tests substitute via t.Setenv.
|
|
func DetectAIAgent() AIAgentName {
|
|
if v := os.Getenv("WEKNORA_NO_AGENT_AUTODETECT"); v != "" && v != "0" && v != "false" {
|
|
return ""
|
|
}
|
|
for _, a := range aiAgentEnvs {
|
|
if os.Getenv(a.env) != "" {
|
|
return a.name
|
|
}
|
|
}
|
|
return ""
|
|
}
|