Convert embedded prompts to keyed format

docs/roadmap/implementation.md

@@ -1,7 +1,7 @@
 # Implementation Plan: PromptKit v0.12.0 Adoption
 
 **Last updated:** 2026-10-03
-**Status:** Ready for implementation; no stages completed.
+**Status:** In progress; Stage 1 completed.
 **Audience:** Luna coding agent.
 
 ## Scope and Execution
@@ -107,6 +107,10 @@ version keys against `RegisteredMetadata`, and run `git diff --check`. Registry
 preparation tests become runnable with the new constructor in Stage 3. Commit
 the asset conversion; do not introduce an old-format reader to test it here.
 
+**Completion marker:** Stage 1 complete. All seven registered prompt assets
+use keyed prompt/version mappings; parsed definitions were structurally checked
+against their prior content, and `git diff --check` passed.
+
 ## Stage 2 — Migrate Operator Profiles, Example Roots, and YAML Fixtures
 
 **Primary files:** `examples/profiles/`, the three maintained configuration

internal/prompts/assets/prompts/modules.glossary.proposal.yaml

@@ -1,6 +1,7 @@
-id: modules.glossary.proposal
+prompts:
-version: v1
+  modules.glossary.proposal:
-messages:
+    v1:
+      messages:
         - role: system
           content: |
             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.
@@ -31,7 +32,7 @@ messages:
 
             Transcript section:
             {{ .SectionJSON }}
-output:
+      output:
         format: json
         validation_mode: json_schema
         schema_path: correction_set.v1.json

internal/prompts/assets/prompts/modules.grammar.proposal.yaml

@@ -1,6 +1,7 @@
-id: modules.grammar.proposal
+prompts:
-version: v1
+  modules.grammar.proposal:
-messages:
+    v1:
+      messages:
         - role: system
           content: |
             You are Audita, a conservative grammar cleanup assistant. Identify only punctuation, capitalization, and spacing cleanup that preserves the same underlying words. The only word-substitution exception is the whole-word article "a"/"an" correction described below; otherwise do not change content, substitute words, or rewrite the speaker's phrasing.
@@ -34,7 +35,7 @@ messages:
 
             Transcript section:
             {{ .SectionJSON }}
-output:
+      output:
         format: json
         validation_mode: json_schema
         schema_path: correction_set.v1.json

internal/prompts/assets/prompts/modules.homophones.proposal.yaml

@@ -1,6 +1,7 @@
-id: modules.homophones.proposal
+prompts:
-version: v1
+  modules.homophones.proposal:
-messages:
+    v1:
+      messages:
         - role: system
           content: |
             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.
@@ -31,7 +32,7 @@ messages:
 
             Transcript section:
             {{ .SectionJSON }}
-output:
+      output:
         format: json
         validation_mode: json_schema
         schema_path: correction_set.v1.json

internal/prompts/assets/prompts/modules.spoken_word.proposal.yaml

@@ -1,6 +1,7 @@
-id: modules.spoken_word.proposal
+prompts:
-version: v1
+  modules.spoken_word.proposal:
-messages:
+    v1:
+      messages:
         - role: system
           content: |
             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.
@@ -36,7 +37,7 @@ messages:
 
             Transcript section:
             {{ .SectionJSON }}
-output:
+      output:
         format: json
         validation_mode: json_schema
         schema_path: correction_set.v1.json

internal/prompts/assets/prompts/validators.editorial_review.yaml

@@ -1,6 +1,7 @@
-id: validators.editorial_review
+prompts:
-version: v1
+  validators.editorial_review:
-messages:
+    v1:
+      messages:
         - role: system
           content: |
             You are Audita, a conservative editorial validation assistant. Evaluate whether each proposed correction is editorial in nature and preserves the segment's underlying meaning. Editorial revisions may include dysfluency cleanup, punctuation changes, capitalization changes, homophone or mistranscription corrections, and similar low-risk editorial cleanup.
@@ -28,7 +29,7 @@ messages:
 
             {{ .TranscriptDescriptionBlock }}Corrections to validate:
             {{ .PayloadJSON }}
-output:
+      output:
         format: json
         validation_mode: json_schema
         schema_path: validator_decision_set.v1.json

internal/prompts/assets/prompts/validators.meaning_reversal_review.yaml

@@ -1,6 +1,7 @@
-id: validators.meaning_reversal_review
+prompts:
-version: v1
+  validators.meaning_reversal_review:
-messages:
+    v1:
+      messages:
         - role: system
           content: |
             You are Audita, a narrow semantic-reversal validation assistant. Evaluate whether each proposed correction changes a word to its antonym or otherwise reverses the meaning of the full segment. Do not treat every word substitution as a problem; focus specifically on antonyms and meaning reversals.
@@ -24,7 +25,7 @@ messages:
 
             {{ .TranscriptDescriptionBlock }}Corrections to validate:
             {{ .PayloadJSON }}
-output:
+      output:
         format: json
         validation_mode: json_schema
         schema_path: validator_decision_set.v1.json

internal/prompts/assets/prompts/validators.spoken_form_plausibility.yaml

@@ -1,6 +1,7 @@
-id: validators.spoken_form_plausibility
+prompts:
-version: v1
+  validators.spoken_form_plausibility:
-messages:
+    v1:
+      messages:
         - role: system
           content: |
             You are Audita, a conservative spoken-form validation assistant. Evaluate whether each proposed correction is plausibly explained by a homophone, phonetic similarity, or a common mistranscription of spoken English. Your job is not to improve style or readability. Approve only when the corrected text is a plausible recovery of the words that were likely spoken.
@@ -23,7 +24,7 @@ messages:
 
             {{ .TranscriptDescriptionBlock }}Corrections to validate:
             {{ .PayloadJSON }}
-output:
+      output:
         format: json
         validation_mode: json_schema
         schema_path: validator_decision_set.v1.json