eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Move prompts into embedded Markdown assets

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-13 18:49:06 +00:00
parent d6126bf52b
commit 037121e9ce
43 changed files with 940 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
internal/modules/grammar/module.go
View File

@@ -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

39
internal/modules/grammar/prompt.go
View File

@@ -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)
}