Files
OmniRoute/tests/unit/claude-context-1m-supported-models.test.ts
Bob.Hou 43eb470790 fix(models): update Anthropic model contextLength to 1M (#7129)
* chore(ci): add .mergify.yml to main — Mergify only reads config from the default branch (#7168)

* fix(ci): add the auto-enqueue pull_request_rule to the Mergify config (queue_conditions alone are eligibility-only) (#7179)

* fix(ci): migrate Mergify auto-enqueue to merge_protections_settings.auto_merge_conditions (rules-based path is EOL 2026-07-16) (#7216)

* fix(ci): drop Mergify batch settings (batching is a paid-tier feature; free plan queue is serial) (#7220)

* fix(ci): merge queue tolerates the advisory dast-smoke failure (its GH-hosted build hang dequeued every attempt) (#7225)

* test(ci): make the #6634 selfref guard hermetic — main's copy hard-fails every PR (#7341)

main's copy of this test still does git I/O inside a unit test:

    const baseSrc = git(['show', 'origin/main:' + FILE]);

Runners check out a shallow single ref, so origin/main does not resolve and the
test dies with 'fatal: invalid object name origin/main'. Every PR into main
fails Unit Tests (7/8) on it — today that is #7313, #7315, #7316, #7334, #7336
and #7337, six PRs red on a defect none of them introduced. #7313 has no other
red at all.

release/v3.8.49 already carries a fix (2e42b8efc, #7174: try/catch, fetch
origin/main on demand, t.skip() when unreachable), but it only reaches main at
release time — so main stays broken for the whole cycle. Cherry-picking it would
also import a new problem: PR Test Policy classifies t.skip() as a silenced
assertion, which we watched it correctly catch on #7300 today.

This is the hermetic version instead (ported from #7327, which does the same for
the release branch): read the file straight off disk, compare against an empty
base so baseTaut/baseExtTaut are 0 — the strictest possible comparison point —
and call evaluateMasking() directly. No git ref, no fetch, no skip, nothing the
runner's checkout depth can break.

The #6634 regression stays covered: the guard's logic lives in
SELF_TEST_FIXTURE_RE (check-test-masking.mjs:337), not in the test. Proven both
ways on main before committing — neutralise SELF_TEST_FIXTURE_RE to /$^/ and
the test FAILS; restore it and it passes 2/2, with check-test-masking.mjs left
byte-identical.

Co-authored-by: growab <nekron@icloud.com>

* chore(quality): tighten main's coverage baseline to the CI's real numbers (#7347)

main's ratchet had been failing --require-tighten on every PR: 11 metrics
improved but the baseline was never tightened. Same class as the #6634
selfref guard — an infra fix that lands only on the release branch leaves
main red for the whole cycle, and every PR into main pays for it.

Values are the merged-coverage numbers from a run on main itself (a local
run measures ~68% vs CI's ~80%; the baseline's own note warns about that
gap). Only the 11 coverage values change — gitleaks and semgrepFindings
keep main's own state.

No changelog fragment: #7326 carries it on release/v3.8.49, and a second
one here would double the entry at release time.

* fix(models): update Anthropic model contextLength to 1M

Opus 4.6, Sonnet 4.6, and Sonnet 5 all have 1M context
window since GA (2026-03-13). Update:

- agyModels + antigravityModelAliases: 200000 -> 1048576 (binary 1M, matches existing convention in those files)
- claude registry: 200000 -> 1000000 (decimal 1M, matches other entries in that file)

Older models (opus-4-5, sonnet-4-5, haiku-4-5) and defaultContextLength: 200000 left untouched.

Signed-off-by: Minxi Hou <houminxi@gmail.com>

* fix(claude): add sonnet-4-6 to CONTEXT_1M_SUPPORTED_MODELS

Sonnet 4.6 has 1M context GA since 2026-02-17. Without this entry, the CC-compatible wire image omits the context-1m beta header for Sonnet 4.6 requests, causing large-context requests to be rejected by Anthropic.

* test: regression test for CONTEXT_1M_SUPPORTED_MODELS allowlist

Verify that every Claude model with contextLength > 200K has a
matching entry in the beta header allowlist, and vice versa.
Parses source files directly (no module imports needed).

Signed-off-by: Minxi Hou <houminxi@gmail.com>

* test: improve regression test with empty-registry guard

Add sanity check that parser finds at least one model. Handle type annotations in CONTEXT_1M_SUPPORTED_MODELS assignment. Remove weaker subagent test.

Signed-off-by: Minxi Hou <houminxi@gmail.com>

* test: update stale contextLength expectations for the 1M Sonnet/Opus 4.6 fix

Three pre-existing tests hardcoded the old 200000 contextLength for
claude-opus-4-6-thinking / claude-sonnet-4-6 / claude-sonnet-5, which this
PR's own registry change (agyModels.ts, antigravityModelAliases.ts, claude
registry) legitimately bumped to 1M GA:

- antigravity-model-aliases.test.ts: deepEqual assertions for
  claude-opus-4-6-thinking and claude-sonnet-5 in the Antigravity catalog
  expected contextLength: 200000; now 1048576. Added an explicit contextLength
  assertion for claude-sonnet-4-6 too.
- auto-combo-context-advertising.test.ts: resolveComboContextLimit regression
  test asserted the claude target's own limit as 200000; the test's intent
  (own limit wins over an 8k sibling, not compressed) is unchanged, only the
  registry's current correct value (1000000) needed updating. Also refreshed
  a stale comment in the MAX-of-candidates test (functionally unaffected,
  since gemini's 1048576 already wins either way).
- models-catalog-route.test.ts: refreshed a stale inline comment (the actual
  assertion checks the MIN across combo targets, 128000, unaffected by the
  1M bump).

Verified via Anthropic's own docs (platform.claude.com/docs/en/build-with-claude/context-windows):
"Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and
Claude Sonnet 4.6 have a 1M-token context window ... on the Claude API,
Amazon Bedrock, Google Cloud, and Microsoft Foundry" -- matches this PR's
claimed 2026-03-13 GA date exactly, and Google Cloud coverage corroborates
the Antigravity-hosted ids. Independently corroborated for the
Antigravity-specific path by unrelated third-party projects fixing the same
gap (earendil-works/pi#2209, badlogic/pi-mono#2194).

Swept the full test suite for other contextLength/contextWindow assertions
against these three model ids (grep + targeted runs across
models-catalog-route, model-capabilities-registry, t31-t33-t34-t38-model-specs,
executor-antigravity, agy-provider, provider-models-config,
model-metadata-registry, claude-web-sonnet5-registry, combo-routing-engine,
command-code-executor, combo-lockout-quota-reset -- 157 tests green); the
Bedrock-hosted registry and modelSpecs.ts module were already correctly at
1000000 for these models, reinforcing this PR's direction.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

---------

Signed-off-by: Minxi Hou <houminxi@gmail.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: growab <nekron@icloud.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
2026-07-18 15:13:57 -03:00

154 lines
5.2 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import path from "node:path";
const REPO_ROOT = path.resolve(import.meta.dirname, "../..");
// ─── Parse CONTEXT_1M_SUPPORTED_MODELS from source (no module import needed) ───
function parseSupportedModels(): string[] {
const src = fs.readFileSync(
path.join(REPO_ROOT, "open-sse/services/claudeCodeCompatible.ts"),
"utf8"
);
// Strip type annotations before matching to handle `const X: string[] = [...]`
const match = src
.replace(/:\s*\w+(\[\])?/, "")
.match(/CONTEXT_1M_SUPPORTED_MODELS\s*=\s*\[([\s\S]*?)\]/);
if (!match) throw new Error("CONTEXT_1M_SUPPORTED_MODELS not found in source");
return match[1]
.split(",")
.map((s) => s.replace(/["'\s]/g, "").toLowerCase())
.filter(Boolean);
}
// ─── Parse Claude models from provider registry (source-level) ───
// Uses brace-counting to isolate each model block within the models array,
// avoiding false matches on the provider-level id field.
function parseClaudeRegistryModels(): Array<{
provider: string;
modelId: string;
contextLength: number;
}> {
const registryDir = path.join(REPO_ROOT, "open-sse/config/providers/registry/claude");
const results: Array<{
provider: string;
modelId: string;
contextLength: number;
}> = [];
for (const file of fs.readdirSync(registryDir).filter((f) => f.endsWith(".ts"))) {
const src = fs.readFileSync(path.join(registryDir, file), "utf8");
// Extract provider id
const providerIdMatch = src.match(/id:\s*["']([^"']+)["']/);
const providerId = providerIdMatch?.[1] ?? file.replace(".ts", "");
// Find the models array
const modelsStart = src.indexOf("models:");
if (modelsStart === -1) continue;
const arrayStart = src.indexOf("[", modelsStart);
if (arrayStart === -1) continue;
// Extract individual model objects using brace counting.
// Skips any non-model nested braces by requiring both id and contextLength
// in the same brace-delimited block.
let braceDepth = 0;
let objStart = -1;
const modelBlocks: string[] = [];
for (let i = arrayStart; i < src.length; i++) {
if (src[i] === "{") {
if (braceDepth === 0) objStart = i;
braceDepth++;
} else if (src[i] === "}") {
braceDepth--;
if (braceDepth === 0 && objStart !== -1) {
modelBlocks.push(src.slice(objStart, i + 1));
objStart = -1;
}
} else if (src[i] === "]" && braceDepth === 0) {
break;
}
}
for (const block of modelBlocks) {
const idMatch = block.match(/id:\s*["']([^"']+)["']/);
const ctxMatch = block.match(/contextLength:\s*(\d+)/);
if (idMatch && ctxMatch) {
results.push({
provider: providerId,
modelId: idMatch[1].toLowerCase(),
contextLength: parseInt(ctxMatch[1], 10),
});
}
}
}
return results;
}
const CONTEXT_1M_THRESHOLD = 200_000;
function isModel1mSupported(modelId: string, supportedModels: string[]): boolean {
const normalized = modelId.replace(/:.*$/, "").toLowerCase();
return supportedModels.some((s) => normalized === s || normalized.startsWith(`${s}-`));
}
// ─── Sanity: parser must find at least one model ───
test("parser finds at least one Claude model in the registry", () => {
const models = parseClaudeRegistryModels();
assert.ok(
models.length > 0,
"parseClaudeRegistryModels returned 0 models — check that open-sse/config/providers/registry/claude/ exists and contains model definitions"
);
});
// ─── Forward: every high-context Claude model must be in the allowlist ───
test("every Claude model with contextLength > 200K is in CONTEXT_1M_SUPPORTED_MODELS", () => {
const supportedModels = parseSupportedModels();
const claudeModels = parseClaudeRegistryModels();
const violations: string[] = [];
for (const m of claudeModels) {
if (m.contextLength > CONTEXT_1M_THRESHOLD && !isModel1mSupported(m.modelId, supportedModels)) {
violations.push(`${m.provider}/${m.modelId} (contextLength=${m.contextLength})`);
}
}
assert.deepEqual(
violations,
[],
`Claude models with contextLength > 200K missing from CONTEXT_1M_SUPPORTED_MODELS.\n` +
`Add the model prefix to the allowlist in claudeCodeCompatible.ts.\n` +
`Violations:\n ${violations.join("\n ")}`
);
});
// ─── Reverse: every allowlist entry must have a matching high-context model ───
test("every CONTEXT_1M_SUPPORTED_MODELS entry has a matching Claude model with contextLength > 200K", () => {
const supportedModels = parseSupportedModels();
const claudeModels = parseClaudeRegistryModels();
const orphans: string[] = [];
for (const supported of supportedModels) {
const found = claudeModels.some(
(m) =>
m.contextLength > CONTEXT_1M_THRESHOLD &&
(m.modelId === supported || m.modelId.startsWith(`${supported}-`))
);
if (!found) orphans.push(supported);
}
assert.deepEqual(
orphans,
[],
`CONTEXT_1M_SUPPORTED_MODELS entries with no matching high-context Claude model.\n` +
`Remove stale entries or check model id spelling.\n` +
`Orphans:\n ${orphans.join("\n ")}`
);
});