The spec: plan_write and plan_update (new, shared, offered in every mode) and plan_submit (now shared) keep one structured plan — findings, objectives, phases of tasks — in place of the todo list, which lives on as a former name of plan_write. The shared system text is one text for both projects, with variables for what differs; the mode texts, a prototypes block and a library block are shared. acp.md: the client hands the device what only it knows (context, library, prototypes), the plan travels as a structure (plan_state), library calls carry the chat's scope, and a client may rewind a session. loop.json says its numbers as numbers. Four conformance areas: plan, prototype, library_scope, toolcall_index. The CLI: the plan is kept per session in the store and drawn above the prompt and on the approval card; the prompt is assembled from the spec's texts with their variables filled; the link reads the instance's instructions, personalization, knowledge scope and prototype offer, sends the plan as a structure and answers rewind; library calls to the instance carry the session as scope; a prototype written in the terminal is saved as a file and named in the transcript; a tool-call fragment without an index continues the last call; the default theme is Moria; dead exports and Hermes leftovers removed. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
39 lines
1.7 KiB
TypeScript
39 lines
1.7 KiB
TypeScript
// The harness spec's conformance cases (harness/conformance/*.json), shared with LLeMbas.
|
|
// bun run harness record fill in the `expect` of every case that has none, from LLeMbas CLI
|
|
// bun run harness record --all record every case again, and say which ones changed
|
|
// Recording is how a new case gets its answer; a changed answer is a change of behaviour, which
|
|
// the spec's version and both projects must then follow.
|
|
import { readdirSync, readFileSync, writeFileSync } from "node:fs"
|
|
import { join } from "node:path"
|
|
import { AREAS } from "../tests/conformance.ts"
|
|
|
|
const dir = join(import.meta.dir, "..", "harness", "conformance")
|
|
const [cmd, flag] = process.argv.slice(2)
|
|
if (cmd !== "record") {
|
|
console.error("usage: bun run harness record [--all]")
|
|
process.exit(2)
|
|
}
|
|
let filled = 0
|
|
let changed = 0
|
|
for (const f of readdirSync(dir).filter((x) => x.endsWith(".json")).sort()) {
|
|
const area = f.replace(/\.json$/, "")
|
|
const run = AREAS[area]
|
|
if (!run) {
|
|
console.log(`${area}: no runner in tests/conformance.ts yet — skipped`)
|
|
continue
|
|
}
|
|
const doc = JSON.parse(readFileSync(join(dir, f), "utf8")) as { about: string; cases: Record<string, unknown>[] }
|
|
for (const c of doc.cases) {
|
|
if ("expect" in c && flag !== "--all") continue
|
|
const { expect: before, ...input } = c
|
|
const now = run(input)
|
|
if ("expect" in c && JSON.stringify(before) !== JSON.stringify(now)) {
|
|
changed++
|
|
console.log(`${area}: ${JSON.stringify(input)}\n was ${JSON.stringify(before)}\n now ${JSON.stringify(now)}`)
|
|
} else if (!("expect" in c)) filled++
|
|
c.expect = now
|
|
}
|
|
writeFileSync(join(dir, f), JSON.stringify(doc, null, 2) + "\n")
|
|
}
|
|
console.log(`recorded: ${filled} new, ${changed} changed`)
|