Move prompts into embedded Markdown assets

internal/modules/glossary/module.go

@@ -60,11 +60,18 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
 		Glossary:          req.Glossary,
 		Config:            req.Config,
 		Messages:          messages,
-		StageName:         proposalStageName(req),
-		StartIndex:        0,
-		LLMClient:         req.LLMClient,
-		Scheduler:         req.LLMScheduler,
-		DiagnosticsDir:    req.DiagnosticsDir,
+		PromptMetadata: map[string]any{
+			"prompt_id":      proposalPromptMetadata().PromptID,
+			"prompt_version": proposalPromptMetadata().PromptVersion,
+			"prompt_source":  proposalPromptMetadata().PromptSource,
+			"embedded_path":  proposalPromptMetadata().EmbeddedPath,
+			"sha256":         proposalPromptMetadata().SHA256,
+		},
+		StageName:      proposalStageName(req),
+		StartIndex:     0,
+		LLMClient:      req.LLMClient,
+		Scheduler:      req.LLMScheduler,
+		DiagnosticsDir: req.DiagnosticsDir,
 	})
 	if err != nil {
 		return nil, err

internal/modules/glossary/prompt.go

@@ -7,6 +7,7 @@ import (
 	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/promptcontext"
+	"gitea.maximumdirect.net/eric/audita/internal/prompts"
 )
 
 type promptSegment struct {
@@ -50,33 +51,21 @@ func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Gloss
 		return nil, fmt.Errorf("marshal transcript prompt context: %w", err)
 	}
 
-	system := "You are Audita, a careful transcript correction assistant. Identify only transcription errors that are strongly supported by the glossary. A valid correction must be acoustically plausible: the original transcript text should sound similar to the proposed correction when spoken aloud. Do not make generic grammar, spelling, capitalization, style, or filler-word edits. Do not substitute an unrelated glossary term just because it could fit the topic. Preserve speaker names, timestamps, and meaning."
-	user := "Review this transcript section and return only glossary-supported corrections that should be applied.\n\n" +
-		"Rules:\n" +
-		"- Correct domain-specific names, aliases, jargon, deities, locations, NPCs, players, factions, and similar terms only when both the glossary and surrounding transcript context support the correction.\n" +
-		"- The correction must plausibly fix a transcription error: the original words should be phonetically or acoustically similar to the corrected words in spoken English.\n" +
-		"- Appropriate example: correcting \"gestures\" to \"Jesters\" can be valid if \"Jesters\" appears in the glossary and nearby context supports that inference.\n" +
-		"- Inappropriate example: correcting \"Lyra\" to \"Jesters\" should be omitted because those words are not similar in spoken English, even if \"Jesters\" appears in the glossary.\n" +
-		"- Do not replace one clear glossary term, character name, location, or ordinary word with a different glossary term unless it is a plausible mishearing.\n" +
-		"- Treat glossary names and aliases already present in the transcript as protected spellings.\n" +
-		"- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases away from their glossary spelling.\n" +
-		"- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.\n" +
-		"- If a segment includes categories, treat them as additional transcript context.\n" +
-		"- Plural forms of glossary names and aliases are allowed targets when spoken similarity and context support them, even if the plural is not explicitly listed in the glossary.\n" +
-		"- Use the exact id from the input segment.\n" +
-		"- For returned corrections, original_text must be only the exact text span that needs replacement, not the full segment text unless the whole segment is the replacement span.\n" +
-		"- corrected_text must be only the replacement text for that span, not the full corrected segment text unless the whole segment is the replacement span.\n" +
-		"- Each returned correction must contain only id, original_text, corrected_text, and confidence.\n" +
-		"- Do not return corrections where original_text and corrected_text are identical.\n" +
-		"- Do not return speaker, start, or end fields.\n" +
-		"- Return only changed segments; do not return entries for unchanged segments.\n" +
-		"- confidence must be between 0.0 and 1.0.\n" +
-		"- If no corrections are needed, return an empty corrections list.\n\n" +
-		promptcontext.TranscriptDescriptionBlock(transcriptDescription) +
-		fmt.Sprintf("Glossary:\n%s\n\nTranscript section:\n%s", string(glossaryJSON), string(sectionJSON))
+	system, user, _, err := prompts.RenderUserSystem(prompts.PromptIDModuleGlossaryProposal, map[string]string{
+		"TranscriptDescriptionBlock": promptcontext.TranscriptDescriptionBlock(transcriptDescription),
+		"GlossaryJSON":               string(glossaryJSON),
+		"SectionJSON":                string(sectionJSON),
+	})
+	if err != nil {
+		return nil, err
+	}
 
 	return []contracts.LLMMessage{
 		{Role: "system", Content: system},
 		{Role: "user", Content: user},
 	}, nil
 }
+
+func proposalPromptMetadata() prompts.Metadata {
+	return prompts.MustLookupMetadata(prompts.PromptIDModuleGlossaryProposal)
+}

internal/modules/grammar/module.go

@@ -60,11 +60,18 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
 		Glossary:          req.Glossary,
 		Config:            req.Config,
 		Messages:          messages,
-		StageName:         proposalStageName(req),
-		StartIndex:        0,
-		LLMClient:         req.LLMClient,
-		Scheduler:         req.LLMScheduler,
-		DiagnosticsDir:    req.DiagnosticsDir,
+		PromptMetadata: map[string]any{
+			"prompt_id":      proposalPromptMetadata().PromptID,
+			"prompt_version": proposalPromptMetadata().PromptVersion,
+			"prompt_source":  proposalPromptMetadata().PromptSource,
+			"embedded_path":  proposalPromptMetadata().EmbeddedPath,
+			"sha256":         proposalPromptMetadata().SHA256,
+		},
+		StageName:      proposalStageName(req),
+		StartIndex:     0,
+		LLMClient:      req.LLMClient,
+		Scheduler:      req.LLMScheduler,
+		DiagnosticsDir: req.DiagnosticsDir,
 	})
 	if err != nil {
 		return nil, err

internal/modules/grammar/prompt.go

@@ -7,6 +7,7 @@ import (
 	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/promptcontext"
+	"gitea.maximumdirect.net/eric/audita/internal/prompts"
 )
 
 type promptSegment struct {
@@ -53,35 +54,21 @@ func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Gloss
 		return nil, fmt.Errorf("marshal transcript prompt context: %w", err)
 	}
 
-	system := "You are Audita, a conservative grammar cleanup assistant. Identify only punctuation, capitalization, and spacing cleanup that preserves the same underlying words. Do not change content, substitute words, or rewrite the speaker's phrasing."
-	user := "Review this transcript section and return only grammar cleanup corrections that should be applied.\n\n" +
-		"Rules:\n" +
-		"- Allowed changes are punctuation, capitalization, spacing, and article cleanup only.\n" +
-		"- You may add, remove, or adjust commas, periods, quotation marks, apostrophes, dashes, ellipses, spacing, and capitalization when the underlying words stay the same.\n" +
-		"- You may change the whole-word article \"a\" to \"an\" or \"an\" to \"a\" when the surrounding text otherwise stays the same.\n" +
-		"- Homophone, spoken-form, and mistranscription corrections are handled during a later review stage; do not propose them here.\n" +
-		"- Do not make word substitutions, spelling fixes, homophone fixes, filler cleanup, repetition cleanup, paraphrases, or other semantic rewrites.\n" +
-		"- Do not change one written word into a different written word, except for capitalization changes to the same letters.\n" +
-		"- If a possible correction depends on changing a content word into a different word, omit it here rather than bundling it together with formatting cleanup.\n" +
-		"- Treat glossary names and aliases as protected spellings and context.\n" +
-		"- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases away from their glossary spelling.\n" +
-		"- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.\n" +
-		"- If a segment includes categories, treat them as additional transcript context.\n" +
-		"- Use the exact id from the input segment.\n" +
-		"- For returned corrections, original_text must be only the exact text span that needs replacement, not the full segment text unless the whole segment is the replacement span.\n" +
-		"- Choose an original_text span that appears exactly once in the current segment text.\n" +
-		"- corrected_text must be only the replacement text for that span, not the full corrected segment text unless the whole segment is the replacement span.\n" +
-		"- Each returned correction must contain only id, original_text, corrected_text, and confidence.\n" +
-		"- Do not return corrections where original_text and corrected_text are identical.\n" +
-		"- Do not return speaker, start, or end fields.\n" +
-		"- Return only changed segments; do not return entries for unchanged segments.\n" +
-		"- confidence must be between 0.0 and 1.0.\n" +
-		"- If no corrections are needed, return an empty corrections list.\n\n" +
-		promptcontext.TranscriptDescriptionBlock(transcriptDescription) +
-		fmt.Sprintf("Protected glossary/context:\n%s\n\nTranscript section:\n%s", string(glossaryJSON), string(sectionJSON))
+	system, user, _, err := prompts.RenderUserSystem(prompts.PromptIDModuleGrammarProposal, map[string]string{
+		"TranscriptDescriptionBlock": promptcontext.TranscriptDescriptionBlock(transcriptDescription),
+		"GlossaryJSON":               string(glossaryJSON),
+		"SectionJSON":                string(sectionJSON),
+	})
+	if err != nil {
+		return nil, err
+	}
 
 	return []contracts.LLMMessage{
 		{Role: "system", Content: system},
 		{Role: "user", Content: user},
 	}, nil
 }
+
+func proposalPromptMetadata() prompts.Metadata {
+	return prompts.MustLookupMetadata(prompts.PromptIDModuleGrammarProposal)
+}

internal/modules/homophones/module.go

@@ -60,11 +60,18 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
 		Glossary:          req.Glossary,
 		Config:            req.Config,
 		Messages:          messages,
-		StageName:         proposalStageName(req),
-		StartIndex:        0,
-		LLMClient:         req.LLMClient,
-		Scheduler:         req.LLMScheduler,
-		DiagnosticsDir:    req.DiagnosticsDir,
+		PromptMetadata: map[string]any{
+			"prompt_id":      proposalPromptMetadata().PromptID,
+			"prompt_version": proposalPromptMetadata().PromptVersion,
+			"prompt_source":  proposalPromptMetadata().PromptSource,
+			"embedded_path":  proposalPromptMetadata().EmbeddedPath,
+			"sha256":         proposalPromptMetadata().SHA256,
+		},
+		StageName:      proposalStageName(req),
+		StartIndex:     0,
+		LLMClient:      req.LLMClient,
+		Scheduler:      req.LLMScheduler,
+		DiagnosticsDir: req.DiagnosticsDir,
 	})
 	if err != nil {
 		return nil, err

internal/modules/homophones/prompt.go

@@ -7,6 +7,7 @@ import (
 	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/promptcontext"
+	"gitea.maximumdirect.net/eric/audita/internal/prompts"
 )
 
 type promptSegment struct {
@@ -52,34 +53,21 @@ func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Gloss
 		return nil, fmt.Errorf("marshal transcript prompt context: %w", err)
 	}
 
-	system := "You are Audita, a conservative homophone correction assistant. Identify only transcript changes that plausibly reflect homophones, phonetic similarity, or common mistranscriptions of spoken English. Do not make punctuation, capitalization, spacing, filler-word, repetition, style, or grammar edits. Do not paraphrase, summarize, or rewrite content."
-	user := "Review this transcript section and return only homophone or spoken-form corrections that should be applied.\n\n" +
-		"Rules:\n" +
-		"- Approve only corrections where the original text is plausibly a mistaken homophone, phonetic rendering, or mistranscription of what was likely spoken.\n" +
-		"- Allow examples such as changing \"dam\" to \"damn\", \"rank\" to \"Hrank\", or \"gestures\" to \"Jesters\" when local context supports the correction.\n" +
-		"- Reject unrelated substitutions like changing \"Lyra\" to \"Jesters\".\n" +
-		"- Reject antonyms or reversals such as changing \"visible\" to \"invisible\".\n" +
-		"- Do not add or remove punctuation, alter capitalization only, normalize spacing, remove filler words, collapse repetitions, or make general readability edits.\n" +
-		"- Treat glossary names and aliases as protected spellings and context.\n" +
-		"- You may correct toward glossary names, aliases, or their plural forms when the correction is acoustically plausible and supported by local context.\n" +
-		"- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases that already appear correctly in the transcript.\n" +
-		"- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.\n" +
-		"- If a segment includes categories, treat them as additional transcript context.\n" +
-		"- Use the exact id from the input segment.\n" +
-		"- For returned corrections, original_text must be only the exact text span that needs replacement, not the full segment text unless the whole segment is the replacement span.\n" +
-		"- Choose an original_text span that appears exactly once in the current segment text.\n" +
-		"- corrected_text must be only the replacement text for that span, not the full corrected segment text unless the whole segment is the replacement span.\n" +
-		"- Each returned correction must contain only id, original_text, corrected_text, and confidence.\n" +
-		"- Do not return corrections where original_text and corrected_text are identical.\n" +
-		"- Do not return speaker, start, or end fields.\n" +
-		"- Return only changed segments; do not return entries for unchanged segments.\n" +
-		"- confidence must be between 0.0 and 1.0.\n" +
-		"- If no corrections are needed, return an empty corrections list.\n\n" +
-		promptcontext.TranscriptDescriptionBlock(transcriptDescription) +
-		fmt.Sprintf("Protected glossary/context:\n%s\n\nTranscript section:\n%s", string(glossaryJSON), string(sectionJSON))
+	system, user, _, err := prompts.RenderUserSystem(prompts.PromptIDModuleHomophonesProposal, map[string]string{
+		"TranscriptDescriptionBlock": promptcontext.TranscriptDescriptionBlock(transcriptDescription),
+		"GlossaryJSON":               string(glossaryJSON),
+		"SectionJSON":                string(sectionJSON),
+	})
+	if err != nil {
+		return nil, err
+	}
 
 	return []contracts.LLMMessage{
 		{Role: "system", Content: system},
 		{Role: "user", Content: user},
 	}, nil
 }
+
+func proposalPromptMetadata() prompts.Metadata {
+	return prompts.MustLookupMetadata(prompts.PromptIDModuleHomophonesProposal)
+}

internal/modules/spoken_word/module.go

@@ -60,11 +60,18 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
 		Glossary:          req.Glossary,
 		Config:            req.Config,
 		Messages:          messages,
-		StageName:         proposalStageName(req),
-		StartIndex:        0,
-		LLMClient:         req.LLMClient,
-		Scheduler:         req.LLMScheduler,
-		DiagnosticsDir:    req.DiagnosticsDir,
+		PromptMetadata: map[string]any{
+			"prompt_id":      proposalPromptMetadata().PromptID,
+			"prompt_version": proposalPromptMetadata().PromptVersion,
+			"prompt_source":  proposalPromptMetadata().PromptSource,
+			"embedded_path":  proposalPromptMetadata().EmbeddedPath,
+			"sha256":         proposalPromptMetadata().SHA256,
+		},
+		StageName:      proposalStageName(req),
+		StartIndex:     0,
+		LLMClient:      req.LLMClient,
+		Scheduler:      req.LLMScheduler,
+		DiagnosticsDir: req.DiagnosticsDir,
 	})
 	if err != nil {
 		return nil, err

internal/modules/spoken_word/module_test.go

@@ -89,7 +89,6 @@ func TestBuildProposalMessagesContainsContextAndMeaningGuardrails(t *testing.T)
 	}
 	for _, forbidden := range []string{
 		"style rewriting",
-		"invent",
 		"grammar-only cleanup",
 		"punctuation-only cleanup",
 	} {

internal/modules/spoken_word/prompt.go

@@ -7,6 +7,7 @@ import (
 	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/promptcontext"
+	"gitea.maximumdirect.net/eric/audita/internal/prompts"
 )
 
 type promptSegment struct {
@@ -52,37 +53,21 @@ func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Gloss
 		return nil, fmt.Errorf("marshal transcript prompt context: %w", err)
 	}
 
-	system := "You are Audita, a conservative spoken-word cleanup assistant. Identify only low-risk cleanup of repeated words or short phrases, filler words, hesitation artifacts, and similar dysfluencies that commonly appear in spoken English transcripts. Preserve substantive meaning, named entities, and transcript content."
-	user := "Review this transcript section and return only spoken-word cleanup corrections that should be applied.\n\n" +
-		"Rules:\n" +
-		"- Approve only conservative cleanup of repeated words, repeated short phrases, filler words, hesitation artifacts, and similar spoken dysfluencies.\n" +
-		"- You may collapse adjacent repetition such as \"I I think\" to \"I think\" or remove filler spans such as \"you know\" or \"uh\" when local context supports that cleanup.\n" +
-		"- Do not collapse repeated words or short phrases when the repetition plausibly expresses urgency, excitement, insistence, or deliberate rhetorical emphasis rather than dysfluency.\n" +
-		"- Phrases such as \"Help! Help! Help!\", \"Stop! Stop! Stop!\", \"No! No! No!\", \"Yes! Yes! Yes!\", and \"Go! Go! Go!\" are often intentional emphasis and should usually be preserved.\n" +
-		"- Only collapse repetition when local context supports it as accidental spoken repetition, hesitation, or verbal restart.\n" +
-		"- You may include low-risk punctuation, spacing, or capitalization cleanup when it is part of removing a dysfluency, such as removing ellipses or hesitation punctuation that no longer belongs after the cleanup.\n" +
-		"- Do not paraphrase, summarize, reorder ideas, replace content with different wording, or make substantive semantic edits.\n" +
-		"- Do not change clear content words just because a different phrasing reads better.\n" +
-		"- Do not convert uncertain statements into certain statements.\n" +
-		"- Treat glossary names and aliases as protected spellings and context.\n" +
-		"- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases that already appear correctly in the transcript.\n" +
-		"- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.\n" +
-		"- If a segment includes categories, treat them as additional transcript context.\n" +
-		"- Use the exact id from the input segment.\n" +
-		"- For returned corrections, original_text must be only the exact text span that needs replacement, not the full segment text unless the whole segment is the replacement span.\n" +
-		"- Choose an original_text span that appears exactly once in the current segment text.\n" +
-		"- corrected_text must be only the replacement text for that span, not the full corrected segment text unless the whole segment is the replacement span.\n" +
-		"- Each returned correction must contain only id, original_text, corrected_text, and confidence.\n" +
-		"- Do not return corrections where original_text and corrected_text are identical.\n" +
-		"- Do not return speaker, start, or end fields.\n" +
-		"- Return only changed segments; do not return entries for unchanged segments.\n" +
-		"- confidence must be between 0.0 and 1.0.\n" +
-		"- If no corrections are needed, return an empty corrections list.\n\n" +
-		promptcontext.TranscriptDescriptionBlock(transcriptDescription) +
-		fmt.Sprintf("Protected glossary/context:\n%s\n\nTranscript section:\n%s", string(glossaryJSON), string(sectionJSON))
+	system, user, _, err := prompts.RenderUserSystem(prompts.PromptIDModuleSpokenWordProposal, map[string]string{
+		"TranscriptDescriptionBlock": promptcontext.TranscriptDescriptionBlock(transcriptDescription),
+		"GlossaryJSON":               string(glossaryJSON),
+		"SectionJSON":                string(sectionJSON),
+	})
+	if err != nil {
+		return nil, err
+	}
 
 	return []contracts.LLMMessage{
 		{Role: "system", Content: system},
 		{Role: "user", Content: user},
 	}, nil
 }
+
+func proposalPromptMetadata() prompts.Metadata {
+	return prompts.MustLookupMetadata(prompts.PromptIDModuleSpokenWordProposal)
+}