coilyco-flight-deck/voice-flow-learning-loop
Archived
1
0
Fork 0
Code Issues 11 Pull requests Projects Releases Packages Wiki Activity Actions

Loop 2 layer 7: trigger-name proposals via LLM #7

New issue
Open
opened 2026-05-23 20:55:37 +00:00 by coilysiren · 0 comments
coilysiren commented 2026-05-23 20:55:37 +00:00
Owner
Copy link

Originally filed by @coilysiren on 2026-05-20T12:01:07Z - https://github.com/coilysiren/voice-flow-learning-loop/issues/10

Context

Layer 7 of the 8-layer build path for Loop 2 documented in README.md.

Goal

For each top candidate, propose 2-3 trigger phrases via LLM. Constraints on triggers:

  • Short (2-3 words).
  • Acoustically distinct from natural speech (the trigger itself should not look like something Kai would say in non-snippet context).
  • Avoid known-mangle-prone tokens. The voice-mangle log corpus (Loop 1's structured blocks indexed by repo-recall) is the authoritative source for "words that mangle when Kai dictates them" — pull from there and exclude.
  • Non-conflicting with other proposed triggers in this batch.
  • Memorable.

Kai picks one or writes her own. The model proposes; she decides.

Done when

  • The Luca route emits 2-3 trigger proposals per candidate.
  • Proposals exclude tokens listed in the Loop 1 voice-mangle log corpus.
  • Conflict detection within a batch (proposed trigger A doesn't collide with proposed trigger B).

Depends on: layer 6 (clean candidate set) and Loop 1's voice-mangle log corpus (.claude/skills/writing-voice-mangle-log/SKILL.md + repo-recall's indexed blocks). Unblocks: layer 8.

_Originally filed by @coilysiren on 2026-05-20T12:01:07Z - [https://github.com/coilysiren/voice-flow-learning-loop/issues/10](https://github.com/coilysiren/voice-flow-learning-loop/issues/10)_ **Context** Layer 7 of the 8-layer build path for Loop 2 documented in [README.md](../blob/main/README.md). **Goal** For each top candidate, propose 2-3 trigger phrases via LLM. Constraints on triggers: - Short (2-3 words). - Acoustically distinct from natural speech (the trigger itself should not look like something Kai would say in non-snippet context). - Avoid known-mangle-prone tokens. The voice-mangle log corpus (Loop 1's structured blocks indexed by repo-recall) is the authoritative source for "words that mangle when Kai dictates them" — pull from there and exclude. - Non-conflicting with other proposed triggers in this batch. - Memorable. Kai picks one or writes her own. The model proposes; she decides. **Done when** - The Luca route emits 2-3 trigger proposals per candidate. - Proposals exclude tokens listed in the Loop 1 voice-mangle log corpus. - Conflict detection within a batch (proposed trigger A doesn't collide with proposed trigger B). **Depends on:** layer 6 (clean candidate set) and Loop 1's voice-mangle log corpus (`.claude/skills/writing-voice-mangle-log/SKILL.md` + repo-recall's indexed blocks). **Unblocks:** layer 8.
coilysiren added
P3
 and removed
P2
 labels 2026-05-31 07:01:25 +00:00
Commenting is not possible because the repository is archived.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels
  
P0
now / blocking / urgent

  
P1
next / important

  
P2
backlog / will do

  
P3
someday / low

  
P4
icebox / frozen / reopen if it becomes real

No labels
P0
P1
P2
P3
P4
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
coilyco-flight-deck/voice-flow-learning-loop#7
No description provided.