Keysat
2b0abad68e
Add a single-session AI flow alongside program generation: describe a
workout in plain words and get a ready-to-log workout back — exercises
with suggested weights, target reps, and set counts grounded in the
user's recent history. The suggestion can be inline-edited or refined
by sending a follow-up instruction back to the model, then "Use this
workout" pre-fills the normal New Workout form (nothing persists until
the user saves through the regular path).
Why reuse, not fork: the existing program-generation spine (detached
background runner, SSE streaming, lenient-JSON preview, 5 providers,
history context, library name->id mapping) already does the hard parts.
A new AIGeneration.kind discriminant ("program" | "workout", default
"program" via boot-time guarded ALTER) selects the parser and keeps the
ephemeral workout rows out of the program-shaped AI history. Refine is a
fresh generation seeded with the prior suggestion (validated through the
same schema before it re-enters the prompt).
Hand-off is sessionStorage -> /main/workouts/new?from=ai -> AiWorkoutPrefill,
which expands each suggestion into N sets and maps effort by cardio-ness
(Gear for cardio, RPE for strength). EditWorkoutData.id is now optional so
the prefill CREATEs rather than PATCHing a nonexistent id. The AI suggests
each weight in that exercise's effective logging unit (the library JSON
carries a per-exercise unit) so the stored number and unit never diverge.
Built + sideloaded to immense-voyage.local as 1.2.0:6; on-box ALTER and
non-root launch confirmed via start-cli. tsc clean (app + packaging),
251 tests pass, next build + s9pk build succeed.
69 lines
3.9 KiB
Markdown
69 lines
3.9 KiB
Markdown
---
|
|
paths:
|
|
- proof-of-work/lib/ai/**
|
|
- proof-of-work/app/api/ai/**
|
|
---
|
|
|
|
# AI subsystem
|
|
|
|
Scoped guidance for the AI generation subsystem (`proof-of-work/lib/ai/**` and the
|
|
generate/generations route handlers). Whole-repo rules live in `AGENTS.md`.
|
|
|
|
## Architecture
|
|
|
|
- `generate/route.ts` kicks off a **detached background runner** (`generationRunner.ts`)
|
|
and returns an id; the client attaches via SSE (`generations/[id]/stream`) and can also
|
|
poll the row. Navigating away does NOT cancel generation.
|
|
- System prompt = `systemPromptBase.ts` (output contract: JSON-only, library
|
|
`exerciseId`s only, suggested weights) + the template's coaching prompt +
|
|
`PROGRAM_OUTPUT_SHAPE` + library + optional history block (`historyContext.ts`).
|
|
- Multi-config: `AIConfigProfile` rows per user; `UserPreferences.activeAIConfigId`
|
|
points at the active one and is mirrored into the legacy `ai*` columns for back-compat.
|
|
|
|
## Two generation kinds (`AIGeneration.kind`)
|
|
|
|
The runner spine is shared by two output shapes, discriminated by `AIGeneration.kind`
|
|
("program" | "workout", default "program"). The runner picks the parser by kind and
|
|
stores the JSON in the (reused) `parsedProgram` column.
|
|
|
|
- **program** (`kind: 'program'`) — `generate/route.ts` → `programSchema.ts`
|
|
(`PROGRAM_OUTPUT_SHAPE` / `parseAIProgram`). Applied to DB rows via `apply.ts`.
|
|
Shown in AI · History (which filters `kind: 'program'`).
|
|
- **workout** (`kind: 'workout'`) — `generate-workout/route.ts` (uses
|
|
`workoutPrompt.ts` + `workoutSchema.ts`: `WORKOUT_OUTPUT_SHAPE` / `parseAIWorkout`).
|
|
A single day's session. **No server-side apply**: the client (`GenerateWorkoutClient.tsx`)
|
|
stashes the reviewed suggestion in `sessionStorage` and routes to
|
|
`/main/workouts/new?from=ai`, where `AiWorkoutPrefill.tsx` expands it (via
|
|
`workoutDraft.ts::buildPrefillExercises`) and pre-fills the normal `WorkoutForm` —
|
|
nothing persists until the user saves through the regular workout path.
|
|
**Refine = a new workout generation** seeded with the prior suggestion JSON
|
|
(`priorWorkout` in the route body → REVISION mode in `workoutPrompt.ts`). These rows
|
|
are ephemeral, so they're excluded from the program-shaped AI · History.
|
|
- Adding a new kind: extend the union in `KickoffOpts`, add a parser + output-shape,
|
|
branch the parser selection in `generationRunner.ts`, and decide whether it belongs in
|
|
History (filtered by kind).
|
|
|
|
## Provider abstraction
|
|
|
|
- Each provider yields an async iterable of `GenerateChunk` (`text` / `usage` / `done` /
|
|
`error`); add new ones under `lib/ai/providers/` and register in `index.ts`.
|
|
`openai.ts` exports both `openai` and `openai-compatible`, so the four provider files
|
|
register **5** providers (`claude`, `openai`, `openai-compatible`, `gemini`, `ollama`).
|
|
- Streaming AI uses SSE; partial JSON is recovered with `lib/ai/lenientJson.ts`.
|
|
- Pricing/model menus live in `lib/ai/pricing.ts` (`PRICES`, `MODEL_MENU`) — keep them
|
|
paired so every menu model has a price entry (there's a test enforcing this).
|
|
|
|
## SSRF / provider-URL safety
|
|
|
|
- Any `fetch` to a user-supplied provider base URL MUST go through
|
|
`assertSafeProviderUrl` (`lib/ai/safeUrl.ts`) first — it enforces http(s) and blocks
|
|
link-local/cloud-metadata (169.254/16, fe80::/10) + unspecified. **Private-LAN +
|
|
loopback are allowed on purpose** (reaching `ollama.startos`/LAN gateways is the
|
|
feature). Currently wired into `providers/ollama.ts`, the `openai-compatible` path in
|
|
`providers/openai.ts` (NOT the fixed `api.openai.com` path), and the `ai/ollama/models`
|
|
probe. Add the guard to any new user-URL fetch path.
|
|
- Custom-URL providers (those with `requiresBaseUrl`: ollama, openai-compatible) are
|
|
**admin-only** — `isCustomUrlProvider` gates `ai/configs` POST + `[id]` PATCH + `ai/test`,
|
|
and `ai/ollama/models` is fully admin-only. The Settings UI hides them from non-admins.
|
|
This is a second defense layer on top of the IP block; keep both when adding routes.
|