Add comparison profile preflight

This commit is contained in:
2026-08-02 05:25:03 +00:00
parent 6173e50d25
commit de1ae896b3
2 changed files with 184 additions and 14 deletions

View File

@@ -5,6 +5,7 @@ import (
"os"
"strings"
"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/report"
@@ -39,6 +40,32 @@ type PromptExecutionsInspectionRequest struct {
LookupEnv func(string) (string, bool)
}
// ComparisonInspectionRequest contains the explicit profile selection for one
// resolved prompt comparison. It intentionally has no configured profile field.
type ComparisonInspectionRequest struct {
Resolved report.Resolved
ProfileIDs []string
Executor promptexec.Executor
LookupEnv func(string) (string, bool)
}
// ComparisonInspectionResult contains the safe, shared prompt identity and
// ordered effective profile identities for a comparison.
type ComparisonInspectionResult struct {
PromptID string
PromptVersion string
PromptHash string
Profiles []ComparisonProfileInspection
}
// ComparisonProfileInspection contains one requested profile's safe effective
// execution identity.
type ComparisonProfileInspection struct {
ProfileID string
BackendID string
ModelName string
}
// InspectPromptExecution validates the exact prompt and profile needed for a
// report before collection, execution, or durable writes begin.
func InspectPromptExecution(ctx context.Context, req PromptInspectionRequest) (PromptInspectionResult, error) {
@@ -64,21 +91,9 @@ func InspectPromptExecutions(ctx context.Context, req PromptExecutionsInspection
profiles := map[string]promptexec.ProfileInspection{}
for _, resolved := range req.Resolved {
definition := resolved.Definition
if strings.TrimSpace(definition.PromptID) == "" || strings.TrimSpace(definition.PromptVersion) == "" {
return nil, promptexec.NewError(promptexec.InvalidConfiguration, "report prompt identity is incomplete", nil)
}
inspection, err := req.Executor.InspectPrompt(ctx, definition.PromptID, definition.PromptVersion)
inspection, err := inspectPromptContract(ctx, req.Executor, definition)
if err != nil {
return nil, promptInspectionError("prompt inspection failed", err)
}
if inspection.PromptID != definition.PromptID || inspection.PromptVersion != definition.PromptVersion {
return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt inspection did not return the requested prompt version", nil)
}
if !validPromptInput(inspection.Inputs) {
return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt must declare exactly one required application/yaml data_package input", nil)
}
if !validPromptOutput(definition, inspection.Output) {
return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt must declare the report JSON Schema output contract", nil)
return nil, err
}
profileID := req.Promptkit.Profile
if profileID == "" {
@@ -103,6 +118,61 @@ func InspectPromptExecutions(ctx context.Context, req PromptExecutionsInspection
return results, nil
}
// InspectComparisonExecution validates one exact prompt and every explicitly
// requested profile before collection or model execution. Profiles are
// inspected sequentially in request order.
func InspectComparisonExecution(ctx context.Context, req ComparisonInspectionRequest) (ComparisonInspectionResult, error) {
if err := comparison.ValidateProfileIDs(req.ProfileIDs); err != nil {
return ComparisonInspectionResult{}, promptexec.NewError(promptexec.InvalidRequest, "comparison profile selection is invalid", err)
}
if req.Executor == nil {
return ComparisonInspectionResult{}, promptexec.NewError(promptexec.InvalidConfiguration, "prompt executor is required", nil)
}
inspection, err := inspectPromptContract(ctx, req.Executor, req.Resolved.Definition)
if err != nil {
return ComparisonInspectionResult{}, comparisonInspectionError("comparison prompt inspection failed", err)
}
result := ComparisonInspectionResult{
PromptID: inspection.PromptID,
PromptVersion: inspection.PromptVersion,
PromptHash: inspection.PromptHash,
Profiles: make([]ComparisonProfileInspection, 0, len(req.ProfileIDs)),
}
for _, profileID := range req.ProfileIDs {
profile, err := inspectPromptProfile(ctx, req.Executor, profileID, req.LookupEnv)
if err != nil {
return ComparisonInspectionResult{}, comparisonInspectionError("comparison profile inspection failed", err)
}
result.Profiles = append(result.Profiles, ComparisonProfileInspection{
ProfileID: profile.ProfileID,
BackendID: profile.BackendID,
ModelName: profile.ModelName,
})
}
return result, nil
}
func inspectPromptContract(ctx context.Context, executor promptexec.Executor, definition report.Definition) (promptexec.PromptInspection, error) {
if strings.TrimSpace(definition.PromptID) == "" || strings.TrimSpace(definition.PromptVersion) == "" {
return promptexec.PromptInspection{}, promptexec.NewError(promptexec.InvalidConfiguration, "report prompt identity is incomplete", nil)
}
inspection, err := executor.InspectPrompt(ctx, definition.PromptID, definition.PromptVersion)
if err != nil {
return promptexec.PromptInspection{}, promptInspectionError("prompt inspection failed", err)
}
if inspection.PromptID != definition.PromptID || inspection.PromptVersion != definition.PromptVersion {
return promptexec.PromptInspection{}, promptexec.NewError(promptexec.InvalidConfiguration, "prompt inspection did not return the requested prompt version", nil)
}
if !validPromptInput(inspection.Inputs) {
return promptexec.PromptInspection{}, promptexec.NewError(promptexec.InvalidConfiguration, "prompt must declare exactly one required application/yaml data_package input", nil)
}
if !validPromptOutput(definition, inspection.Output) {
return promptexec.PromptInspection{}, promptexec.NewError(promptexec.InvalidConfiguration, "prompt must declare the report JSON Schema output contract", nil)
}
return inspection, nil
}
func inspectPromptProfile(ctx context.Context, executor promptexec.Executor, profileID string, lookupEnv func(string) (string, bool)) (promptexec.ProfileInspection, error) {
profile, err := executor.InspectProfile(ctx, profileID)
if err != nil {
@@ -140,3 +210,11 @@ func promptInspectionError(operation string, err error) error {
}
return promptexec.NewError(promptexec.InvalidConfiguration, operation, err)
}
func comparisonInspectionError(operation string, err error) error {
category := promptexec.CategoryOf(err)
if category == "" {
category = promptexec.InvalidConfiguration
}
return promptexec.NewError(category, operation, err)
}

View File

@@ -3,6 +3,7 @@ package app
import (
"context"
"errors"
"reflect"
"strings"
"testing"
"time"
@@ -131,6 +132,95 @@ func TestInspectPromptExecutionsReusesEffectiveProfile(t *testing.T) {
}
}
func TestInspectComparisonExecutionPreservesOrderedExplicitProfiles(t *testing.T) {
resolved := inspectionResolved(t)
executor := &inspectionExecutor{
prompt: validPromptInspection(resolved.Definition),
profiles: map[string]promptexec.ProfileInspection{
"weather-light": {ProfileID: "weather-light", BackendID: "local", ModelName: "light-model"},
"weather-deep": {ProfileID: "weather-deep", BackendID: "cloud", ModelName: "deep-model"},
},
}
profileIDs := []string{"weather-light", "weather-deep"}
result, err := InspectComparisonExecution(context.Background(), ComparisonInspectionRequest{
Resolved: resolved, ProfileIDs: profileIDs, Executor: executor,
})
if err != nil {
t.Fatalf("InspectComparisonExecution() error = %v", err)
}
if result.PromptID != resolved.Definition.PromptID || result.PromptVersion != resolved.Definition.PromptVersion || result.PromptHash != "prompt-hash" {
t.Fatalf("prompt result = %#v", result)
}
if !reflect.DeepEqual(executor.profileRequests, profileIDs) || len(executor.promptRequests) != 1 || executor.executeRequests != 0 {
t.Fatalf("prompt/profile/execute requests = %#v/%#v/%d", executor.promptRequests, executor.profileRequests, executor.executeRequests)
}
wantProfiles := []ComparisonProfileInspection{
{ProfileID: "weather-light", BackendID: "local", ModelName: "light-model"},
{ProfileID: "weather-deep", BackendID: "cloud", ModelName: "deep-model"},
}
if !reflect.DeepEqual(result.Profiles, wantProfiles) {
t.Fatalf("profiles = %#v, want %#v", result.Profiles, wantProfiles)
}
}
func TestInspectComparisonExecutionRejectsInvalidProfilesBeforeInspection(t *testing.T) {
resolved := inspectionResolved(t)
for _, profileIDs := range [][]string{
{"weather-light"},
{"weather-light", " \t"},
{"weather-light", "weather-light"},
} {
t.Run(strings.Join(profileIDs, ","), func(t *testing.T) {
executor := &inspectionExecutor{prompt: validPromptInspection(resolved.Definition)}
_, err := InspectComparisonExecution(context.Background(), ComparisonInspectionRequest{
Resolved: resolved, ProfileIDs: profileIDs, Executor: executor,
})
if err == nil || promptexec.CategoryOf(err) != promptexec.InvalidRequest {
t.Fatalf("error/category = %v/%q, want invalid request", err, promptexec.CategoryOf(err))
}
if len(executor.promptRequests) != 0 || len(executor.profileRequests) != 0 || executor.executeRequests != 0 {
t.Fatalf("invalid profile selection performed prompt/profile/execution work: %#v/%#v/%d", executor.promptRequests, executor.profileRequests, executor.executeRequests)
}
})
}
}
func TestInspectComparisonExecutionStopsAtFirstProfileFailure(t *testing.T) {
resolved := inspectionResolved(t)
executor := &inspectionExecutor{
prompt: validPromptInspection(resolved.Definition),
profiles: map[string]promptexec.ProfileInspection{
"weather-light": {ProfileID: "weather-light", BackendID: "local", ModelName: "light-model"},
"missing-key": {ProfileID: "missing-key", APIKeyEnv: "PROMPT_API_KEY"},
"weather-deep": {ProfileID: "weather-deep", BackendID: "cloud", ModelName: "deep-model"},
},
}
_, err := InspectComparisonExecution(context.Background(), ComparisonInspectionRequest{
Resolved: resolved, ProfileIDs: []string{"weather-light", "missing-key", "weather-deep"}, Executor: executor,
LookupEnv: func(string) (string, bool) { return "", false },
})
if err == nil || promptexec.CategoryOf(err) != promptexec.MissingCredential {
t.Fatalf("error/category = %v/%q, want missing credential", err, promptexec.CategoryOf(err))
}
if !reflect.DeepEqual(executor.profileRequests, []string{"weather-light", "missing-key"}) || len(executor.promptRequests) != 1 || executor.executeRequests != 0 {
t.Fatalf("prompt/profile/execute requests = %#v/%#v/%d", executor.promptRequests, executor.profileRequests, executor.executeRequests)
}
}
func TestInspectComparisonExecutionStopsBeforeProfileInspectionWhenPromptFails(t *testing.T) {
resolved := inspectionResolved(t)
executor := &inspectionExecutor{promptErr: promptexec.NewError(promptexec.PromptNotFound, "prompt is unavailable", nil)}
_, err := InspectComparisonExecution(context.Background(), ComparisonInspectionRequest{
Resolved: resolved, ProfileIDs: []string{"weather-light", "weather-deep"}, Executor: executor,
})
if err == nil || promptexec.CategoryOf(err) != promptexec.PromptNotFound || !strings.Contains(err.Error(), "comparison prompt") {
t.Fatalf("error/category = %v/%q, want prompt-context prompt not found", err, promptexec.CategoryOf(err))
}
if len(executor.promptRequests) != 1 || len(executor.profileRequests) != 0 || executor.executeRequests != 0 {
t.Fatalf("prompt/profile/execute requests = %#v/%#v/%d", executor.promptRequests, executor.profileRequests, executor.executeRequests)
}
}
type inspectionPromptRequest struct {
id string
version string
@@ -143,6 +233,7 @@ type inspectionExecutor struct {
promptErr error
promptRequests []inspectionPromptRequest
profileRequests []string
executeRequests int
}
func (e *inspectionExecutor) InspectPrompt(_ context.Context, id string, version string) (promptexec.PromptInspection, error) {
@@ -166,6 +257,7 @@ func (e *inspectionExecutor) InspectProfile(_ context.Context, id string) (promp
}
func (e *inspectionExecutor) Execute(context.Context, promptexec.ExecuteRequest, promptexec.PreparationCallback) (*promptexec.Execution, error) {
e.executeRequests++
return nil, errors.New("unexpected execution")
}