Completes the deferred B8 half. `--context-window auto` now probes the configured model and calibrates SKL/CML budgets to its real window instead of always falling back to the conservative advisory anchor. - lib/context-window.mjs: pure modelToContextWindow() maps known 1M-tier model IDs (Fable 5, Opus 4.8/4.7/4.6, Sonnet 4.6 — verified June 2026 — plus the explicit [1m] tier tag, dated/provider-prefixed IDs, and the opus/sonnet/fable aliases) to the 1M window; unknown/unconfirmed -> null (caller keeps the conservative anchor). resolveContextWindow() auto branch now probes opts.model: recognized -> auto-probed (not advisory); unknown or unpinned -> auto-unresolved (advisory, pre-B8b behavior). - lib/active-model.mjs (new): resolveActiveModel() reads the model the way Claude Code resolves it — shell ANTHROPIC_MODEL override, then settings cascade local > project > user. Injectable env, hermetic under test HOME. - scan-orchestrator: resolves the active model only when the flag is `auto` and threads it into resolveContextWindow; posture inherits via runAllScanners. Default (no flag) and explicit --context-window <n> paths ignore the model and stay byte-stable; frozen v5.0.0 + SC-5 snapshots untouched. TDD: 17 new tests (context-window mapping/probe + active-model cascade). Suite 1296 green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
132 lines
6 KiB
JavaScript
132 lines
6 KiB
JavaScript
/**
|
|
* Context-window constants — single source of truth.
|
|
*
|
|
* Several Claude Code budgets scale with the model's context window:
|
|
* - the skill listing is allotted ~2% of context (CC 2.1.32, changelog L2860);
|
|
* - the "CLAUDE.md is too long" warning threshold scales with it (CC 2.1.169).
|
|
*
|
|
* We cannot observe the user's actual context window, so scanners anchor on a
|
|
* conservative 200k window (the smallest common size — it fires earliest, the
|
|
* safe default when the window is unknown) and disclose the relaxed 1M figure.
|
|
*
|
|
* Zero external dependencies.
|
|
*/
|
|
|
|
// Conservative anchor: the smallest common context window. Budgets anchored
|
|
// here fire earliest, which is the safe default when the window is unknown.
|
|
export const CONTEXT_WINDOW_ANCHOR = 200_000;
|
|
|
|
// Large context window (Opus/Sonnet 1M tier). Used to disclose how a budget
|
|
// relaxes on large-context models.
|
|
export const LARGE_CONTEXT_WINDOW = 1_000_000;
|
|
|
|
// How much larger the 1M window is than the 200k anchor (= 5). A budget that
|
|
// scales linearly with the window relaxes by this factor at 1M.
|
|
export const LARGE_CONTEXT_SCALE = LARGE_CONTEXT_WINDOW / CONTEXT_WINDOW_ANCHOR;
|
|
|
|
// Dependency-free thousands separator (repo invariant: zero external deps).
|
|
export const withCommas = (n) => String(n).replace(/\B(?=(\d{3})+(?!\d))/g, ',');
|
|
|
|
// Model families whose context window is the large (1M) tier. Verified June 2026
|
|
// (platform.claude.com models overview): Fable 5, Opus 4.8/4.7/4.6 and Sonnet 4.6
|
|
// all run a 1M context window. Matched by substring so dated IDs
|
|
// (claude-opus-4-8-20260528) and provider-prefixed IDs
|
|
// (us.anthropic.claude-opus-4-8) resolve too. Models we cannot confirm (e.g.
|
|
// Haiku, older 200k-era IDs) are deliberately left out: the caller then keeps the
|
|
// conservative anchor rather than guess a relaxed budget.
|
|
export const LARGE_CONTEXT_MODEL_IDS = [
|
|
'claude-fable-5',
|
|
'claude-opus-4-8',
|
|
'claude-opus-4-7',
|
|
'claude-opus-4-6',
|
|
'claude-sonnet-4-6',
|
|
];
|
|
|
|
// Short aliases Claude Code accepts in the `model` setting / ANTHROPIC_MODEL that
|
|
// currently resolve to a 1M-tier model (`opusplan` plans on an Opus-tier model).
|
|
export const LARGE_CONTEXT_MODEL_ALIASES = new Set(['opus', 'sonnet', 'fable', 'opusplan']);
|
|
|
|
/**
|
|
* Map a configured model id/alias to its context window, or null when we cannot
|
|
* confirm it. Pure: no IO. Used by the `--context-window auto` probe (B8b) so
|
|
* known 1M-tier models calibrate budgets instead of falling back to the
|
|
* conservative advisory anchor.
|
|
*
|
|
* @param {string} modelId - e.g. "claude-opus-4-8[1m]", "claude-sonnet-4-6", "opus"
|
|
* @returns {number|null} the context window, or null if unrecognized
|
|
*/
|
|
export function modelToContextWindow(modelId) {
|
|
if (typeof modelId !== 'string') return null;
|
|
const id = modelId.trim().toLowerCase();
|
|
if (!id) return null;
|
|
// Explicit tier tag wins — the running session model surfaces as e.g.
|
|
// "claude-opus-4-8[1m]". This is the strongest, most future-proof signal.
|
|
if (id.includes('[1m]')) return LARGE_CONTEXT_WINDOW;
|
|
// Known 1M-tier families (substring → tolerant of date/provider-prefix variants).
|
|
for (const fam of LARGE_CONTEXT_MODEL_IDS) {
|
|
if (id.includes(fam)) return LARGE_CONTEXT_WINDOW;
|
|
}
|
|
// Short aliases.
|
|
if (LARGE_CONTEXT_MODEL_ALIASES.has(id)) return LARGE_CONTEXT_WINDOW;
|
|
// Unknown: cannot confirm the window — keep the conservative anchor (null).
|
|
return null;
|
|
}
|
|
|
|
/**
|
|
* @typedef {object} ResolvedContextWindow
|
|
* @property {number} window - the context window budgets calibrate against
|
|
* @property {boolean} advisory - true when the window is unknown: keep the anchor
|
|
* but downgrade budget findings to info instead of
|
|
* firing them as a breach
|
|
* @property {'default'|'explicit'|'auto-probed'|'auto-unresolved'} source
|
|
*/
|
|
|
|
/**
|
|
* Resolve the raw `--context-window` CLI value into a window + advisory flag.
|
|
*
|
|
* Design (B8): the DEFAULT (no flag) is byte-identical to the pre-B8 behavior —
|
|
* the conservative 200k anchor at full severity. Only an explicit value changes
|
|
* calibration. `auto` asks the tool to figure out the window.
|
|
*
|
|
* B8b: `auto` now probes the configured model (`opts.model`, resolved from the
|
|
* settings cascade / ANTHROPIC_MODEL by the orchestrator). A recognized 1M-tier
|
|
* model calibrates to its window (source `auto-probed`, not advisory). When the
|
|
* model is unknown or unpinned, it keeps the conservative anchor but marks the
|
|
* result advisory (source `auto-unresolved`) so SKL/CML downgrade their budget
|
|
* findings to info rather than "crying wolf" on a window we cannot confirm.
|
|
*
|
|
* @param {string|number|null|undefined} arg
|
|
* @param {{ model?: string|null }} [opts] - probe input for `auto` (ignored on the
|
|
* default/explicit paths, which stay byte-stable).
|
|
* @returns {ResolvedContextWindow}
|
|
*/
|
|
export function resolveContextWindow(arg, opts = {}) {
|
|
if (arg == null) {
|
|
return { window: CONTEXT_WINDOW_ANCHOR, advisory: false, source: 'default' };
|
|
}
|
|
if (String(arg).trim().toLowerCase() === 'auto') {
|
|
const probed = modelToContextWindow(opts.model);
|
|
if (probed) {
|
|
return { window: probed, advisory: false, source: 'auto-probed' };
|
|
}
|
|
return { window: CONTEXT_WINDOW_ANCHOR, advisory: true, source: 'auto-unresolved' };
|
|
}
|
|
const n = typeof arg === 'number' ? arg : parseInt(String(arg).trim(), 10);
|
|
if (Number.isFinite(n) && n > 0) {
|
|
return { window: n, advisory: false, source: 'explicit' };
|
|
}
|
|
// Unparseable / non-positive: fall back to the conservative default (no advisory).
|
|
return { window: CONTEXT_WINDOW_ANCHOR, advisory: false, source: 'default' };
|
|
}
|
|
|
|
/**
|
|
* Scale a 200k-anchored budget to a given context window. Linear in the window,
|
|
* so it is the identity at the anchor (keeps the default byte-stable).
|
|
*
|
|
* @param {number} anchorValue - the budget/threshold defined at the 200k anchor
|
|
* @param {number} window - the target context window
|
|
* @returns {number}
|
|
*/
|
|
export function scaleForWindow(anchorValue, window) {
|
|
return Math.round(anchorValue * (window / CONTEXT_WINDOW_ANCHOR));
|
|
}
|