Assemble comparison application workflow

This commit is contained in:
2026-08-02 05:50:29 +00:00
parent d642791c10
commit d39e42de30
3 changed files with 431 additions and 11 deletions

214
internal/app/comparison.go Normal file
View File

@@ -0,0 +1,214 @@
package app
import (
"context"
"fmt"
"os"
"path/filepath"
"time"
"gitea.maximumdirect.net/eric/weatherreporter/internal/comparison"
"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
"gitea.maximumdirect.net/eric/weatherreporter/internal/promptdebug"
"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
"gitea.maximumdirect.net/eric/weatherreporter/internal/timeutil"
)
// ComparisonRequest describes one explicit, multi-profile report comparison.
// It deliberately does not accept a notifier: comparison publication is local.
type ComparisonRequest struct {
Config config.Config
Report ReportKind
ProfileIDs []string
WorkingDir string
OutputDir string
Replace bool
LLMDebugDir string
Date time.Time
Clock timeutil.Clock
Collector Collector
Executor promptexec.Executor
}
// ComparisonResult records the resolved comparison and profile outcomes.
type ComparisonResult struct {
ComparisonID string
ReportID report.ID
ReportName string
PromptID string
PromptVersion string
PromptHash string
StartedAt time.Time
FinishedAt time.Time
Timezone string
ValidPeriod timeutil.Period
OutputDirectory string
ManifestPath string
DataPackagePath string
Total int
Succeeded int
Failed int
Results []ComparisonProfileResult
}
// ComparisonProfileResult records one explicitly selected profile.
type ComparisonProfileResult struct {
Position int
ProfileID string
BackendID string
ModelName string
Status string
ValidationStatus promptexec.ValidationStatus
ReportPath string
LLMDebugPath string
Error *comparison.SafeError
}
// CompareDetailed assembles, executes, and atomically publishes a comparison
// bundle. Profile failures publish a complete partial bundle; all other
// failures leave the destination untouched.
func CompareDetailed(ctx context.Context, req ComparisonRequest) (*ComparisonResult, error) {
if err := comparison.ValidateProfileIDs(req.ProfileIDs); err != nil {
return nil, err
}
clock := req.Clock
if clock == nil {
clock = timeutil.SystemClock{}
}
now := clock.Now()
resolved, err := ResolveGenerate(GenerateRequest{Config: req.Config, Report: req.Report, Date: req.Date}, now)
if err != nil {
return nil, err
}
metadata := resolved.Metadata()
comparisonID, err := comparison.BuildComparisonID(metadata.RunID)
if err != nil {
return nil, fmt.Errorf("build comparison identity: %w", err)
}
result := initialComparisonResult(req, resolved, comparisonID, now.UTC())
outputName, err := resolved.OutputName()
if err != nil {
return result, fmt.Errorf("resolve comparison output name: %w", err)
}
outputDirectory, err := resolveComparisonOutputDirectory(req.WorkingDir, req.OutputDir, req.Config.Output.Directory, outputName)
if err != nil {
return result, err
}
initialPlan, err := comparison.PlanDestination(req.WorkingDir, outputDirectory, req.Replace)
if err != nil {
return result, fmt.Errorf("preflight comparison destination: %w", err)
}
result.OutputDirectory = initialPlan.Target
debugWriter, err := promptdebug.NewPromptDebugWriter(req.LLMDebugDir)
if err != nil {
return result, promptexec.NewError(promptexec.InvalidConfiguration, "initialize prompt debug", err)
}
inspection, err := InspectComparisonExecution(ctx, ComparisonInspectionRequest{
Resolved: resolved, ProfileIDs: req.ProfileIDs, Executor: req.Executor, LookupEnv: os.LookupEnv,
})
if err != nil {
return result, err
}
result.PromptID, result.PromptVersion, result.PromptHash = inspection.PromptID, inspection.PromptVersion, inspection.PromptHash
collection, err := collectWeather(ctx, req.Config, req.Collector)
if err != nil {
return result, err
}
prepared, err := prepareReport(prepareReportRequest{Config: req.Config, Resolved: resolved, Collection: *collection})
if err != nil {
return result, fmt.Errorf("prepare comparison report: %w", err)
}
executed := executeComparisonProfiles(ctx, comparisonExecutionRequest{
Prepared: prepared, Inspection: inspection, ComparisonID: comparisonID, DebugWriter: debugWriter, Executor: req.Executor,
})
result.FinishedAt = clock.Now().UTC()
copyComparisonOutcomes(result, executed.Outcomes, false)
if executed.Canceled {
return result, fmt.Errorf("comparison execution: %w", ctx.Err())
}
bundle := comparisonBundle(result, prepared.dataPackageCopy(), executed.Outcomes)
if err := bundle.Validate(); err != nil {
return result, fmt.Errorf("build comparison bundle: %w", err)
}
publicationPlan, err := comparison.PlanDestination(req.WorkingDir, outputDirectory, req.Replace)
if err != nil {
return result, fmt.Errorf("re-preflight comparison destination: %w", err)
}
if err := comparison.Publish(ctx, publicationPlan, bundle); err != nil {
return result, fmt.Errorf("publish comparison bundle: %w", err)
}
result.OutputDirectory = publicationPlan.Target
result.ManifestPath = filepath.Join(publicationPlan.Target, comparison.ManifestFilename)
result.DataPackagePath = filepath.Join(publicationPlan.Target, comparison.DataPackageFilename)
copyComparisonOutcomes(result, executed.Outcomes, true)
if result.Failed > 0 {
return result, fmt.Errorf("comparison completed with %d failed profiles", result.Failed)
}
return result, nil
}
func initialComparisonResult(req ComparisonRequest, resolved report.Resolved, comparisonID string, startedAt time.Time) *ComparisonResult {
metadata := resolved.Metadata()
return &ComparisonResult{
ComparisonID: comparisonID,
ReportID: resolved.Definition.ID,
ReportName: resolved.Definition.Name,
StartedAt: startedAt,
Timezone: req.Config.WeatherAPI.Timezone,
ValidPeriod: metadata.ValidPeriod,
}
}
func copyComparisonOutcomes(result *ComparisonResult, outcomes []comparisonProfileOutcome, published bool) {
result.Results = make([]ComparisonProfileResult, len(outcomes))
result.Total, result.Succeeded, result.Failed = len(outcomes), 0, 0
for index, outcome := range outcomes {
profile := ComparisonProfileResult{
Position: outcome.Position, ProfileID: outcome.ProfileID, BackendID: outcome.BackendID, ModelName: outcome.ModelName,
Status: outcome.Status, ValidationStatus: outcome.ValidationStatus, LLMDebugPath: outcome.LLMDebugPath, Error: outcome.Error,
}
if published && outcome.Status == comparison.StatusSucceeded {
profile.ReportPath = filepath.Join(result.OutputDirectory, outcome.ReportPath)
}
result.Results[index] = profile
if outcome.Status == comparison.StatusSucceeded {
result.Succeeded++
} else {
result.Failed++
}
}
}
func comparisonBundle(result *ComparisonResult, dataPackage []byte, outcomes []comparisonProfileOutcome) comparison.LogicalBundle {
manifest := comparison.Manifest{
SchemaVersion: comparison.SchemaVersion, ComparisonID: result.ComparisonID,
StartedAt: result.StartedAt.UTC(), FinishedAt: result.FinishedAt.UTC(),
ReportID: string(result.ReportID), Timezone: result.Timezone,
ValidPeriod: comparison.ValidPeriod{Start: result.ValidPeriod.Start, End: result.ValidPeriod.End},
PromptID: result.PromptID, PromptVersion: result.PromptVersion, PromptHash: result.PromptHash,
DataPackage: comparison.DataPackageReference{Path: comparison.DataPackageFilename, SHA256: comparison.SHA256(dataPackage)},
Total: result.Total, Succeeded: result.Succeeded, Failed: result.Failed,
Results: make([]comparison.Result, len(outcomes)),
}
bundle := comparison.LogicalBundle{Manifest: manifest, DataPackage: dataPackage}
for index, outcome := range outcomes {
manifestResult := comparison.Result{
Position: outcome.Position, ProfileID: outcome.ProfileID, BackendID: outcome.BackendID, ModelName: outcome.ModelName,
Status: outcome.Status, ValidationStatus: string(outcome.ValidationStatus), Error: outcome.Error,
}
if outcome.Status == comparison.StatusSucceeded {
manifestResult.ReportPath = outcome.ReportPath
bundle.Reports = append(bundle.Reports, comparison.BundleReport{Position: outcome.Position, Path: outcome.ReportPath, Markdown: outcome.Markdown})
}
bundle.Manifest.Results[index] = manifestResult
}
return bundle
}

View File

@@ -0,0 +1,180 @@
package app
import (
"context"
"encoding/json"
"errors"
"os"
"path/filepath"
"strings"
"testing"
"gitea.maximumdirect.net/eric/weatherreporter/internal/comparison"
"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
"gitea.maximumdirect.net/eric/weatherreporter/internal/timeutil"
)
func TestCompareDetailedPublishesOneCoherentBundle(t *testing.T) {
cfg := comparisonConfig()
bundle := generationBundle(t)
workingDir := t.TempDir()
executor := &generationExecutor{}
inspectedBeforeCollection := false
result, err := CompareDetailed(context.Background(), ComparisonRequest{
Config: cfg, Report: ReportDaily, ProfileIDs: []string{"weather-light", "weather-deep"},
WorkingDir: workingDir, Date: generationTime("2026-05-29T12:00:00-05:00"),
Clock: timeutil.FixedClock{Time: generationTime("2026-05-29T08:30:00-05:00")},
Collector: &generationCollector{bundle: &bundle, beforeRun: func() {
inspectedBeforeCollection = executor.promptInspections == 1 && executor.profileInspections == 2
}}, Executor: executor,
})
if err != nil {
t.Fatalf("CompareDetailed() error = %v", err)
}
if result == nil || result.Total != 2 || result.Succeeded != 2 || result.Failed != 0 || executor.promptInspections != 1 || executor.profileInspections != 2 || executor.executeCalls != 2 || !inspectedBeforeCollection || result.ManifestPath == "" || result.DataPackagePath == "" {
t.Fatalf("result/executor = %#v/%#v", result, executor)
}
if result.OutputDirectory != filepath.Dir(result.ManifestPath) || !filepath.IsAbs(result.ManifestPath) || !filepath.IsAbs(result.DataPackagePath) {
t.Fatalf("published paths = %#v", result)
}
for index, profile := range result.Results {
if profile.Position != index+1 || profile.Status != comparison.StatusSucceeded || !filepath.IsAbs(profile.ReportPath) || profile.Error != nil {
t.Fatalf("profile result = %#v", profile)
}
}
data, readErr := os.ReadFile(result.ManifestPath)
if readErr != nil {
t.Fatal(readErr)
}
var manifest comparison.Manifest
if err := json.Unmarshal(data, &manifest); err != nil {
t.Fatal(err)
}
if manifest.ComparisonID != result.ComparisonID || manifest.Total != result.Total || manifest.Succeeded != result.Succeeded || manifest.DataPackage.SHA256 == "" || len(manifest.Results) != 2 {
t.Fatalf("manifest = %#v", manifest)
}
if manifest.Results[0].ReportPath != filepath.Base(result.Results[0].ReportPath) || manifest.Results[1].ReportPath != filepath.Base(result.Results[1].ReportPath) {
t.Fatalf("manifest report paths = %#v", manifest.Results)
}
}
func TestCompareDetailedPublishesPartialBundleAndReturnsAggregateError(t *testing.T) {
cfg := comparisonConfig()
bundle := generationBundle(t)
executor := &generationExecutor{executeErrors: map[string]error{"weather-deep": errors.New("provider detail must not escape")}}
result, err := CompareDetailed(context.Background(), ComparisonRequest{
Config: cfg, Report: ReportDaily, ProfileIDs: []string{"weather-light", "weather-deep", "weather-fallback"},
WorkingDir: t.TempDir(), Date: generationTime("2026-05-29T12:00:00-05:00"),
Clock: timeutil.FixedClock{Time: generationTime("2026-05-29T08:30:00-05:00")},
Collector: &generationCollector{bundle: &bundle}, Executor: executor,
})
if err == nil || err.Error() != "comparison completed with 1 failed profiles" || result == nil || result.Total != 3 || result.Succeeded != 2 || result.Failed != 1 {
t.Fatalf("CompareDetailed() result/error = %#v/%v", result, err)
}
failure := result.Results[1]
if failure.Status != comparison.StatusFailed || failure.ReportPath != "" || failure.Error == nil || strings.Contains(failure.Error.Message, "provider detail") {
t.Fatalf("failure = %#v", failure)
}
if _, statErr := os.Stat(result.ManifestPath); statErr != nil {
t.Fatalf("partial manifest: %v", statErr)
}
if _, statErr := os.Stat(filepath.Join(result.OutputDirectory, filepath.Base(result.Results[0].ReportPath))); statErr != nil {
t.Fatalf("successful partial report: %v", statErr)
}
}
func TestCompareDetailedPreflightsBeforePromptOrCollection(t *testing.T) {
invalidDestination := filepath.Join(t.TempDir(), "not-a-directory")
if err := os.WriteFile(invalidDestination, []byte("x"), 0o600); err != nil {
t.Fatal(err)
}
bundle := generationBundle(t)
collector := &generationCollector{bundle: &bundle}
executor := &generationExecutor{}
result, err := CompareDetailed(context.Background(), ComparisonRequest{
Config: comparisonConfig(), Report: ReportDaily, ProfileIDs: []string{"weather-light", "weather-deep"},
WorkingDir: t.TempDir(), OutputDir: invalidDestination, Date: generationTime("2026-05-29T12:00:00-05:00"),
Clock: timeutil.FixedClock{Time: generationTime("2026-05-29T08:30:00-05:00")}, Collector: collector, Executor: executor,
})
if err == nil || result == nil || collector.called || executor.promptInspections != 0 || executor.executeCalls != 0 || result.ManifestPath != "" {
t.Fatalf("result/error/collector/executor = %#v/%v/%#v/%#v", result, err, collector, executor)
}
}
func TestCompareDetailedPublishesManifestWhenEveryProfileFails(t *testing.T) {
bundle := generationBundle(t)
executor := &generationExecutor{executeErrors: map[string]error{
"weather-light": errors.New("first provider failure"), "weather-deep": errors.New("second provider failure"),
}}
result, err := CompareDetailed(context.Background(), ComparisonRequest{
Config: comparisonConfig(), Report: ReportDaily, ProfileIDs: []string{"weather-light", "weather-deep"},
WorkingDir: t.TempDir(), Date: generationTime("2026-05-29T12:00:00-05:00"),
Clock: timeutil.FixedClock{Time: generationTime("2026-05-29T08:30:00-05:00")},
Collector: &generationCollector{bundle: &bundle}, Executor: executor,
})
if err == nil || err.Error() != "comparison completed with 2 failed profiles" || result == nil || result.Succeeded != 0 || result.Failed != 2 || result.ManifestPath == "" {
t.Fatalf("CompareDetailed() result/error = %#v/%v", result, err)
}
for _, profile := range result.Results {
if profile.ReportPath != "" || profile.Error == nil {
t.Fatalf("failed profile = %#v", profile)
}
}
}
func TestCompareDetailedCancellationPreservesPublishedBundle(t *testing.T) {
workingDir := t.TempDir()
bundle := generationBundle(t)
request := ComparisonRequest{
Config: comparisonConfig(), Report: ReportDaily, ProfileIDs: []string{"weather-light", "weather-deep"},
WorkingDir: workingDir, Date: generationTime("2026-05-29T12:00:00-05:00"),
Clock: timeutil.FixedClock{Time: generationTime("2026-05-29T08:30:00-05:00")}, Collector: &generationCollector{bundle: &bundle}, Executor: &generationExecutor{},
}
previous, err := CompareDetailed(context.Background(), request)
if err != nil {
t.Fatalf("initial CompareDetailed() error = %v", err)
}
before, err := os.ReadFile(previous.ManifestPath)
if err != nil {
t.Fatal(err)
}
ctx, cancel := context.WithCancel(context.Background())
request.Replace = true
request.Executor = &generationExecutor{cancelBeforeReturn: cancel}
result, err := CompareDetailed(ctx, request)
if !errors.Is(err, context.Canceled) || result == nil || result.ManifestPath != "" || result.DataPackagePath != "" {
t.Fatalf("canceled CompareDetailed() result/error = %#v/%v", result, err)
}
after, readErr := os.ReadFile(previous.ManifestPath)
if readErr != nil || string(after) != string(before) {
t.Fatalf("published manifest changed = %q, error = %v", after, readErr)
}
}
func TestCompareDetailedLeavesExistingBundleWhenPublicationPreflightChanges(t *testing.T) {
workingDir := t.TempDir()
target := filepath.Join(workingDir, "comparison-output")
bundle := generationBundle(t)
executor := &generationExecutor{beforeExecute: func(promptexec.ExecuteRequest) {
_ = os.WriteFile(target, []byte("changed"), 0o600)
}}
result, err := CompareDetailed(context.Background(), ComparisonRequest{
Config: comparisonConfig(), Report: ReportDaily, ProfileIDs: []string{"weather-light", "weather-deep"},
WorkingDir: workingDir, OutputDir: target, Date: generationTime("2026-05-29T12:00:00-05:00"),
Clock: timeutil.FixedClock{Time: generationTime("2026-05-29T08:30:00-05:00")}, Collector: &generationCollector{bundle: &bundle}, Executor: executor,
})
if err == nil || result == nil || result.ManifestPath != "" || result.DataPackagePath != "" || result.Results[0].ReportPath != "" {
t.Fatalf("CompareDetailed() result/error = %#v/%v", result, err)
}
data, readErr := os.ReadFile(target)
if readErr != nil || string(data) != "changed" {
t.Fatalf("destination = %q, error = %v", data, readErr)
}
}
func comparisonConfig() config.Config {
cfg := config.Defaults()
cfg.WeatherAPI.Timezone, cfg.Location.ID = "America/Chicago", "home"
return cfg
}

View File

@@ -6,6 +6,7 @@ import (
"errors"
"os"
"path/filepath"
"sync"
"testing"
"time"
@@ -37,52 +38,77 @@ type generationExecutor struct {
called bool
executeCalls int
promptInspections int
profileInspections int
inspectErr error
executeErr error
executeErrors map[string]error
beforeExecute func(promptexec.ExecuteRequest)
cancelBeforeReturn context.CancelFunc
validation promptexec.ValidationStatus
rawOutput []byte
failedPrompt string
}
var generationExecutorMu sync.Mutex
func (e *generationExecutor) InspectPrompt(_ context.Context, id, version string) (promptexec.PromptInspection, error) {
generationExecutorMu.Lock()
defer generationExecutorMu.Unlock()
e.promptInspections++
if e.inspectErr != nil {
return promptexec.PromptInspection{}, e.inspectErr
}
definition := generationDefinitionForPrompt(id)
return promptexec.PromptInspection{PromptID: id, PromptVersion: version, PromptHash: "prompt-hash", DefaultProfileID: "fixture", Inputs: []promptexec.InputDefinition{{Name: "data_package", Required: true, ContentType: "application/yaml"}}, Output: promptexec.OutputContract{Format: "json", ValidationMode: "json_schema", SchemaPath: definition.GeneratedTextSchemaID + ".generated_text.schema.json"}}, nil
return promptexec.PromptInspection{PromptID: id, PromptVersion: version, PromptHash: generationPromptHash, DefaultProfileID: "fixture", Inputs: []promptexec.InputDefinition{{Name: "data_package", Required: true, ContentType: "application/yaml"}}, Output: promptexec.OutputContract{Format: "json", ValidationMode: "json_schema", SchemaPath: definition.GeneratedTextSchemaID + ".generated_text.schema.json"}}, nil
}
func (*generationExecutor) InspectProfile(_ context.Context, id string) (promptexec.ProfileInspection, error) {
func (e *generationExecutor) InspectProfile(_ context.Context, id string) (promptexec.ProfileInspection, error) {
generationExecutorMu.Lock()
defer generationExecutorMu.Unlock()
e.profileInspections++
return promptexec.ProfileInspection{ProfileID: id, BackendID: "fixture", ModelName: "fixture-model"}, nil
}
func (e *generationExecutor) Execute(_ context.Context, req promptexec.ExecuteRequest, callback promptexec.PreparationCallback) (*promptexec.Execution, error) {
stamp := time.Date(2026, 5, 29, 15, 0, 0, 0, time.UTC)
if err := callback(promptexec.Preparation{PromptID: req.PromptID, PromptVersion: req.PromptVersion, PromptHash: "prompt-hash", RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID, BackendID: "fixture", ModelName: "fixture-model", StartedAt: stamp, EndedAt: stamp}, nil); err != nil {
if err := callback(promptexec.Preparation{PromptID: req.PromptID, PromptVersion: req.PromptVersion, PromptHash: generationPromptHash, RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID, BackendID: "fixture", ModelName: "fixture-model", StartedAt: stamp, EndedAt: stamp}, nil); err != nil {
return nil, err
}
generationExecutorMu.Lock()
e.called = true
e.executeCalls++
if e.executeErr != nil {
return nil, e.executeErr
}
beforeExecute := e.beforeExecute
profileErr := e.executeErrors[req.ProfileID]
executeErr := e.executeErr
status := e.validation
rawOutput := append([]byte(nil), e.rawOutput...)
failedPrompt := e.failedPrompt
cancelBeforeReturn := e.cancelBeforeReturn
generationExecutorMu.Unlock()
if beforeExecute != nil {
beforeExecute(req)
}
if profileErr != nil {
return nil, profileErr
}
if executeErr != nil {
return nil, executeErr
}
if status == "" {
status = promptexec.ValidationPassed
}
if e.failedPrompt == req.PromptID {
if failedPrompt == req.PromptID {
status = promptexec.ValidationFailed
}
rawOutput := e.rawOutput
if rawOutput == nil {
rawOutput = []byte(`{"summary":"Showers are possible during the selected day.","forecast_discussion":["A front will keep rain chances in the forecast."],"precipitation_timing":"Rain is most likely during the afternoon."}`)
}
if e.cancelBeforeReturn != nil {
e.cancelBeforeReturn()
if cancelBeforeReturn != nil {
cancelBeforeReturn()
}
return &promptexec.Execution{RunID: "provider-run", PromptID: req.PromptID, PromptVersion: req.PromptVersion, PromptHash: "prompt-hash", RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID, BackendID: "fixture", ModelName: "fixture-model", StartedAt: stamp, EndedAt: stamp, RawOutput: rawOutput, Validation: promptexec.NewValidation(status, "json_schema", generationDefinitionForPrompt(req.PromptID).GeneratedTextSchemaID+".generated_text.schema.json", nil)}, nil
return &promptexec.Execution{RunID: "provider-run", PromptID: req.PromptID, PromptVersion: req.PromptVersion, PromptHash: generationPromptHash, RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID, BackendID: "fixture", ModelName: "fixture-model", StartedAt: stamp, EndedAt: stamp, RawOutput: rawOutput, Validation: promptexec.NewValidation(status, "json_schema", generationDefinitionForPrompt(req.PromptID).GeneratedTextSchemaID+".generated_text.schema.json", nil)}, nil
}
const generationPromptHash = "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef"
func generationDefinitionForPrompt(promptID string) report.Definition {
for _, definition := range report.DefaultRegistry().All() {
if definition.PromptID == promptID {