FE-1624: Implement split-ownership Voice conversations with Brunch - #9571
Draft
kostandinang wants to merge 2 commits into
Draft
Conversation
Amp-Thread-ID: https://ampcode.com/threads/T-01a07d12-9d2b-730f-a20f-b2ba85ca102f Co-authored-by: Amp <amp@ampcode.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
2 Skipped Deployments
|
Amp-Thread-ID: https://ampcode.com/threads/T-01a07d12-9d2b-730f-a20f-b2ba85ca102f Co-authored-by: Amp <amp@ampcode.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
🌟 What is the purpose of this PR?
Prepare split-ownership Voice conversations: Brunch retains domain strategy and validation, Realtime handles permitted conversational delivery, Flue owns the canonical conversation, and Petrinaut owns safe tool execution.
This draft is planning-only. It preserves the provisional design and presents a bounded mission-conversion proposal for owner approval. It does not change product behavior or promote the inherited accepted Mission 6b authority. Source inspection found no supported persistence-only external dialogue recorder in Flue 2.0.3 or the inspected upstream HEAD; dependent implementation is blocked rather than replaced with a sidecar.
🔗 Related links
🚫 Blocked by
The latter two gates block product implementation, not review of this planning packet.
🔍 What does this change?
MISSION.mdor changing product code.🏗️ Agent notes
Kostandin Angjellari authorized a new successor issue and draft PR stacked directly on #9564. FE-1624 and branch
kostandin/fe-1624-split-ownership-voiceform that successor. The original local checkout and its uncommitted design/spine remain intact. No parent or sibling branch was rewritten;gh stackwas unavailable, so the Git branch starts at the exact parent head and this PR explicitly targets its branch.There is no new live mission yet. The six-address candidate conversion is in the proposal. Its initial prerequisite is supported no-wake recording; the separately approved product stage is one Brunch delegation → two recorded Realtime exchanges → one structured agent-authored handback referencing originals → Brunch-validated workpiece update → fresh-process reconstruction. Integrated recovery and safety gates follow before readiness; the first tracer is not architecture completion.
Protect causal per-step client results, mixed server/browser topology, staggered sibling tools, effect-replay batching, explicit human evidence, conversation-owned callbacks, coherent-state refusal, and no autoplay. The current
runbook-irselector must not promote newly recorded Realtime assistant text to Brunch workpiece authority.Flue signals can carry non-human waking handbacks, but cannot substitute for persistence-only dialogue. Caller-supplied authorship attributes need application enforcement. Public abort leaves settled submissions untouched and does not durably cancel pending browser operations. Speech interruption and durable Stop remain separate; effect/receipt gaps require reconciliation rather than an exactly-once claim.
The detailed plan names stage owners, targeted package commands, real built-runtime tests, browser/media witnesses, no-wake/attribution/identity/staleness/modality/interleaving/partial-effect/recovery discriminators, and explicit no-paid-campaign gates. It preserves remaining architecture obligations in their planning homes rather than silently treating the first stage as completion.
Pre-Merge Checklist 🚀
🚢 Has this modified a publishable library?
This PR:
📜 Does this require a change to the docs?
The changes in this PR:
🕸️ Does this require a change to the Turbo Graph?
The changes in this PR:
🐾 Next steps
Review the bounded conversion envelope. Resolve the supported recording prerequisite, then commit owner-approved authority separately before dependent code. Preserve the remaining design obligations through each later gate.
🛡 What tests cover this?
MISSION.md, and byte-identical preservation of the source design.git diff --checkpasses.❓ How to test this?
MISSION.mdis identical to the parent, remaining architecture obligations retain planning homes, and no product readiness or paid-run claim is made.📹 Demo
Not applicable: this is a planning-only review packet with no UI change.