amosblomqvist
52c02533d1
Per-batch pipeline is now extract → spine → audit → merge (owner order, 2026-09-30), the spine inside the serialized audit section so it reads the graph exactly as the following audit will. Measured motive: 0 of 133 chains in the live corpus crossed a stretch boundary — no stage minted cross-stretch chains. - src/agent/subagents/spine.ts: SESSION/NOTES spine preambles + shared SPINE_CORE (span doctrine; extraction doctrines carried over), the submit_spine TypeBox schema, validateSpine (mechanical span law: every chain touches >=1 fresh endpoint AND >=1 existing digest endpoint; unknown ids, self-reference, and id collisions are loud), the digest prompt builder, and the runner (strong tier, retry-only). - extraction.ts: 'assembling' phase, spine stage in the per-need gate, usage/billing stage, assemble() inside withAuditLock for both front doors; first stretch of a source skips the call (empty digest, no spend); the audit sees COMBINED propositions (chunk + connectives), never chains; merger receives the combined findings. - core/graph.ts mergeFindings: chain endpoints resolve through the job-local map OR pass through verbatim as existing n_ ids (the spine's mixed namespace). - EXTRACTION_CORE: steps-of-reasoning selection bar (examples, notation glosses, and restatements that no argument needs are not steps). - Factory chunk budget 4096 -> 8192 (fewer seams, more local context). - healStringifiedArrays moved to the shared submit seam (submit-agent.ts). - Cost panel: Assembly row; usage records carry a spine stage (optional on legacy records). - Tests +5: prompt pins, span-law matrix, digest rendering, seeded end-to-end flow (spanning chain + connective, verbatim n_ endpoint, spine billed as its own stage), non-spanning refused + retried.
255 lines
11 KiB
TypeScript
255 lines
11 KiB
TypeScript
/**
|
|
* Tests for the resolution layer (settings-storage wave, 2026-09-19;
|
|
* model-slots wave 2026-09-20; BYOK all-the-way-down wave 2026-09-22):
|
|
* core/settings-resolution.ts — the delta→concrete projection. There are
|
|
* NO factory pins anymore: a model chain that ends empty resolves to
|
|
* null/undefined, and the per-need refusal gates (turn, job spawn,
|
|
* extraction) fire on exactly that.
|
|
*/
|
|
|
|
import assert from "node:assert/strict";
|
|
import { describe, it } from "node:test";
|
|
import {
|
|
extractionEnabled,
|
|
graphToolsEnabled,
|
|
resolveConversationSpec,
|
|
resolveModelSpec,
|
|
resolveRoleSpec,
|
|
resolveSettings,
|
|
resolveSlot,
|
|
} from "../src/core/settings-resolution.ts";
|
|
import { BACKGROUND_MODEL_ROLES, type UserSettings } from "../src/core/settings.ts";
|
|
|
|
describe("resolveSettings", () => {
|
|
it("null record (first boot): non-model knobs land on factory defaults; every model view is EMPTY", () => {
|
|
const eff = resolveSettings(null);
|
|
assert.deepEqual(eff.general, { autoUpdate: true });
|
|
assert.deepEqual(eff.agent.tools, {});
|
|
assert.deepEqual(eff.agent.prompts, {});
|
|
assert.deepEqual(eff.agent.search, {});
|
|
// BYOK (owner, 2026-09-22): no factory floor — every role undefined,
|
|
// every slot null. No phantom ids anywhere.
|
|
for (const role of BACKGROUND_MODEL_ROLES) {
|
|
assert.equal(eff.agent.models[role], undefined, role);
|
|
}
|
|
assert.equal(eff.models.strong, null);
|
|
assert.equal(eff.models.cheap, null);
|
|
assert.equal(eff.models.vision, null);
|
|
assert.equal(eff.appearance.mode, "dark");
|
|
assert.equal(eff.appearance.background, null);
|
|
assert.equal(eff.appearance.fontFamily, null);
|
|
assert.equal(eff.appearance.proseFontSize, 16);
|
|
assert.equal(eff.appearance.sessionNameSerif, true);
|
|
assert.equal(eff.appearance.mdRendering.headingWeight, 900);
|
|
// wave 7 collapse: the master switch ONLY + the redesign's chunk
|
|
// budget — absent record resolves the factory 8192 (the 2026-09-30 bump)
|
|
assert.deepEqual(eff.graph, { enabled: true, extractionChunkTokens: 8192 });
|
|
});
|
|
|
|
it("explicit record values win over every factory default", () => {
|
|
const record: UserSettings = {
|
|
version: 1,
|
|
general: { autoUpdate: false },
|
|
agent: {
|
|
models: { researcher: { model: { provider: "openrouter", id: "qwen/qwen3.8-flash" } } },
|
|
tools: { research: false },
|
|
prompts: { "system-prompt.md": true },
|
|
search: { engine: "tavily" },
|
|
},
|
|
appearance: { mode: "light", proseFontSize: 20, mdRendering: { headingWeight: 600 } },
|
|
graph: { enabled: false },
|
|
};
|
|
const eff = resolveSettings(record);
|
|
assert.equal(eff.general.autoUpdate, false);
|
|
assert.deepEqual(eff.agent.models.researcher, {
|
|
provider: "openrouter",
|
|
id: "qwen/qwen3.8-flash",
|
|
// thinking NOT overridden and no cheap slot → UNSET (the engine
|
|
// build resolves it from DEFAULT_THINKING_ORDER, not a pin).
|
|
thinkingLevel: undefined,
|
|
});
|
|
assert.deepEqual(eff.agent.search, { engine: "tavily" });
|
|
assert.deepEqual(eff.agent.tools, { research: false });
|
|
assert.deepEqual(eff.agent.prompts, { "system-prompt.md": true });
|
|
assert.equal(eff.appearance.mode, "light");
|
|
assert.equal(eff.appearance.proseFontSize, 20);
|
|
assert.equal(eff.appearance.mdRendering.headingWeight, 600);
|
|
// wave 7 collapse: the section IS the master switch (absent budget
|
|
// field = factory 8192 — a pre-redesign record resolves cleanly).
|
|
assert.deepEqual(eff.graph, { enabled: false, extractionChunkTokens: 8192 });
|
|
// The chunk budget rides the same resolution: stored value wins.
|
|
const budgeted = resolveSettings({ version: 1, graph: { extractionChunkTokens: 2000 } });
|
|
assert.deepEqual(budgeted.graph, { enabled: true, extractionChunkTokens: 2000 });
|
|
});
|
|
|
|
it("partial role override: thinkingLevel alone borrows the SLOT's model (or nothing, without one)", () => {
|
|
const eff = resolveSettings({
|
|
version: 1,
|
|
models: { cheap: { model: { provider: "zai", id: "glm-5.3-flash" } } },
|
|
agent: { models: { extractor: { thinkingLevel: "medium" } } },
|
|
});
|
|
assert.deepEqual(eff.agent.models.extractor, {
|
|
provider: "zai",
|
|
id: "glm-5.3-flash",
|
|
thinkingLevel: "medium",
|
|
});
|
|
const bare = resolveSettings({ version: 1, agent: { models: { extractor: { thinkingLevel: "medium" } } } });
|
|
assert.equal(bare.agent.models.extractor, undefined); // no model anywhere → chain empty
|
|
});
|
|
|
|
it("resolveModelSpec is field-independent per override aspect", () => {
|
|
const slots = { cheap: { model: { provider: "zai", id: "slot-model" }, thinkingLevel: "high" as const } };
|
|
assert.deepEqual(
|
|
resolveModelSpec("auditor", { model: { provider: "other", id: "x" } }, slots),
|
|
{ provider: "other", id: "x", thinkingLevel: "high" }, // override model + slot level
|
|
);
|
|
assert.deepEqual(resolveModelSpec("auditor", { thinkingLevel: "max" }, slots), {
|
|
provider: "zai",
|
|
id: "slot-model",
|
|
thinkingLevel: "max", // override level + slot model
|
|
});
|
|
assert.equal(resolveModelSpec("auditor", undefined, {}), undefined);
|
|
});
|
|
});
|
|
|
|
describe("the slot tier (BYOK, owner 2026-09-22)", () => {
|
|
it("slot alone re-tiers every role of its tier (no role overrides present)", () => {
|
|
const eff = resolveSettings({ version: 1, models: { cheap: { model: { provider: "zai", id: "glm-5.3-flash" } } } });
|
|
for (const role of ["researcher", "demoBuilder", "extractor", "auditor"] as const) {
|
|
assert.deepEqual(
|
|
eff.agent.models[role],
|
|
{ provider: "zai", id: "glm-5.3-flash", thinkingLevel: undefined }, // level unset → default order
|
|
role,
|
|
);
|
|
}
|
|
// other tiers untouched (empty)
|
|
assert.equal(eff.agent.models.visualMaker, undefined);
|
|
});
|
|
|
|
it("role override still beats the slot; each field independent", () => {
|
|
const eff = resolveSettings({
|
|
version: 1,
|
|
agent: { models: { researcher: { model: { provider: "groq", id: "r-override" } } } },
|
|
models: { cheap: { model: { provider: "zai", id: "r-slot" }, thinkingLevel: "high" } },
|
|
});
|
|
assert.deepEqual(eff.agent.models.researcher, {
|
|
provider: "groq",
|
|
id: "r-override",
|
|
thinkingLevel: "high", // slot level rides the override's model
|
|
});
|
|
assert.deepEqual(eff.agent.models.auditor, { provider: "zai", id: "r-slot", thinkingLevel: "high" });
|
|
});
|
|
|
|
it("vision slot covers visualMaker AND pdfReader; level-only slots resolve as NULL", () => {
|
|
const eff = resolveSettings({ version: 1, models: { vision: { model: { provider: "zai", id: "v-model" }, thinkingLevel: "max" } } });
|
|
assert.deepEqual(eff.agent.models.visualMaker, { provider: "zai", id: "v-model", thinkingLevel: "max" });
|
|
assert.deepEqual(eff.models.vision, { provider: "zai", id: "v-model", thinkingLevel: "max" });
|
|
// a stored level WITHOUT a model is inert (kept on disk, no phantom default)
|
|
const inert = resolveSettings({ version: 1, models: { strong: { thinkingLevel: "medium" } } });
|
|
assert.equal(inert.models.strong, null);
|
|
assert.equal(inert.agent.models.researcher, undefined); // strong's emptiness must not leak into other tiers
|
|
});
|
|
|
|
it("resolveSlot: configured iff the model is present", () => {
|
|
assert.deepEqual(resolveSlot({ model: { provider: "zai", id: "m" }, thinkingLevel: "medium" }), {
|
|
provider: "zai",
|
|
id: "m",
|
|
thinkingLevel: "medium",
|
|
});
|
|
assert.deepEqual(resolveSlot({ model: { provider: "zai", id: "m" } }), {
|
|
provider: "zai",
|
|
id: "m",
|
|
thinkingLevel: undefined, // unset → resolved from the default order at build
|
|
});
|
|
assert.equal(resolveSlot({ thinkingLevel: "medium" }), null);
|
|
assert.equal(resolveSlot(undefined), null);
|
|
});
|
|
|
|
it("resolveRoleSpec: background roles and the conversation pair share the chain", () => {
|
|
const record: UserSettings = {
|
|
version: 1,
|
|
models: { strong: { model: { provider: "zai", id: "strong-model" } } },
|
|
};
|
|
// conversation pair: slot only (their override is chat-controlled)
|
|
assert.deepEqual(resolveRoleSpec("prober", record), {
|
|
provider: "zai",
|
|
id: "strong-model",
|
|
thinkingLevel: undefined, // level unset → default order at build
|
|
});
|
|
// background role override beats the slot
|
|
const withOverride: UserSettings = {
|
|
...record,
|
|
agent: { models: { researcher: { model: { provider: "groq", id: "r" } } } },
|
|
};
|
|
assert.deepEqual(resolveRoleSpec("researcher", withOverride), { provider: "groq", id: "r", thinkingLevel: undefined });
|
|
// pdfReader rides the vision slot (never a background override)
|
|
const visionRecord: UserSettings = {
|
|
version: 1,
|
|
models: { vision: { model: { provider: "zai", id: "v" }, thinkingLevel: "low" } },
|
|
};
|
|
assert.deepEqual(resolveRoleSpec("pdfReader", visionRecord), { provider: "zai", id: "v", thinkingLevel: "low" });
|
|
assert.equal(resolveRoleSpec("teacher", null), undefined);
|
|
});
|
|
});
|
|
|
|
describe("resolveConversationSpec (the turn gate's chain)", () => {
|
|
it("chat.model over the strong slot; null when both empty", () => {
|
|
assert.equal(resolveConversationSpec(undefined, null), null);
|
|
assert.deepEqual(
|
|
resolveConversationSpec(undefined, { provider: "zai", id: "s" }),
|
|
{ provider: "zai", id: "s", thinkingLevel: undefined },
|
|
);
|
|
assert.deepEqual(
|
|
resolveConversationSpec({ model: { provider: "groq", id: "c" } }, null),
|
|
{ provider: "groq", id: "c", thinkingLevel: undefined },
|
|
);
|
|
});
|
|
|
|
it("bare chat thinking level rides the strong slot's model", () => {
|
|
assert.deepEqual(
|
|
resolveConversationSpec({ thinkingLevel: "high" }, { provider: "zai", id: "s", thinkingLevel: "low" }),
|
|
{ provider: "zai", id: "s", thinkingLevel: "high" },
|
|
);
|
|
// chat.model present, strong unset: level may still ride the chat alone
|
|
assert.deepEqual(
|
|
resolveConversationSpec({ model: { provider: "groq", id: "c" }, thinkingLevel: "max" }, null),
|
|
{ provider: "groq", id: "c", thinkingLevel: "max" },
|
|
);
|
|
// nothing set anywhere: unset level, not a phantom one
|
|
assert.deepEqual(resolveConversationSpec({ model: { provider: "groq", id: "c" } }, null), {
|
|
provider: "groq",
|
|
id: "c",
|
|
thinkingLevel: undefined,
|
|
});
|
|
});
|
|
});
|
|
|
|
describe("the graph channel gates (the wave's seam honoring)", () => {
|
|
it("WRITE channel (extraction): dies with the master switch — the ONLY graph setting since wave 7", () => {
|
|
assert.equal(extractionEnabled({ enabled: true }), true);
|
|
assert.equal(extractionEnabled({ enabled: false }), false);
|
|
});
|
|
|
|
it("the write gate rides resolveSettings' factory defaults (all on → open)", () => {
|
|
const eff = resolveSettings(null);
|
|
assert.equal(extractionEnabled(eff.graph), true);
|
|
const off = resolveSettings({ version: 1, graph: { enabled: false } });
|
|
assert.equal(extractionEnabled(off.graph), false);
|
|
});
|
|
|
|
it("PROBER GRAPH TOOLS gate (wave 7, owner ruling 2026-09-23): the agent toggle AND the graph master switch compose", () => {
|
|
const graph = { enabled: true };
|
|
assert.equal(graphToolsEnabled({ graph, agent: { graphTools: {} } }), true, "absent subsection = ON");
|
|
assert.equal(graphToolsEnabled({ graph, agent: { graphTools: { enabled: true } } }), true);
|
|
assert.equal(graphToolsEnabled({ graph, agent: { graphTools: { enabled: false } } }), false);
|
|
const dead = { ...graph, enabled: false };
|
|
assert.equal(graphToolsEnabled({ graph: dead, agent: { graphTools: { enabled: true } } }), false, "graph off kills the tools regardless of the toggle");
|
|
});
|
|
|
|
it("graphTools rides resolveSettings: absent record → the empty subsection (ON); a record's delta passes through", () => {
|
|
const eff = resolveSettings(null);
|
|
assert.deepEqual(eff.agent.graphTools, {});
|
|
const off = resolveSettings({ version: 1, agent: { graphTools: { enabled: false } } });
|
|
assert.deepEqual(off.agent.graphTools, { enabled: false });
|
|
});
|
|
}); |