433 lines
15 KiB
Go
433 lines
15 KiB
Go
package audita
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/url"
|
|
"os"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
"gitea.maximumdirect.net/eric/narratio/internal/adapters/subprocess"
|
|
"gitea.maximumdirect.net/eric/narratio/internal/fileops"
|
|
)
|
|
|
|
// MaxProcessedOutputBytes bounds Audita's processed-transcript JSON result.
|
|
const MaxProcessedOutputBytes int64 = 64 * 1024 * 1024
|
|
|
|
// MaxReportOutputBytes bounds Audita's optional report JSON result.
|
|
const MaxReportOutputBytes int64 = 16 * 1024 * 1024
|
|
|
|
// SubprocessRunnerConfig defines deterministic settings for Audita CLI execution.
|
|
type SubprocessRunnerConfig struct {
|
|
Binary string
|
|
Timeout time.Duration
|
|
LLMAPIKeyEnv string
|
|
Modules []string
|
|
BaseURL string
|
|
Model string
|
|
TranscriptDescription string
|
|
ConfigPath string
|
|
OutputSchema string
|
|
WorkDirRetention string
|
|
TotalLLMConcurrency *int
|
|
ProposalLLMConcurrency *int
|
|
ValidationModel string
|
|
ValidationLLMConcurrency *int
|
|
Report bool
|
|
}
|
|
|
|
// SubprocessRunner invokes Audita via subprocess.
|
|
type SubprocessRunner struct {
|
|
binary string
|
|
timeout time.Duration
|
|
llmAPIKeyEnv string
|
|
modules []string
|
|
baseURL string
|
|
model string
|
|
transcriptDescription string
|
|
configPath string
|
|
outputSchema string
|
|
workDirRetention string
|
|
totalLLMConcurrency *int
|
|
proposalLLMConcurrency *int
|
|
validationModel string
|
|
validationLLMConcurrency *int
|
|
report bool
|
|
}
|
|
|
|
// NewSubprocessRunnerFromConfigValues parses config-derived values once.
|
|
func NewSubprocessRunnerFromConfigValues(
|
|
binary string,
|
|
timeout string,
|
|
llmAPIKeyEnv string,
|
|
modules []string,
|
|
baseURL string,
|
|
model string,
|
|
transcriptDescription string,
|
|
configPath string,
|
|
outputSchema string,
|
|
workDirRetention string,
|
|
totalLLMConcurrency *int,
|
|
proposalLLMConcurrency *int,
|
|
validationModel string,
|
|
validationLLMConcurrency *int,
|
|
report bool,
|
|
) (*SubprocessRunner, error) {
|
|
if strings.TrimSpace(timeout) == "" {
|
|
return nil, fmt.Errorf("audita timeout is required")
|
|
}
|
|
parsedTimeout, err := time.ParseDuration(timeout)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("parse audita timeout %q: %w", timeout, err)
|
|
}
|
|
return NewSubprocessRunner(SubprocessRunnerConfig{
|
|
Binary: binary,
|
|
Timeout: parsedTimeout,
|
|
LLMAPIKeyEnv: llmAPIKeyEnv,
|
|
Modules: modules,
|
|
BaseURL: baseURL,
|
|
Model: model,
|
|
TranscriptDescription: transcriptDescription,
|
|
ConfigPath: configPath,
|
|
OutputSchema: outputSchema,
|
|
WorkDirRetention: workDirRetention,
|
|
TotalLLMConcurrency: totalLLMConcurrency,
|
|
ProposalLLMConcurrency: proposalLLMConcurrency,
|
|
ValidationModel: validationModel,
|
|
ValidationLLMConcurrency: validationLLMConcurrency,
|
|
Report: report,
|
|
})
|
|
}
|
|
|
|
// NewSubprocessRunner constructs a validated Audita subprocess runner.
|
|
func NewSubprocessRunner(cfg SubprocessRunnerConfig) (*SubprocessRunner, error) {
|
|
if strings.TrimSpace(cfg.Binary) == "" {
|
|
return nil, fmt.Errorf("audita binary is required")
|
|
}
|
|
if cfg.Timeout <= 0 {
|
|
return nil, fmt.Errorf("audita timeout must be > 0")
|
|
}
|
|
for i, module := range cfg.Modules {
|
|
if strings.TrimSpace(module) == "" {
|
|
return nil, fmt.Errorf("audita module at index %d is empty", i)
|
|
}
|
|
}
|
|
if strings.TrimSpace(cfg.BaseURL) != "" {
|
|
u, err := url.Parse(cfg.BaseURL)
|
|
if err != nil || u.Scheme == "" || u.Host == "" {
|
|
if err != nil {
|
|
return nil, fmt.Errorf("audita base url %q is invalid: %w", cfg.BaseURL, err)
|
|
}
|
|
return nil, fmt.Errorf("audita base url %q is invalid", cfg.BaseURL)
|
|
}
|
|
}
|
|
if cfg.TotalLLMConcurrency != nil && *cfg.TotalLLMConcurrency <= 0 {
|
|
return nil, fmt.Errorf("audita total llm concurrency must be > 0 when provided")
|
|
}
|
|
if cfg.ProposalLLMConcurrency != nil && *cfg.ProposalLLMConcurrency <= 0 {
|
|
return nil, fmt.Errorf("audita proposal llm concurrency must be > 0 when provided")
|
|
}
|
|
if cfg.ValidationLLMConcurrency != nil && *cfg.ValidationLLMConcurrency <= 0 {
|
|
return nil, fmt.Errorf("audita validation llm concurrency must be > 0 when provided")
|
|
}
|
|
switch strings.TrimSpace(cfg.OutputSchema) {
|
|
case "", "bare-segments", "audita-v1":
|
|
default:
|
|
return nil, fmt.Errorf("audita output schema must be one of: bare-segments, audita-v1")
|
|
}
|
|
switch strings.TrimSpace(cfg.WorkDirRetention) {
|
|
case "", "always", "auto", "never":
|
|
default:
|
|
return nil, fmt.Errorf("audita work dir retention must be one of: always, auto, never")
|
|
}
|
|
|
|
modules := make([]string, len(cfg.Modules))
|
|
for i, m := range cfg.Modules {
|
|
modules[i] = strings.TrimSpace(m)
|
|
}
|
|
|
|
return &SubprocessRunner{
|
|
binary: strings.TrimSpace(cfg.Binary),
|
|
timeout: cfg.Timeout,
|
|
llmAPIKeyEnv: strings.TrimSpace(cfg.LLMAPIKeyEnv),
|
|
modules: modules,
|
|
baseURL: strings.TrimSpace(cfg.BaseURL),
|
|
model: strings.TrimSpace(cfg.Model),
|
|
transcriptDescription: strings.TrimSpace(cfg.TranscriptDescription),
|
|
configPath: strings.TrimSpace(cfg.ConfigPath),
|
|
outputSchema: strings.TrimSpace(cfg.OutputSchema),
|
|
workDirRetention: strings.TrimSpace(cfg.WorkDirRetention),
|
|
totalLLMConcurrency: cfg.TotalLLMConcurrency,
|
|
proposalLLMConcurrency: cfg.ProposalLLMConcurrency,
|
|
validationModel: strings.TrimSpace(cfg.ValidationModel),
|
|
validationLLMConcurrency: cfg.ValidationLLMConcurrency,
|
|
report: cfg.Report,
|
|
}, nil
|
|
}
|
|
|
|
// Run executes Audita process with deterministic flags and validates output artifacts.
|
|
func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishResult, error) {
|
|
if r == nil {
|
|
return PolishResult{}, fmt.Errorf("audita subprocess runner is nil")
|
|
}
|
|
if strings.TrimSpace(req.MergedTranscriptPath) == "" {
|
|
return PolishResult{}, fmt.Errorf("audita merged transcript path is required")
|
|
}
|
|
if strings.TrimSpace(req.GlossaryPath) == "" {
|
|
return PolishResult{}, fmt.Errorf("audita glossary path is required")
|
|
}
|
|
if strings.TrimSpace(req.OutputProcessedPath) == "" {
|
|
return PolishResult{}, fmt.Errorf("audita output processed path is required")
|
|
}
|
|
if strings.TrimSpace(req.WorkDir) == "" {
|
|
return PolishResult{}, fmt.Errorf("audita work dir is required")
|
|
}
|
|
if r.report && strings.TrimSpace(req.ReportPath) == "" {
|
|
return PolishResult{}, fmt.Errorf("audita report is enabled but report path is missing")
|
|
}
|
|
|
|
reqModules := req.Modules
|
|
if reqModules == nil {
|
|
reqModules = append([]string(nil), r.modules...)
|
|
}
|
|
args := r.buildArgs(req, reqModules)
|
|
|
|
credentialEnvVar := strings.TrimSpace(r.llmAPIKeyEnv)
|
|
credentialPresent := false
|
|
env := map[string]string{}
|
|
if credentialEnvVar != "" {
|
|
credential, ok := os.LookupEnv(credentialEnvVar)
|
|
if !ok || strings.TrimSpace(credential) == "" {
|
|
return PolishResult{}, fmt.Errorf("audita: required credential environment variable %s is not set", credentialEnvVar)
|
|
}
|
|
env["AUDITA_LLM_API_KEY"] = credential
|
|
credentialPresent = true
|
|
}
|
|
|
|
if req.GeneratedConfigPath != "" {
|
|
if err := r.writeInvocationConfig(req, args, reqModules, credentialPresent); err != nil {
|
|
return PolishResult{}, fmt.Errorf("write audita invocation config %q: %w", req.GeneratedConfigPath, err)
|
|
}
|
|
}
|
|
|
|
runRes, err := subprocess.Run(ctx, subprocess.RunRequest{
|
|
Executable: r.binary,
|
|
Args: args,
|
|
Timeout: r.timeout,
|
|
EnvOverrides: env,
|
|
StdoutLogPath: req.StdoutLogPath,
|
|
StderrLogPath: req.StderrLogPath,
|
|
})
|
|
if err != nil {
|
|
wrappedMessage := fmt.Sprintf(
|
|
"run audita process (binary=%q, stdout_log=%q, stderr_log=%q)",
|
|
r.binary,
|
|
req.StdoutLogPath,
|
|
req.StderrLogPath,
|
|
)
|
|
wrappedMessage = addSubprocessStreamHint(wrappedMessage, err)
|
|
return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf(
|
|
"%s: %w",
|
|
wrappedMessage,
|
|
err,
|
|
)
|
|
}
|
|
|
|
if err := validateProcessedOutput(req.OutputProcessedPath); err != nil {
|
|
return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf("validate audita processed output %q: %w", req.OutputProcessedPath, err)
|
|
}
|
|
if r.report {
|
|
if err := validateJSONFile(req.ReportPath); err != nil {
|
|
return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf("validate audita report output %q: %w", req.ReportPath, err)
|
|
}
|
|
}
|
|
|
|
return PolishResult{
|
|
ProcessedTranscriptPath: req.OutputProcessedPath,
|
|
ReportPath: req.ReportPath,
|
|
WorkDir: req.WorkDir,
|
|
StdoutLogPath: req.StdoutLogPath,
|
|
StderrLogPath: req.StderrLogPath,
|
|
GeneratedConfigPath: req.GeneratedConfigPath,
|
|
ExitCode: runRes.ExitCode,
|
|
Duration: runRes.Duration,
|
|
InvokedBinary: r.binary,
|
|
Metadata: map[string]any{
|
|
"adapter": "audita_subprocess",
|
|
"modules": reqModules,
|
|
"base_url": r.baseURL,
|
|
"model": r.model,
|
|
"transcript_description": r.transcriptDescription,
|
|
"config_path": r.configPath,
|
|
"output_schema": r.outputSchema,
|
|
"work_dir_retention": r.workDirRetention,
|
|
"validation_model": r.validationModel,
|
|
"total_llm_concurrency": r.totalLLMConcurrency,
|
|
"proposal_llm_concurrency": r.proposalLLMConcurrency,
|
|
"validation_llm_concurrency": r.validationLLMConcurrency,
|
|
"credential_env_var": r.llmAPIKeyEnv,
|
|
"credential_present": credentialPresent,
|
|
},
|
|
}, nil
|
|
}
|
|
|
|
func (r *SubprocessRunner) failureResult(req PolishRequest, modules []string, runRes subprocess.RunResult, credentialPresent bool) PolishResult {
|
|
return PolishResult{
|
|
ProcessedTranscriptPath: req.OutputProcessedPath,
|
|
ReportPath: req.ReportPath,
|
|
WorkDir: req.WorkDir,
|
|
StdoutLogPath: req.StdoutLogPath,
|
|
StderrLogPath: req.StderrLogPath,
|
|
GeneratedConfigPath: req.GeneratedConfigPath,
|
|
ExitCode: runRes.ExitCode,
|
|
Duration: runRes.Duration,
|
|
InvokedBinary: r.binary,
|
|
Metadata: map[string]any{
|
|
"adapter": "audita_subprocess",
|
|
"modules": modules,
|
|
"base_url": r.baseURL,
|
|
"model": r.model,
|
|
"transcript_description": r.transcriptDescription,
|
|
"config_path": r.configPath,
|
|
"output_schema": r.outputSchema,
|
|
"work_dir_retention": r.workDirRetention,
|
|
"validation_model": r.validationModel,
|
|
"total_llm_concurrency": r.totalLLMConcurrency,
|
|
"proposal_llm_concurrency": r.proposalLLMConcurrency,
|
|
"validation_llm_concurrency": r.validationLLMConcurrency,
|
|
"credential_env_var": r.llmAPIKeyEnv,
|
|
"credential_present": credentialPresent,
|
|
},
|
|
}
|
|
}
|
|
|
|
func (r *SubprocessRunner) buildArgs(req PolishRequest, modules []string) []string {
|
|
args := []string{
|
|
"process",
|
|
req.MergedTranscriptPath,
|
|
"--glossary", req.GlossaryPath,
|
|
"--output", req.OutputProcessedPath,
|
|
"--work-dir", req.WorkDir,
|
|
}
|
|
if r.baseURL != "" {
|
|
args = append(args, "--base-url", r.baseURL)
|
|
}
|
|
if r.model != "" {
|
|
args = append(args, "--model", r.model)
|
|
}
|
|
if len(modules) > 0 {
|
|
args = append(args, "--modules", strings.Join(modules, ","))
|
|
}
|
|
if r.report {
|
|
args = append(args, "--report-json", req.ReportPath)
|
|
}
|
|
if r.transcriptDescription != "" {
|
|
args = append(args, "--transcript-description", r.transcriptDescription)
|
|
}
|
|
if r.configPath != "" {
|
|
args = append(args, "--config", r.configPath)
|
|
}
|
|
if r.outputSchema != "" {
|
|
args = append(args, "--output-schema", r.outputSchema)
|
|
}
|
|
if r.workDirRetention != "" {
|
|
args = append(args, "--work-dir-retention", r.workDirRetention)
|
|
}
|
|
if r.totalLLMConcurrency != nil {
|
|
args = append(args, "--total-llm-concurrency", strconv.Itoa(*r.totalLLMConcurrency))
|
|
}
|
|
if r.proposalLLMConcurrency != nil {
|
|
args = append(args, "--proposal-llm-concurrency", strconv.Itoa(*r.proposalLLMConcurrency))
|
|
}
|
|
if r.validationModel != "" {
|
|
args = append(args, "--validation-model", r.validationModel)
|
|
}
|
|
if r.validationLLMConcurrency != nil {
|
|
args = append(args, "--validation-llm-concurrency", strconv.Itoa(*r.validationLLMConcurrency))
|
|
}
|
|
return args
|
|
}
|
|
|
|
func (r *SubprocessRunner) writeInvocationConfig(req PolishRequest, args []string, modules []string, credentialPresent bool) error {
|
|
payload := map[string]any{
|
|
"schema": "audita.generated.v1",
|
|
"binary": r.binary,
|
|
"args": args,
|
|
"timeout": r.timeout.String(),
|
|
"modules": modules,
|
|
"base_url": r.baseURL,
|
|
"model": r.model,
|
|
"transcript_description": r.transcriptDescription,
|
|
"config_path": r.configPath,
|
|
"output_schema": r.outputSchema,
|
|
"work_dir_retention": r.workDirRetention,
|
|
"validation_model": r.validationModel,
|
|
"total_llm_concurrency": r.totalLLMConcurrency,
|
|
"proposal_llm_concurrency": r.proposalLLMConcurrency,
|
|
"validation_llm_concurrency": r.validationLLMConcurrency,
|
|
"report_enabled": r.report,
|
|
"merged_transcript_path": req.MergedTranscriptPath,
|
|
"glossary_path": req.GlossaryPath,
|
|
"output_path": req.OutputProcessedPath,
|
|
"report_path": req.ReportPath,
|
|
"work_dir": req.WorkDir,
|
|
"credential_env_var": r.llmAPIKeyEnv,
|
|
"credential_present": credentialPresent,
|
|
}
|
|
return subprocess.WriteYAMLAtomic(req.GeneratedConfigPath, payload, fileops.WorkspaceFileMode)
|
|
}
|
|
|
|
func validateProcessedOutput(path string) error {
|
|
data, err := readAuditaResult(path, MaxProcessedOutputBytes, "processed transcript")
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
var payload map[string]any
|
|
if err := json.Unmarshal(data, &payload); err != nil {
|
|
return fmt.Errorf("parse json: %w", err)
|
|
}
|
|
segments, ok := payload["segments"]
|
|
if !ok {
|
|
return fmt.Errorf("top-level segments is required")
|
|
}
|
|
if _, ok := segments.([]any); !ok {
|
|
return fmt.Errorf("top-level segments must be an array")
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func addSubprocessStreamHint(message string, runErr error) string {
|
|
if runErr == nil {
|
|
return message
|
|
}
|
|
lower := strings.ToLower(runErr.Error())
|
|
if strings.Contains(lower, "bad file descriptor") || strings.Contains(lower, "exit code 120") {
|
|
return message + "; hint=audita child process may have started with invalid stderr/stdout descriptors"
|
|
}
|
|
return message
|
|
}
|
|
|
|
func validateJSONFile(path string) error {
|
|
data, err := readAuditaResult(path, MaxReportOutputBytes, "report")
|
|
if err != nil {
|
|
return err
|
|
}
|
|
var v any
|
|
if err := json.Unmarshal(data, &v); err != nil {
|
|
return fmt.Errorf("parse json: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func readAuditaResult(path string, limit int64, category string) ([]byte, error) {
|
|
data, err := fileops.ReadRegularFile(path, limit)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("audita %s result exceeds or cannot be read within %d-byte limit: %w", category, limit, err)
|
|
}
|
|
return data, nil
|
|
}
|