fix: remove one machine's addresses and paths from the shipped defaults
The plugin was developed against an Ollama on a private LAN address, and that address had reached places that ship: - the `config` parameter description the MODEL reads on every request; - the commented example in `cordis.patch.yml`, the layer every profile applies; - `scripts/smoke.mjs` and `scripts/measure.mjs` endpoint defaults; - both measure scripts' default workspace, which was an absolute local path and named a private repository; - README examples and test fixtures. All of them now use `http://127.0.0.1:11434`, which is Ollama's documented default and belongs to no particular machine — kept rather than emptied because `validateSettings` requires an http(s) URL, so an empty default would turn every call into INVALID_SETTINGS until someone configured it. Test fixtures use 192.0.2.10 instead: TEST-NET-1 is reserved for documentation and cannot point at a host anybody runs. The `focus` and `config` examples are generic, and the workspace defaults are the working directory. Two script bugs surfaced once the defaults stopped pointing at a live box, and are fixed here. `measure.mjs` built its own configuration literal, which was ten fields short of the schema — harmless while nothing validated it, and a refused call the moment `execute` began checking the section it was handed; it now resolves its configuration through the plugin's own `Config`, so it cannot drift again. It also crashed on a failed search (`first.index.scanned` of a result that has no index) instead of reporting the endpoint it could not reach, which is now the ordinary case. `scope-measure.mjs` divided by a scope that does not exist in any workspace without focus markers, and now says so. Also corrects `cordis.patch.yml`'s description of what the row registers: in 0.1.7 the exported `Config` is the settings registration, not a namespace on `ctx.settings`.
This commit is contained in:
1 parent
7261d46ee2
commit
a48e05585e
7 files changed
+93
-48
No files matched your search
+41
-27
@@ -19,38 +19,37 @@ import { mkdtemp, rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
|
||||
import { apply } from '../index.js'
|
||||
import { apply, Config, settingsSnapshot } from '../index.js'
|
||||
|
||||
const WORKSPACE = process.argv[2] ?? '/root/workspaces/ha-runtime'
|
||||
const QUERY = process.argv[3] ?? 'how does the occupancy state machine decide a room is occupied'
|
||||
// Whatever repository you run this against, and whatever you want to ask it.
|
||||
// The defaults are the working directory and a query that names a behaviour
|
||||
// rather than a symbol — which is the kind of question the plugin exists for.
|
||||
const WORKSPACE = process.argv[2] ?? process.cwd()
|
||||
const QUERY = process.argv[3] ?? 'where is the retry policy applied'
|
||||
const BUDGET_MS = Number(process.argv[4] ?? 90_000)
|
||||
|
||||
const API_BASE = process.env.RECALL_API_BASE ?? 'http://10.50.1.2:11434'
|
||||
// The endpoint to measure against: the Ollama convention unless RECALL_API_BASE
|
||||
// says otherwise. Nothing here is specific to the machine this was written on.
|
||||
const API_BASE = process.env.RECALL_API_BASE ?? 'http://127.0.0.1:11434'
|
||||
const MODEL = process.env.RECALL_MODEL ?? 'unclemusclez/jina-embeddings-v2-base-code:latest'
|
||||
|
||||
const config = {
|
||||
embeddingApiBase: API_BASE,
|
||||
embeddingModel: MODEL,
|
||||
embeddingDimensions: 768,
|
||||
embeddingApiKey: '',
|
||||
embeddingBatchSize: 32,
|
||||
embeddingConcurrency: 4,
|
||||
embeddingTimeoutMs: 120_000,
|
||||
extensions: [],
|
||||
exclude: [],
|
||||
maxFiles: 20_000,
|
||||
maxFileBytes: 1_048_576,
|
||||
chunkLines: 48,
|
||||
maxChunkLines: 80,
|
||||
overlapLines: 8,
|
||||
defaultLimit: 8,
|
||||
maxLimit: 25,
|
||||
perFileLimit: 2,
|
||||
excerptLines: 40,
|
||||
minSimilarity: 0.2,
|
||||
syncBudgetMs: BUDGET_MS,
|
||||
stateDir: '',
|
||||
}
|
||||
// The measurement's configuration, stated as the few values it cares about and
|
||||
// resolved through the plugin's own schema — so this script can never drift
|
||||
// from the Config the plugin validates against. A hand-written literal used to
|
||||
// stand here, and it was missing ten fields: harmless while nothing checked,
|
||||
// and a refused call the moment `execute` began validating the section it was
|
||||
// handed.
|
||||
const config = settingsSnapshot(
|
||||
Config({
|
||||
embeddingApiBase: API_BASE,
|
||||
embeddingModel: MODEL,
|
||||
embeddingBatchSize: 32,
|
||||
embeddingConcurrency: 4,
|
||||
embeddingTimeoutMs: 120_000,
|
||||
excerptLines: 40,
|
||||
syncBudgetMs: BUDGET_MS,
|
||||
}),
|
||||
)
|
||||
|
||||
/** The smallest context `apply` touches, with no settings provider mounted. */
|
||||
function context() {
|
||||
@@ -92,6 +91,21 @@ async function main() {
|
||||
const coldMs = Date.now() - coldStart
|
||||
console.log('--- FIRST SEARCH (bounded cold start) ---')
|
||||
console.log(`elapsed : ${(coldMs / 1000).toFixed(1)}s (budget ${BUDGET_MS / 1000}s)`)
|
||||
|
||||
// A search that did not run has no index or results to report, and the tool
|
||||
// already says why. Without this the first `first.index.*` line throws a
|
||||
// TypeError that buries the actual cause — an endpoint that is not there is
|
||||
// the ordinary case now that the default is the loopback convention.
|
||||
if (first.ok !== true) {
|
||||
console.log(`failed : ${first.errorCode ?? 'UNKNOWN'}`)
|
||||
console.log(`note : ${first.note ?? '(none)'}`)
|
||||
if (first.remedy !== undefined) console.log(`remedy : ${first.remedy}`)
|
||||
console.log('')
|
||||
console.log(`nothing to measure: point RECALL_API_BASE at a reachable endpoint (currently ${API_BASE}).`)
|
||||
process.exitCode = 1
|
||||
return
|
||||
}
|
||||
|
||||
console.log(`scanned files : ${first.index.scanned}`)
|
||||
console.log(`indexed files : ${first.index.files}`)
|
||||
console.log(`chunks : ${first.index.chunks}`)
|
||||
|
||||
@@ -6,10 +6,9 @@
|
||||
* cold-start cost they imply are all arithmetic over the chunker, which is
|
||||
* deterministic and offline.
|
||||
*
|
||||
* The cold-start projection uses the throughput actually measured against the
|
||||
* real endpoint on this repository: 2,257 chunks embedded in 90s, about 25
|
||||
* chunks/s. It is a projection from a real figure, not a guess, and it is
|
||||
* labelled as a projection.
|
||||
* The cold-start projection uses a throughput measured against a live endpoint
|
||||
* during development: 2,257 chunks embedded in 90s, about 25 chunks/s. It is a
|
||||
* projection from a real figure, not a guess, and it is labelled as one.
|
||||
*
|
||||
* node scripts/scope-measure.mjs [workspace]
|
||||
*/
|
||||
@@ -20,9 +19,15 @@ import { join } from 'node:path'
|
||||
import { chunkFile } from '../lib/chunk.js'
|
||||
import { listCodeFiles } from '../lib/walk.js'
|
||||
|
||||
const WORKSPACE = process.argv[2] ?? '/root/workspaces/ha-runtime'
|
||||
// The repository to measure; the working directory by default, so the script
|
||||
// carries no assumption about where anyone keeps their code.
|
||||
const WORKSPACE = process.argv[2] ?? process.cwd()
|
||||
|
||||
/** Chunks per second, measured on this repository against the live endpoint. */
|
||||
/**
|
||||
* Chunks per second, measured against a live endpoint during development
|
||||
* (2,257 chunks in 90s). A measured constant, not a guess — and a projection
|
||||
* input, which is why the cold-start figures below are labelled as projections.
|
||||
*/
|
||||
const MEASURED_CHUNKS_PER_SECOND = 2257 / 90
|
||||
|
||||
/** Count files and chunks for one directory, relative to a base for display. */
|
||||
@@ -98,6 +103,18 @@ async function main() {
|
||||
if (scopes.length > 10) console.log(` … and ${scopes.length - 10} more`)
|
||||
console.log('')
|
||||
|
||||
// A workspace with no marker files has no scopes to compare, and that is a
|
||||
// normal answer rather than a failure — the plugin falls back to the whole
|
||||
// workspace there. Say so and stop, instead of dividing by the scope that
|
||||
// does not exist.
|
||||
if (scopes.length === 0) {
|
||||
console.log('=== WHAT SCOPING BUYS ===')
|
||||
console.log(' nothing here: no directory in this workspace carries a focus marker,')
|
||||
console.log(' so every call indexes the whole workspace. Add a marker file (see')
|
||||
console.log(' focusMarkers in the README) to a module you work on to create one.')
|
||||
return
|
||||
}
|
||||
|
||||
const median = scopes[Math.floor(scopes.length / 2)]
|
||||
const totalScoped = scopes.reduce((sum, scope) => sum + scope.chunks, 0)
|
||||
console.log('=== WHAT SCOPING BUYS ===')
|
||||
|
||||
+4
-1
@@ -19,7 +19,10 @@ import { rankChunks } from '../lib/rank.js'
|
||||
import { RecallIndex } from '../lib/store.js'
|
||||
import { listCodeFiles } from '../lib/walk.js'
|
||||
|
||||
const API_BASE = process.env.RECALL_API_BASE ?? 'http://10.50.1.2:11434'
|
||||
// The endpoint to check against. The default is the Ollama convention, which
|
||||
// is what the plugin's own schema defaults to; point RECALL_API_BASE at your
|
||||
// own host when it is somewhere else.
|
||||
const API_BASE = process.env.RECALL_API_BASE ?? 'http://127.0.0.1:11434'
|
||||
const MODEL = process.env.RECALL_MODEL ?? 'unclemusclez/jina-embeddings-v2-base-code:latest'
|
||||
const DIMENSIONS = Number(process.env.RECALL_DIMENSIONS ?? 768)
|
||||
|
||||
|
||||
Reference in new issue
Block a user