FE-698: Prompt/context scenario substrate foundation#111
Conversation
lunelson
force-pushed
the
ln/fe-698-slice-d
branch
from
3fef067 to
e431537
Compare
lunelson
force-pushed
the
ln/fe-698-slice-e
branch
from
01453e6 to
b4fa6b9
Compare
graphite-app
Bot
changed the base branch from
ln/fe-698-slice-d
to
graphite-base/111
lunelson
force-pushed
the
ln/fe-698-slice-e
branch
from
b4fa6b9 to
ec24cc4
Compare
lunelson
force-pushed
the
graphite-base/111
branch
from
e431537 to
9400c1e
Compare
lunelson
changed the title
PR SummaryMedium Risk Overview Expands the scenario runner from Adds a probe-only execution path for Reviewed by Cursor Bugbot for commit 0fb5687. Bugbot is set up for automated code reviews on this repo. Configure here. |
🤖 Augment PR SummarySummary: Establishes the FE-698 “prompt/context scenario substrate” foundation so prompt + context engineering becomes explicit, typed, and probeable before broader agent-heavy productization. Changes:
Technical Notes: Scenarios intentionally remain “probe/review artifacts” (proposal-only / not durable truth), while capability metadata and prompt asset provenance are captured to keep future agent surfaces consistent. 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 2fd4282. Configure here.
lunelson
force-pushed
the
ln/fe-698-slice-e
branch
from
bbb63ab to
27de9e2
Compare
lunelson
force-pushed
the
ln/fe-698-slice-e
branch
from
99cc970 to
0fb5687
Compare
kostandinang
left a comment
kostandinang
left a comment
There was a problem hiding this comment.
Check the failing test
| - [2026-05-07] FE-698 prompt/context foundation slices — Packaged markdown prompt registry + observer and web-research context-pack foundations + scenario runner capture skeleton/composition + agent mutation-surface audit + capability registry metadata. Server interviewer, observer, side-chat, and web-research role prompts now load from markdown assets through a typed prompt registry; observer capture and web-research probes render typed scenario-specific context packs; seeded prompt scenarios compose production prompts with typed context-pack output into deterministic no-provider probe artifacts; and scenario artifacts can declare validated Brunch capability contracts. Review fixes moved observer prompt composition into a pure module and made prompt scenario prompt sources explicit. The agent mutation-surface audit inventories current and projected agent-originated write paths as input to later handler slices. Verified: `npm run verify` for code slices; audit verified by code-search/document consistency. This is a completed foundation within FE-698, not retirement of the whole FE-698 frontier; the live continuation remains in `Next`. | ||
| - [2026-05-07] Side-chat V2 — Edit / Drill-down / Propose-edge plumbing (FE-673, PR #97) — added `edit`, `edge`, and `drill-down` patch kinds. Server `classifyEditImpact` returns `none | soft | hard`; soft applies directly with undo, hard returns `deferred: true` placeholder. Client: patch-list reducer + three applier factories with real undo handlers. Verified: `npm run verify` (935 tests, 19 new). Watch: `SideChatPopover` Edit button stays `disabled` and hard-impact deferred banner is live until V3.0 lands. | ||
| - [2026-05-06] Multi-chat substrate + reconciliation needs (FE-697) — `chat` table with one interview chat per spec, nullable `turn.chat_id`, `specification.primary_chat_id`, mirrored `chat.active_turn_id`, plus the `reconciliation_need` queue with directed source/target items, narrow `kind`/`status`, partial unique index on open rows, cascade FK. Spec creation inserts spec + interview chat in one transaction; `advanceHead` is transactional. No user-visible change. Verified: `npm run verify` (673 tests) plus manual fixture playback (39 specs / 81 turns / dual-pointer equivalence). A82 / A83 validated for Phase 1. | ||
| - [2026-05-01] Side-chat V1.1 — Explore vertical slice. End-to-end graph-launched chat interaction shipped: prompt builder, POST `/side-chat` SSE endpoint, popover host, graph-view wiring, SSE consumer, and active-button activation. Follow-up refactor collapsed pending assistant text into the message list and extracted `SideChatHost` so activation is a tree-mount fact. This is complete implementation history; future conceptual work is multi-chat / reconciliation, not Side-chat V2/V3. |
There was a problem hiding this comment.
Side-chat V1.1 appears twice like a duplicate paste; worth deleting one so history stays single-source.
| mkdirSync(sourceDir); | ||
| mkdirSync(destinationDir); | ||
|
|
||
| copyServerPromptAssets(sourceDir, destinationDir); |
There was a problem hiding this comment.
imports copyServerPromptAssets from ../../vite.config.js, but neither vite.config.ts nor
config/vite-server-runtime.ts exports such a symbol.
Seeing
TypeError: copyServerPromptAssets is not a function
❯ src/server/prompt-build-boundary.test.ts:20:5
18| mkdirSync(destinationDir);
19|
20| copyServerPromptAssets(sourceDir, destinationDir);
| ^
21| writeFileSync(join(destinationDir, '[stale-prompt.md](http://stale-prompt.md)'), 'removed');
22| writeFileSync(join(sourceDir, '[current-prompt.md](http://current-prompt.md)'), 'current'); 2 participants
Stack Context
This PR is the FE-698 prompt/context scenario substrate foundation. It makes prompt and context engineering explicit and testable before productizing more agent-heavy surfaces such as web research, candidate-spec assist, behavioral kernels, architect proposals, or post-spec decomposition probes.
What?
context-pack.tsinto a public mini-library backed by private scenario-specific modules.Why?
FE-698 is meant to prevent future agent features from each inventing their own prompt/context path. This PR establishes the shared substrate while keeping provider credential UX, production provider routing, UI, persistence, Pi integration, and durable Brunch mutations out of scope.
Candidate-spec and other generative scenario outputs are intentionally review/probe artifacts, not accepted graph truth. Future agent-originated writes should go through Brunch-owned mutation handlers / changeset surfaces rather than direct ORM or ad hoc tool calls.
Verification
npm run verify