sorokin.oleg.edu/learnharness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 7 Wiki Activity

Context-meter amendment: CONTEXT_LIMITS dies — pi's live catalog is the only limit source

Browse Source 
Owner ruling (2026-09-23, amendment to 04e336d): no hardcoded fallback
exists anywhere. contextWindow(record, limits) resolves the denominator
ONLY from the live index (provider:id -> contextWindow straight from
pi's catalog); a model missing from it (historical session, package
update, failed fetch) reads limit null and the meter renders
usage-only — the honest-render precedent, never a fake window.

- src/core/prices.ts: the 1354-entry CONTEXT_LIMITS table (65KB) and its
  generation apparatus deleted; the fold returns limit: number | null.
  PRICES untouched (regen verified byte-identical via the reworked
  sync-pricing script).
- scripts/sync-pricing.ts: generates PRICES only; contextWindow leaves
  the priced map, the guard, and the template.
- The dock meter's owner-selected treatment: the activity feed carries
  the limit server-side. catalogContextLimits() (server/model-catalog.ts)
  builds the index over the same keyed providers the picker federates;
  activityFeed() joins it onto every running job (ActivityJob.contextLimit,
  null when the model is missing — the dock reads it off the feed, no
  client-side table, no regression while the UI's catalog-join chunk lands).
- components/activity-dock.tsx: toBlobs reads job.contextLimit (import
  of CONTEXT_LIMITS gone); stats-bar renders usage-only on null limit
  (mechanical interim — UI stream's join chunk follows).
- tests: usage.test.ts pins the no-fallback contract (index hit / absent
  / empty / missing-model -> null); activity-feed.test.ts pins the
  server join (catalog model -> 1048576, unknown -> null, no-usage ->
  null); render pins updated to the interim usage-only render.
This commit is contained in:
amosblomqvist
2026-09-24 02:10:06 +03:00
parent b68a16fdb4
commit 4ded547cb5
11 changed files with 200 additions and 1450 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/usage.test.ts
+70 -50
View File
@@ -78,18 +78,22 @@ test("turnCost sums steps; sessionCost reports unpriced turns", () => {
assert.ok(totals.cost > 0);
});
test("contextWindow: last call's footprint against the model's limit", () => {
const cw = contextWindow({
turns: [
{ id: "t1", messageId: "m1", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 9_000, outputTokens: 1_000 })] },
{ id: "t2", messageId: "m2", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 90_000, outputTokens: 10_000 })] },
],
});
test("contextWindow: last call's footprint against the live index's limit", () => {
const limits = new Map([["openrouter:z-ai/glm-5.3-flash", 1_048_576]]);
const cw = contextWindow(
{
turns: [
{ id: "t1", messageId: "m1", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 9_000, outputTokens: 1_000 })] },
{ id: "t2", messageId: "m2", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 90_000, outputTokens: 10_000 })] },
],
},
limits,
);
assert.ok(cw);
assert.equal(cw.model, "openrouter:z-ai/glm-5.3-flash");
assert.equal(cw.usedTokens, 100_000);
assert.equal(cw.limit, 1_048_576);
assert.equal(contextWindow({ turns: [] }), null);
assert.equal(contextWindow({ turns: [] }, limits), null);
});
test("contextWindow NUMERATOR: cache tokens count (owner audit, 2026-09-23)", () => {
@@ -97,70 +101,86 @@ test("contextWindow NUMERATOR: cache tokens count (owner audit, 2026-09-23)", ()
// while the real footprint was ~190k — provider `input` EXCLUDES the
// cached portion, so input+output alone is wildly low. The fold is
// pi's totalTokens semantics: all four fields.
const cw = contextWindow({
turns: [
{
id: "t1",
messageId: "m1",
at: "x",
model: "openrouter:z-ai/glm-5.3-flash",
steps: [call({ inputTokens: 40_000, outputTokens: 1_000, cacheReadTokens: 145_000, cacheWriteTokens: 4_000 })],
},
],
});
const limits = new Map([["openrouter:z-ai/glm-5.3-flash", 1_048_576]]);
const cw = contextWindow(
{
turns: [
{
id: "t1",
messageId: "m1",
at: "x",
model: "openrouter:z-ai/glm-5.3-flash",
steps: [call({ inputTokens: 40_000, outputTokens: 1_000, cacheReadTokens: 145_000, cacheWriteTokens: 4_000 })],
},
],
},
limits,
);
assert.ok(cw);
assert.equal(cw.usedTokens, 40_000 + 1_000 + 145_000 + 4_000, "input + output + cacheRead + cacheWrite");
// Cache fields absent (non-caching providers): the fold is unchanged.
const plain = contextWindow({
turns: [{ id: "t1", messageId: "m1", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 9_000, outputTokens: 1_000 })] }],
});
const plain = contextWindow(
{ turns: [{ id: "t1", messageId: "m1", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 9_000, outputTokens: 1_000 })] }] },
limits,
);
assert.ok(plain);
assert.equal(plain.usedTokens, 10_000);
});
test("contextWindow DENOMINATOR: the live-limits index wins; CONTEXT_LIMITS is the fallback", () => {
test("contextWindow DENOMINATOR: the live index is the ONLY source — no fallback (owner amendment, 2026-09-23)", () => {
const turns = [
{ id: "t1", messageId: "m1", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 10_000, outputTokens: 1_000 })] },
];
// The live catalog (GET /api/models) wins even when it disagrees with
// the generated table.
const live = new Map([["openrouter:z-ai/glm-5.3-flash", 65_536]]);
const cw = contextWindow({ turns }, live);
assert.ok(cw);
assert.equal(cw.limit, 65_536, "the live index beats the static table");
// No live entry: the generated table serves the uncatalogued model.
assert.equal(contextWindow({ turns })!.limit, 1_048_576);
const emptyLive = new Map<string, number>();
assert.equal(contextWindow({ turns }, emptyLive)!.limit, 1_048_576, "an empty live index falls back too");
// Unknown to both: null (no meter, never a guessed limit).
assert.equal(contextWindow({ turns: [{ ...turns[0]!, model: "unknown/model" }] }), null);
assert.equal(contextWindow({ turns: [{ ...turns[0]!, model: "unknown/model" }] }, live), null);
assert.equal(cw.limit, 65_536, "pi's catalog, via the index, is the one source");
// No index at all (a client that hasn't fetched the catalog): the
// meter renders usage-only — limit null, never a guessed window.
const noIndex = contextWindow({ turns });
assert.ok(noIndex);
assert.equal(noIndex.usedTokens, 11_000);
assert.equal(noIndex.limit, null);
const emptyIndex = contextWindow({ turns }, new Map<string, number>());
assert.ok(emptyIndex);
assert.equal(emptyIndex.limit, null, "an empty index (failed fetch) is usage-only too");
// A model missing from the live catalog (historical session, package
// update removed it): usage-only, never a fake window.
const missing = contextWindow({ turns: [{ ...turns[0]!, model: "nope/gone-model" }] }, live);
assert.ok(missing);
assert.equal(missing.limit, null);
assert.equal(missing.usedTokens, 11_000, "the footprint still reads honestly");
});
test("contextWindow ride-along: a zeroed/aborted last step falls back to the previous step", () => {
// An aborted last call reports zeroed usage — that is not the session
// footprint. The honest reading is the previous step's usage.
const cw = contextWindow({
turns: [
{
id: "t1",
messageId: "m1",
at: "x",
model: "openrouter:z-ai/glm-5.3-flash",
steps: [
call({ inputTokens: 80_000, outputTokens: 5_000 }),
call({ inputTokens: 0, outputTokens: 0 }), // aborted — zeroed
],
},
],
});
const limits = new Map([["openrouter:z-ai/glm-5.3-flash", 1_048_576]]);
const cw = contextWindow(
{
turns: [
{
id: "t1",
messageId: "m1",
at: "x",
model: "openrouter:z-ai/glm-5.3-flash",
steps: [
call({ inputTokens: 80_000, outputTokens: 5_000 }),
call({ inputTokens: 0, outputTokens: 0 }), // aborted — zeroed
],
},
],
},
limits,
);
assert.ok(cw);
assert.equal(cw.usedTokens, 85_000, "the previous step's footprint, not a bogus tiny meter");
// ALL steps zeroed (a first-call abort): no reading at all — null.
assert.equal(
contextWindow({
turns: [{ id: "t1", messageId: "m1", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 0, outputTokens: 0 })] }],
}),
contextWindow(
{ turns: [{ id: "t1", messageId: "m1", at: "x", model: "openrouter:z-ai/glm-5.3-flash", steps: [call({ inputTokens: 0, outputTokens: 0 })] }] },
limits,
),
null,
);
});