feat(models): BYOK all the way down — factory pins deleted, per-need refusal gates
Owner decision 2026-09-22: 'it doesn't make sense to have any default
model configured anywhere; the application is bring your own keys.'
config.ts: MODELS deleted; ModelRole becomes an explicit 9-role union;
DEFAULT_THINKING_ORDER (medium, low, high, minimal, xhigh, max) bakes
the unset-level default — first entry the model supports; explicitly
set levels keep pi's native nearest-clamp.
core/settings-resolution: the factory layer dissolves — the chain is
role override → slot → NOTHING. resolveSettings(record) takes no
factory. Empty chains resolve to null/undefined; a thinkingLevel-only
slot is inert (stored, never run). resolveConversationSpec: chat.model
override over the strong slot, null when both empty. resolveRoleSpec
spans all nine roles for the job/extraction engines.
Refusal envelope (core/settings.ts): modelsNotConfigured(missing) —
{error, code: 'models_not_configured', missing: [slot tiers]} +
ModelsNotConfiguredError with .envelope. Per-need gates, each honest:
- chat-handler: universal turn gate (new + continuing turns) returns
503 before beginTurn — no liveness, no write-ahead persist, no graph
trigger before the gate fires.
- runner.runJob: unresolvable engine lands the job as error with the
envelope wording; no phantom loop, no result steer.
- extraction: refuseIfStagesUnconfigured throws before any stage
(turn-service info-skips so coverage retries next turn; the import
route surfaces per-file code+missing); labeler-less runs skip
cluster naming with a console line and still merge.
Write side: slot entries must carry a model — level-only slot writes
are 400s (absent slot key = clear). piEngineForSpec resolves unset
thinking levels via DEFAULT_THINKING_ORDER; piEngineFor now throws
honestly; thinkingLevelFor/modelIdFor deleted; teacher-agent, pi-run,
visual-maker, pdf-reader all read engine.level.
model-catalog: defaults/slots/rolePins null when the chain is empty
(contracts nullable) — no phantom ids in payloads. Stores drop
MODEL_PINS entirely.
Tests: pin-leaners converted to explicit injection (per-chat model
pins on scripted chats — exactly what the setup flow writes; faux
engines for agent-construction tests). New coverage: the 503 gate
envelope, the runner refusal, the extraction refusal + labeler skip.
Gates: typecheck, lint, 815/815, build.
This commit is contained in:
@@ -16,6 +16,15 @@ import * as teacherAgent from "../src/agent/teacher-agent.ts";
|
||||
import { allSegmentPaths, effectivePromptSegments } from "../src/agent/prompt-segments.ts";
|
||||
import { isValidSegmentPath } from "../src/core/prompt-segments.ts";
|
||||
import { promptOverrides } from "../src/store/prompt-overrides.ts";
|
||||
import { createFauxCore } from "@earendil-works/pi-ai";
|
||||
import type { PiEngine } from "../src/agent/models.ts";
|
||||
|
||||
/** A scripted pi engine (pi-ai's faux provider) — the agent build needs an
|
||||
* injected engine since BYOK removed the factory pins (owner, 2026-09-22). */
|
||||
function fauxEngine(): PiEngine {
|
||||
const faux = createFauxCore({});
|
||||
return { model: faux.getModel(), streamFn: faux.streamSimple };
|
||||
}
|
||||
|
||||
after(() => {
|
||||
fs.rmSync(PROMPTS_OVERRIDE_DIR, { recursive: true, force: true });
|
||||
@@ -210,9 +219,13 @@ describe("composeInstructions: override honoring + the byte-identical source pat
|
||||
it("promptSwitches threads through agent construction into the system prompt", () => {
|
||||
promptOverrides.writeOverride("system-prompt.md", "TOTALLY CUSTOM BASE");
|
||||
try {
|
||||
const agent = createTeacherAgent(undefined, { promptSwitches: { "system-prompt.md": true } });
|
||||
// BYOK (owner, 2026-09-22): no factory pins — the agent build needs
|
||||
// an injected engine; a scripted faux one stands in (the prompt is
|
||||
// what's under test here, not the model).
|
||||
const engine = fauxEngine();
|
||||
const agent = createTeacherAgent(undefined, { engine, promptSwitches: { "system-prompt.md": true } });
|
||||
assert.ok(agent.state.systemPrompt.includes("TOTALLY CUSTOM BASE"));
|
||||
const source = createTeacherAgent(undefined, {});
|
||||
const source = createTeacherAgent(undefined, { engine });
|
||||
assert.ok(!source.state.systemPrompt.includes("TOTALLY CUSTOM BASE"), "no switches → cached source");
|
||||
} finally {
|
||||
promptOverrides.deleteOverride("system-prompt.md");
|
||||
|
||||
Reference in New Issue
Block a user