mirror of
https://github.com/helmfile/helmfile.git
synced 2026-10-04 14:51:26 +02:00
* feat: add `helmfile doctor` command for AI-assisted diff analysis `helmfile doctor` runs `helmfile diff` and asks an OpenAI-compatible LLM to summarize the changes and flag risks (data loss, security exposure, breaking changes, downtime, performance, best-practice issues). Key design decisions: - When no LLM is configured, doctor is equivalent to `helmfile diff` with one exception: --show-secrets is always forced off (secrets never reach stdout, even without an LLM). - Secrets are ALWAYS redacted via two layers: (1) ShowSecrets() forced to false so helm-diff emits <REDACTED> placeholders; (2) a defense-in-depth text redactor strips residual secret-looking content (Secret YAML blocks, sensitive key/value lines, base64 blobs, JWT tokens) before LLM transmission. - LLM configuration precedence: env (HELMFILE_LLM_*) < helmfile.yaml (llm:) < CLI flags (--llm-*). - Supports any OpenAI-compatible backend (OpenAI, Azure, One-API, LiteLLM, Ollama, etc.) with automatic response_format fallback for backends that don't support JSON mode. - Prompt injection defense: release names and environment values are JSON-encoded before insertion into the LLM prompt. - Exit codes: 0 (success/low-risk), 2 (high-risk gate, bypass with --force), 1 (other errors). Helm-diff's 'detected changes' exit-2 is swallowed. New packages: - pkg/agent/llm: OpenAI-compatible client with JSON response parsing, mock client for testing, prompt builder with injection defense. - pkg/agent/doctor: secret redactor (state machine + regex), report renderer (markdown + JSON), config resolver (env < yaml < flag merge). Testing: 70+ unit tests covering redaction patterns, prompt injection, response_format fallback, JSON parsing, yaml roundtrip, concurrency safety, panic recovery, and error propagation. go test -race passes. Documentation: full doctor section in docs/cli.md, llm: block reference in docs/configuration.md, updated skills/helmfile for AI agents. Signed-off-by: yxxhero <aiopsclub@163.com> * docs: fix doctor equivalence wording per PR review Per review feedback (PR #2660): the docs claimed doctor is 'equivalent to helmfile diff — same flags, same output, same exit codes' in the unconfigured path, but this over-promises because: 1. doctor --output is the report format (not helm-diff's output format) 2. helm-diff's --output is exposed as --diff-output in doctor 3. --show-secrets is silently ignored Updated all three locations (cli.md, cmd/doctor.go Long + godoc, pkg/app/doctor.go godoc) to say 'falls back to helmfile diff with --show-secrets forced off' and explicitly note the --output / --diff-output flag difference. Signed-off-by: yxxhero <aiopsclub@163.com> --------- Signed-off-by: yxxhero <aiopsclub@163.com>
110 lines
3.6 KiB
Go
110 lines
3.6 KiB
Go
// Package doctor orchestrates the `helmfile doctor` flow: capture helm diff
|
|
// output, hand it to an LLM via the OpenAI-compatible Chat Completions
|
|
// protocol, then render a structured risk report.
|
|
//
|
|
// When no LLM is configured (APIKey or Model missing), doctor degrades to
|
|
// plain `helmfile diff` with zero behavior change.
|
|
package doctor
|
|
|
|
import (
|
|
goContext "context"
|
|
"time"
|
|
|
|
"github.com/helmfile/helmfile/pkg/agent/llm"
|
|
)
|
|
|
|
// Result bundles everything `helmfile doctor` needs to render its output and
|
|
// decide on an exit code.
|
|
type Result struct {
|
|
// Analysis is the structured LLM output. Nil when the LLM was not called
|
|
// (diff empty) or when LLMCallFailed is set.
|
|
Analysis *llm.Analysis
|
|
// RawDiff is the helm diff text AFTER secret redaction. Doctor never
|
|
// exposes unredacted secret content through Result.
|
|
RawDiff string
|
|
// SecretsRedacted counts secret-looking values stripped from RawDiff.
|
|
// Surfaced in the report footer so users can spot unexpected leaks.
|
|
SecretsRedacted int
|
|
// LLMCallFailed indicates the LLM was configured but the call failed;
|
|
// the caller should degrade to printing RawDiff with a warning.
|
|
LLMCallFailed bool
|
|
// LLMError is the underlying LLM error when LLMCallFailed is true.
|
|
LLMError error
|
|
// Model is the model identifier used (for the report footer).
|
|
Model string
|
|
// Duration is how long the LLM call took.
|
|
Duration time.Duration
|
|
}
|
|
|
|
// HasHighRisk delegates to Analysis.HasHighRisk when an analysis exists.
|
|
func (r Result) HasHighRisk() bool {
|
|
return r.Analysis != nil && r.Analysis.HasHighRisk()
|
|
}
|
|
|
|
// Options controls a single Analyze run.
|
|
type Options struct {
|
|
// Client is the LLM client. When nil, Analyze returns a Result that
|
|
// signals "no LLM" so the caller can degrade to plain diff.
|
|
Client llm.Client
|
|
// Environment is the --environment value (may be empty).
|
|
Environment string
|
|
// Releases is the list of release names that appear in the diff (may be nil).
|
|
Releases []string
|
|
// Model is the model identifier; surfaced in the report footer.
|
|
Model string
|
|
// Redactor controls secret redaction. A zero-value SecretRedactor is
|
|
// fine: its Redact method falls back to "<REDACTED>". Redaction is
|
|
// ALWAYS applied — there is no opt-out at this layer.
|
|
Redactor SecretRedactor
|
|
}
|
|
|
|
// Analyze runs the full doctor pipeline against the given diff text.
|
|
//
|
|
// Behavior:
|
|
// - Empty diff → empty Result (caller should print nothing).
|
|
// - diff is ALWAYS redacted via opts.Redactor first. RawDiff in the
|
|
// returned Result is the redacted text; the original is discarded.
|
|
// - nil Client → Result with RawDiff only (the "unconfigured" path).
|
|
// Redaction still happens — pipes downstream shouldn't see raw secrets.
|
|
// - Non-nil Client → calls LLM; on error returns LLMCallFailed=true.
|
|
func Analyze(ctx goContext.Context, diff string, opts Options) Result {
|
|
if diff == "" {
|
|
return Result{}
|
|
}
|
|
|
|
redacted, redactionCount := opts.Redactor.Redact(diff)
|
|
|
|
if opts.Client == nil {
|
|
return Result{
|
|
RawDiff: redacted,
|
|
SecretsRedacted: redactionCount,
|
|
}
|
|
}
|
|
|
|
start := time.Now()
|
|
a, err := opts.Client.Analyze(ctx, redacted, llm.AnalyzeInput{
|
|
Environment: opts.Environment,
|
|
Releases: opts.Releases,
|
|
})
|
|
duration := time.Since(start)
|
|
|
|
if err != nil {
|
|
return Result{
|
|
RawDiff: redacted,
|
|
SecretsRedacted: redactionCount,
|
|
LLMCallFailed: true,
|
|
LLMError: err,
|
|
Model: opts.Model,
|
|
Duration: duration,
|
|
}
|
|
}
|
|
|
|
return Result{
|
|
Analysis: &a,
|
|
RawDiff: redacted,
|
|
SecretsRedacted: redactionCount,
|
|
Model: opts.Model,
|
|
Duration: duration,
|
|
}
|
|
}
|