HomerandClaude Opus 5.5
28ff205ed0
LLeMbas CLI 2.0 is LLeMbas-server-specific (CLI rule 2). Removed: the anthropic, gemini, ollama and responses clients, context discovery and llama-swap unloading (discover.ts), the Connection schema with its dialect, auth, key_cmd, discover, unload_url and one_model_at_a_time, the model `fallback` (it only ever moved to another server), effort_map and cache, and the multi-connection refs. Kept: openai-chat, http, sse, think, effort, tokens and all of src/lembas. - connections.yaml holds the login (`type: webui`, as lembas login writes it). A custom entry from 1.x is read past with a warning that says how to log in, so an old file still starts; with several logins left, the latest is used and the others named. - A model's ref is the id the server serves it under; the older forms (`<login>/<id>`, `<login>/<model>`) still resolve and config.yaml is rewritten once. Without a login there is no model, and the error (and the first-run screen, now the sign-in alone) says `lembas login <address>`. - A login to another server signs this machine out of the previous one. - The window is the server's word (no discovery); a capacity group comes from the server's `capacity.group` alone; embeddings use the server's /v1/embeddings. - `lembas models` lists the server's models; install.sh's starter files, the README and the JSON schemas say the same. Tests: every fixture is a login now (the fake server lists models, answers other GETs with 404, and can hand one model to another script, as a server with several backends); the dialect suites and the cross-connection tests are gone with their code. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
89 lines
5.2 KiB
TypeScript
89 lines
5.2 KiB
TypeScript
import { afterEach, describe, expect, test } from "bun:test"
|
|
import { mkdirSync, mkdtempSync, writeFileSync } from "node:fs"
|
|
import { tmpdir } from "node:os"
|
|
import { join } from "node:path"
|
|
import { createApp } from "../src/app.ts"
|
|
import type { AskReply, Event } from "../src/bus/index.ts"
|
|
import { paths } from "../src/config/paths.ts"
|
|
import { resetLearned } from "../src/provider/learned.ts"
|
|
import { contextBreakdown, renderBreakdown } from "../src/session/context.ts"
|
|
import { delta, fakeProvider, toolCall, usage, type Fake } from "./fake-provider.ts"
|
|
|
|
let fake: Fake | undefined
|
|
afterEach(() => {
|
|
fake?.stop()
|
|
resetLearned()
|
|
})
|
|
|
|
|
|
function app(yaml: string, script: Parameters<typeof fakeProvider>[0], config = "") {
|
|
fake = fakeProvider(script)
|
|
mkdirSync(paths.config, { recursive: true })
|
|
writeFileSync(join(paths.config, "connections.yaml"), yaml.replaceAll("URL", fake.url), { mode: 0o600 })
|
|
writeFileSync(join(paths.config, "config.yaml"), `model: f/m\n${config}`)
|
|
const cwd = mkdtempSync(join(tmpdir(), "ph-ctx-"))
|
|
writeFileSync(join(cwd, "big.txt"), "x".repeat(6000))
|
|
return createApp({ cwd, mode: "edit", store: false, asker: { ask: async (): Promise<AskReply> => ({ kind: "once" }) } })
|
|
}
|
|
|
|
describe("context", () => {
|
|
test("past auto_at: nothing already sent is cut; the conversation is compacted, with a table of the reads", async () => {
|
|
// window 16000, auto_at 0.6 → limit 9600. Harness spec 3.0.0 (context.md): old tool outputs are
|
|
// never pruned in place — that would make the server read everything after them again.
|
|
const a = app(`connections:\n f:\n type: webui\n url: URL\n models: { f/m: { context: 16000 } }\n`, [
|
|
{ chunks: [toolCall(0, "c1", "read", '{"path":"big.txt"}'), usage(1000, 10)] },
|
|
{ chunks: [toolCall(0, "c2", "read", '{"path":"big2.txt"}'), usage(6600, 10)] },
|
|
{ chunks: [delta({ content: "## Summary\nRead two files." })] },
|
|
{ chunks: [delta({ content: "done" }), usage(2000, 5)] },
|
|
], "compaction: { auto_at: 0.6 }\n")
|
|
const lines = Array.from({ length: 1000 }, (_, i) => `line ${i} of a long file`).join("\n")
|
|
writeFileSync(join(a.project.root, "big.txt"), lines)
|
|
writeFileSync(join(a.project.root, "big2.txt"), lines)
|
|
const notices: string[] = []
|
|
a.bus.on((e: Event) => e.type === "notice" && notices.push(e.message))
|
|
await a.engine.prompt("go")
|
|
expect(notices.some((n) => n.includes("pruned"))).toBe(false)
|
|
expect(notices.some((n) => n.includes("compacting"))).toBe(true)
|
|
// The first read went out whole, and stayed whole until the summary replaced the conversation.
|
|
const sent = fake!.requests[1].messages.filter((m: any) => m.role === "tool").map((m: any) => m.content as string)
|
|
expect(sent[0]).toStartWith("[#0001 big.txt lines 1-1000 of 1000 sha ")
|
|
expect(sent[0]).toContain("line 999 of a long file")
|
|
// After it: the summary, the harness's table of what was read, and the request word for word.
|
|
const after = JSON.stringify(fake!.requests[3].messages)
|
|
expect(after).toContain("Read two files.")
|
|
expect(after).toContain("## Files read before this summary")
|
|
expect(after).toMatch(/\| big\.txt \| 1-1000 of 1000 \| [0-9a-f]{8} \| #0001 \|/)
|
|
expect(after).toMatch(/\| big2\.txt \| 1-1000 of 1000 \| [0-9a-f]{8} \| #0002 \|/)
|
|
})
|
|
|
|
test("too full: compacted mid-task, then told to carry on", async () => {
|
|
const a = app(`connections:\n f:\n type: webui\n url: URL\n models: { f/m: { context: 4000 } }\n`, [
|
|
{ chunks: [delta({ content: "y".repeat(8000) }), toolCall(0, "c1", "list", "{}"), usage(3900, 2000)] },
|
|
{ chunks: [delta({ content: "## What we are doing\nA long task." })] },
|
|
{ chunks: [delta({ content: "carried on" }), usage(500, 5)] },
|
|
], "compaction: { auto_at: 0.8 }\n")
|
|
const notices: string[] = []
|
|
a.bus.on((e: Event) => e.type === "notice" && notices.push(e.message))
|
|
await a.engine.prompt("go")
|
|
expect(notices.some((n) => n.includes("compacting the conversation"))).toBe(true)
|
|
expect(fake!.requests[1].messages[0].content).toContain("## Transcript")
|
|
const last = fake!.requests[2].messages
|
|
expect(JSON.stringify(last[1])).toContain("A long task.")
|
|
// the original request comes back verbatim, with the note
|
|
expect(last.at(-1).content).toStartWith("go\n(The conversation was compacted")
|
|
expect(last.at(-1).content).toContain("This was the request")
|
|
})
|
|
|
|
test("/context: parts of the system prompt, tools, the conversation, against the window", async () => {
|
|
const a = app(`connections:\n f:\n type: webui\n url: URL\n models: { f/m: { context: 32768 } }\n`, [{ chunks: [toolCall(0, "c1", "read", '{"path":"big.txt"}'), usage(1500, 20)] }, { chunks: [delta({ content: "ok" }), usage(3100, 5)] }])
|
|
await a.engine.prompt("read it")
|
|
const system = a.engine.o.system(a.engine.mode, a.engine.model)
|
|
const text = renderBreakdown(contextBreakdown(a.engine, system, [], undefined, a.engine.o.tools))
|
|
expect(text).toContain("window 32.8k")
|
|
expect(text).toContain("system prompt")
|
|
expect(text).toMatch(/tool definitions \(\d+\)/)
|
|
expect(text).toMatch(/tool results\s+514/) // one 6000-character line, cut at 2000 by read, under its header
|
|
expect(text).toMatch(/in use\s+3\.1k/)
|
|
})
|
|
})
|