BitSquare/Codeman
2
0 Fork 0
mirror of https://github.com/Ark0N/Codeman.git synced 2026-11-14 10:39:32 +01:00
Code Issues Packages Projects Releases Wiki Activity

feat(local-model): hardware probe, model catalogue and the pure recommendation

Browse Source 
The core of the read-only recommendation: what this Mac is, what the catalogue
knows, and which model fits. Nothing is downloaded, installed or written.

- hardware.ts: one bounded async spawn of /usr/sbin/sysctl with seven keys,
  without -n, parsed as "key: value" lines by the pure parseSysctl(). Free disk
  of the data dir through statfs behind the bounded path probe. Fallbacks from
  node:os, a 60 s cache, never throws, never system_profiler. A wired limit of
  0 means "not set".
- local-model-catalog.ts: seven models, three harness rows (pi gated) and the
  chips table as a compiled constant, validated by a Zod schema on first use.
  No override file. Model ids are name:tag in lowercase without a slash; every
  model carries paramsB and an (empty) tested list. Chip names match on the
  end of the chip string, so 'M4' is not the chip of 'Apple M4 Pro'.
- recommend.ts: device budget (the wired limit when above 0, else 2/3 of
  memory below 36 GB and 3/4 from 36 GB, less the reserve), need = weights +
  KV cache + 1 GiB + prompt cache, fit good up to 0.85 and tight up to 0.98,
  speed ok, unknown or slow (a chip in no chips row is unknown), and the
  ranking. Verdicts ok, limited (best model under 12 billion parameters) and
  none with its reason. "Recommended" only for a pick with a tested entry for
  this Mac, which no row has today.
- types/local-model.ts: comments brought in line with the code (chip matching,
  budgetShare rounding, a budget of 0 on an Intel Mac).
- cli-registry-no-id-branching.test.ts: the guard also catches a comparison of
  a `cli` field with a CLI id (plus one stray blank line Prettier refused).

Tests: test/local-model-format.test.ts, test/local-model-hardware.test.ts
(the captured output of two real Macs), test/local-model-catalog.test.ts,
test/local-model-recommend.test.ts.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer committed 2026-11-06 16:27:33 +01:00
1 parent 73ce6a1819
commit 92c20fe572
9 files changed
+3423 -79
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/config/local-model-catalog.ts
+278 -27
View File
@@ -2,16 +2,7 @@
* @fileoverview The local model catalogue: which models, harnesses and chips the recommendation
* knows, as a compiled constant validated by a Zod schema.
*
* SKELETON: the schema below is the shape of the contract (it mirrors `LocalModelCatalog` in
* src/types/local-model.ts) and the stock constant is EMPTY. Still to come here:
* - the model rows (ids and byte sizes from the registry manifests, `paramsB`, an empty
* `tested` array each; `flint:40b` stays out), the harness rows and the chips table;
* - the cross-row rules the schema cannot say field by field: unique model ids, unique harness
* `cli`s, `contexts` largest first, `chips` most specific first, `promptCacheTiers` ascending
* and starting at 0;
* - `getLocalModelCatalog()` parsing the constant once, on first use, never at import.
*
* Rules that hold from the start:
* Rules:
* - There is NO override file and no runtime download data in this stage: nothing here reads
* the data dir, and a data file can never decide what gets recommended.
* - A model id is `name:tag` in lowercase with no slash (`LOCAL_MODEL_ID_PATTERN`), so it can
@@ -20,14 +11,71 @@
* registry id as data: no code may compare it with a literal. Whether that CLI exists and can
* take a custom model is checked against the registry at call time, in
* src/local-model/harness-facts.ts, never here.
* - The schema checks more than fields. Across rows it requires: unique model ids and ranks,
* unique harness `cli`s and ranks, `contexts` largest first, a `tested` entry naming a harness
* row, `chips` most specific first, and `promptCacheTiers` ascending from 0.
* - `getLocalModelCatalog()` parses the constant once, on first use and never at import, and
* throws on a bad row. test/local-model-catalog.test.ts pins that the stock constant parses,
* so a bad row fails the gate and never reaches the route.
*
* Where each figure of the stock rows comes from, and what was checked (2026-11-06):
*
* | Figure | Source | Checked |
* |----------------------|-----------------------------------------------------------|--------------------------------------|
* | `id`, `bytes` | registry manifest of the tag, sum of its layer sizes | yes, to the byte, by the facts review |
* | `license` | the model card (all Apache-2.0) | read by the research, not re-checked |
* | `paramsB` | 27.8 from the model card; the others are the count in the | no. Only the 12 billion line reads |
* | | model's name | it, and no row is near that line |
* | `kvBytesPerToken` | COMPUTED from each model's config: 2 x full-attention | no. Not measured in a running |
* | | layers x KV heads x head size x 2 bytes | runtime. The review called the |
* | | | gpt-oss figure plausible, no more |
* | `contexts`, `rank` | a judgement of the design | no |
* | `speedPer100Gbps` | one published run on an M1 Max (400 GB/s): generation | the run was read. It stands for less |
* | | only, short prompt. The two q8_0 rows are SCALED by file | than a session: no long prompt, no |
* | | size, not measured | thinking tokens |
* | `minMacosMajor` | the runtime's documentation (macOS 14) | yes, by the facts review |
* | `promptCacheTiers` | a decision of the design, not a measurement | no |
* | harness `minContext` | 65536: the runtime's documentation for both harnesses. | 65536 yes. 32768 no, which is why |
* | | 32768: recalled | that row is gated |
* | `chips` | the bandwidth column of | yes, read at the source for this |
* | | https://github.com/ggml-org/llama.cpp/discussions/4167 | file |
*
* `tested` is empty on every row: nobody has run any of these models with a harness on a Mac
* yet. Until a row has an entry, the recommendation never says "Recommended".
*/
import { z } from 'zod';
import type { LocalModelCatalog } from '../types.js';
import type { ChipEntry, LocalModelCatalog } from '../types.js';
/** A model id: lowercase name, one colon, a tag. No slash, so no registry host or namespace can ride along. */
export const LOCAL_MODEL_ID_PATTERN = /^[a-z0-9][a-z0-9._-]*:[a-z0-9][a-z0-9._-]*$/;
/**
* Whether `chip` (a `machdep.cpu.brand_string`, 'Apple M4 Pro') is the chip a `ChipEntry.match`
* ('M4 Pro') names: the string must END with the match, and the match must start at the
* beginning or after a space. Case is ignored.
*
* Stricter than "the match occurs in the string" on purpose. 'M4' is not the chip of
* 'Apple M4 Pro', 'M1' is not the chip of 'Apple M10', and a variant this table has never heard
* of ('Apple M6 Pro') matches no row instead of borrowing the bandwidth of its base chip.
*/
export function chipNameMatches(chip: string, match: string): boolean {
const name = chip.trim().toLowerCase();
const wanted = match.trim().toLowerCase();
if (wanted === '' || !name.endsWith(wanted)) return false;
const start = name.length - wanted.length;
return start === 0 || name[start - 1] === ' ';
}
/**
* The memory bandwidth (GB/s) of `chip`, from the first row that names it. `undefined` when the
* chip string is absent or no row names it: the speed is then UNKNOWN, a bandwidth is never guessed.
*/
export function chipBandwidthGbps(chips: readonly ChipEntry[], chip: string | undefined): number | undefined {
if (!chip) return undefined;
return chips.find((row) => chipNameMatches(chip, row.match))?.gbps;
}
const isoDate = z.string().regex(/^\d{4}-\d{2}-\d{2}$/, 'must be an ISO date (YYYY-MM-DD)');
const positiveInt = z.number().int().positive();
@@ -79,7 +127,20 @@ const PromptCacheTierSchema = z
})
.strict();
/** Validates a whole catalogue. Typed against `LocalModelCatalog`, so the two cannot drift apart. */
/** The index of the first value that already occurred earlier in the list, or -1. */
function firstRepeat<T>(values: readonly T[]): number {
const seen = new Set<T>();
for (let i = 0; i < values.length; i++) {
if (seen.has(values[i])) return i;
seen.add(values[i]);
}
return -1;
}
/**
* Validates a whole catalogue: every field, then the rules that hold across rows (see the file
* header). Typed against `LocalModelCatalog`, so the two cannot drift apart.
*/
export const LocalModelCatalogSchema: z.ZodType<LocalModelCatalog> = z
.object({
schema: z.literal(1),
@@ -90,33 +151,223 @@ export const LocalModelCatalogSchema: z.ZodType<LocalModelCatalog> = z
harnesses: z.array(LocalHarnessEntrySchema),
chips: z.array(ChipEntrySchema),
})
.strict();
.strict()
.superRefine((catalog, ctx) => {
const issue = (path: (string | number)[], message: string): void => {
ctx.addIssue({ code: 'custom', path, message });
};
// A repeated id would make "the model" ambiguous, a repeated rank would make the order of
// two models depend on where they sit in the array.
const repeatedId = firstRepeat(catalog.models.map((m) => m.id));
if (repeatedId >= 0) issue(['models', repeatedId, 'id'], 'model ids must be unique');
const repeatedRank = firstRepeat(catalog.models.map((m) => m.rank));
if (repeatedRank >= 0) issue(['models', repeatedRank, 'rank'], 'model ranks must be unique');
const harnessClis = catalog.harnesses.map((h) => h.cli);
const repeatedCli = firstRepeat(harnessClis);
if (repeatedCli >= 0) issue(['harnesses', repeatedCli, 'cli'], 'a harness may be listed only once');
const repeatedHarnessRank = firstRepeat(catalog.harnesses.map((h) => h.rank));
if (repeatedHarnessRank >= 0) issue(['harnesses', repeatedHarnessRank, 'rank'], 'harness ranks must be unique');
catalog.models.forEach((model, m) => {
for (let i = 1; i < model.contexts.length; i++) {
if (model.contexts[i] >= model.contexts[i - 1]) {
issue(['models', m, 'contexts', i], 'contexts must be listed largest first, without repeats');
break;
}
}
// An entry for a harness the catalogue does not list could never match a candidate: a typo.
model.tested.forEach((entry, t) => {
if (!harnessClis.includes(entry.cli)) {
issue(['models', m, 'tested', t, 'cli'], 'a tested entry must name a harness of this catalogue');
}
});
});
// Most specific first ('M4 Max' before 'M4'): a row whose text sits inside a LATER row's text
// is the less specific of the two, so it is in the wrong place. A repeated match is the same
// mistake.
for (let later = 1; later < catalog.chips.length; later++) {
const laterMatch = catalog.chips[later].match.toLowerCase();
const shadowing = catalog.chips.slice(0, later).find((row) => laterMatch.includes(row.match.toLowerCase()));
if (shadowing) {
issue(
['chips', later, 'match'],
`chips must be listed most specific first: '${shadowing.match}' comes before '${catalog.chips[later].match}'`
);
break;
}
}
// The tiers are read as "the last one whose minimum is not above this Mac's memory", so they
// must start at 0 (every Mac has a tier) and ascend.
if (catalog.promptCacheTiers[0].minMemGb !== 0) {
issue(['promptCacheTiers', 0, 'minMemGb'], 'the first prompt cache tier must start at 0');
}
for (let i = 1; i < catalog.promptCacheTiers.length; i++) {
if (catalog.promptCacheTiers[i].minMemGb <= catalog.promptCacheTiers[i - 1].minMemGb) {
issue(['promptCacheTiers', i, 'minMemGb'], 'prompt cache tiers must ascend by minMemGb');
break;
}
}
});
const KIB = 1024;
const MIB = 1024 ** 2;
const GIB = 1024 ** 3;
/**
* The catalogue that ships with Codeman. EMPTY for now (no model, harness or chip rows), but
* valid: with it `recommend()` can only answer verdict `none`.
*
* The two constants that are already decided are filled in: macOS 14 is the oldest version the
* runtime supports, and the prompt cache is 512 MiB on a Mac below 32 GB and 2 GiB from 32 GB.
* The catalogue that ships with Codeman. Never read directly outside this file and its test:
* callers use `getLocalModelCatalog()`, which validates it first.
*/
export const STOCK_LOCAL_MODEL_CATALOG: LocalModelCatalog = {
schema: 1,
updated: '2026-11-06',
// The oldest macOS the model runtime supports.
minMacosMajor: 14,
// Host memory the runtime's prompt cache may take beside the model: 512 MiB on a Mac below
// 32 GB, 2 GiB from 32 GB. Part of the need of every candidate.
promptCacheTiers: [
{ minMemGb: 0, bytes: 512 * 1024 ** 2 },
{ minMemGb: 32, bytes: 2 * 1024 ** 3 },
{ minMemGb: 0, bytes: 512 * MIB },
{ minMemGb: 32, bytes: 2 * GIB },
],
// Ordered by rank. The higher rank wins among models that fit equally well and are equally
// fast. `flint:40b` is left out on purpose: its plain tag is the slow build on a Mac and it
// has an open bug with tool arguments.
models: [
{
id: 'qwen3.5:9b',
label: 'Qwen3.5 9B',
license: 'Apache-2.0',
paramsB: 9,
bytes: 6_550_825_373,
kvBytesPerToken: 32 * KIB,
contexts: [65536, 32768],
rank: 1,
// 37.1 tokens per second measured on 400 GB/s.
speedPer100Gbps: 9.3,
tested: [],
},
{
id: 'qwen3.5:9b-q8_0',
label: 'Qwen3.5 9B (Q8)',
license: 'Apache-2.0',
paramsB: 9,
bytes: 10_449_217_949,
kvBytesPerToken: 32 * KIB,
contexts: [65536, 32768],
rank: 2,
// Not measured: the 9.3 of the row above scaled by file size.
speedPer100Gbps: 5.8,
tested: [],
},
{
id: 'gpt-oss:20b',
label: 'GPT-OSS 20B',
license: 'Apache-2.0',
paramsB: 20,
bytes: 13_793_441_427,
kvBytesPerToken: 24 * KIB,
contexts: [131072, 65536],
rank: 3,
// No speed figure: its speed is unknown on every chip.
tested: [],
},
{
id: 'qwen3.6:35b-a3b',
label: 'Qwen3.6 35B-A3B',
license: 'Apache-2.0',
paramsB: 35,
bytes: 22_621_314_161,
kvBytesPerToken: 20 * KIB,
contexts: [131072, 65536],
rank: 4,
// 54.5 tokens per second measured on 400 GB/s (3 billion parameters are active per token).
speedPer100Gbps: 13.6,
tested: [],
},
{
id: 'qwen3.8:27b',
label: 'Qwen3.8 27B',
license: 'Apache-2.0',
paramsB: 27.8,
bytes: 17_741_871_939,
kvBytesPerToken: 64 * KIB,
contexts: [131072, 65536, 32768],
rank: 5,
// 11.8 tokens per second measured on 400 GB/s.
speedPer100Gbps: 2.95,
tested: [],
},
{
id: 'qwen3.8:27b-q8_0',
label: 'Qwen3.8 27B (Q8)',
license: 'Apache-2.0',
paramsB: 27.8,
bytes: 29_978_241_837,
kvBytesPerToken: 64 * KIB,
contexts: [262144, 131072],
rank: 6,
// Not measured: the 2.95 of the row above scaled by file size.
speedPer100Gbps: 1.7,
tested: [],
},
{
id: 'qwen3.5:122b-a10b',
label: 'Qwen3.5 122B-A10B',
license: 'Apache-2.0',
paramsB: 122,
bytes: 81_370_035_877,
kvBytesPerToken: 24 * KIB,
contexts: [131072],
rank: 7,
// No speed figure: its speed is unknown on every chip.
tested: [],
},
],
// The higher rank wins when a model can run with more than one harness.
harnesses: [
{ cli: 'opencode', minContext: 65536, rank: 3 },
// Sends a fixed prompt of about 36,000 tokens, so the first answer takes minutes.
{ cli: 'claude', minContext: 65536, rank: 2, slowFirstTurn: true },
// Gated: neither its 32768 minimum nor its handling of a `name:tag` model id is verified.
{ cli: 'pi', minContext: 32768, rank: 1, gated: true },
],
// Memory bandwidth in GB/s, most specific first. Only chips that shipped and are in the source
// table are listed. Where one name covers two bandwidths (M3 Max 300 or 400, M4 Max 410 or 546,
// M5 Max 460 or 614) the LOWER one stands, so a speed computed from it is a floor.
chips: [
{ match: 'M5 Ultra', gbps: 1228 },
{ match: 'M3 Ultra', gbps: 800 },
{ match: 'M2 Ultra', gbps: 800 },
{ match: 'M1 Ultra', gbps: 800 },
{ match: 'M5 Max', gbps: 460 },
{ match: 'M4 Max', gbps: 410 },
{ match: 'M3 Max', gbps: 300 },
{ match: 'M2 Max', gbps: 400 },
{ match: 'M1 Max', gbps: 400 },
{ match: 'M5 Pro', gbps: 307 },
{ match: 'M4 Pro', gbps: 273 },
{ match: 'M3 Pro', gbps: 150 },
{ match: 'M2 Pro', gbps: 200 },
{ match: 'M1 Pro', gbps: 200 },
{ match: 'M5', gbps: 154 },
{ match: 'M4', gbps: 120 },
{ match: 'M3', gbps: 100 },
{ match: 'M2', gbps: 100 },
{ match: 'M1', gbps: 68 },
],
models: [],
harnesses: [],
chips: [],
};
let validated: LocalModelCatalog | undefined;
/**
* The catalogue in force. There is no override in this stage, so this is the stock constant;
* callers go through this function anyway, so a later stage can change where it comes from
* without touching them.
* The catalogue in force: the stock constant, validated once on first use. Callers go through
* this function, so a later stage can change where the catalogue comes from without touching
* them. Throws when the constant breaks its own schema, which the catalogue test rules out.
*/
export function getLocalModelCatalog(): LocalModelCatalog {
return STOCK_LOCAL_MODEL_CATALOG;
validated ??= LocalModelCatalogSchema.parse(STOCK_LOCAL_MODEL_CATALOG);
return validated;
}