mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
b3f8b4c9c6
Behavioral gaps from the coverage audit (line coverage was already 100%; these
close BEHAVIOR gaps):
- fs-local: service-level writeText/editText pre-abort → FS_ABORTED (file
unchanged); concurrent guarded-write race and mixed write-vs-edit race (one
wins, one FS_STALE_VERSION, locks released); edit→edit version refresh at the
provider; the replaceIfVersion post-write version matches a fresh stat. fsio:
a mid-stream abort → FS_ABORTED (previously only pre-abort was covered).
- fs-policy: the agent-without-session owner rung ({agent:{}} → no owner →
createIfAbsent / FS_NOT_OBSERVED); fs/write-intent first-wins (symmetric to
the existing edit-intent test).
- tool-fs: abort-through-the-tool for read/write/edit (isError FS_ABORTED, file
unchanged); a deterministic tool-tier concurrent-edit race via a shared read;
the throwing-fs/observed contract (a throwing listener surfaces as isError but
the mutation already hit disk); the replace_all edit message; parseReadArgs
rejects fractional/NaN offset and zero/negative limit.
- dsh-fs: FsError chains a cause through ErrorOptions.
New with-key e2e (packages/fs/tool-fs/tests/fs-tools.e2e.ts, self-skips without
DEEPSEEK_API_KEY): a real model drives the real read/write/edit tools to create
→ read → edit a file, verified on disk; a second test proves a relative path
resolves against the per-session cwd (factory meta.cwd) not config.cwd. Booted
via a plain tests/harness.ts. Added dsh-agent-loop + dsh-llm-deepseek devDeps.
48 lines
1.8 KiB
TypeScript
48 lines
1.8 KiB
TypeScript
import { Context } from 'cordis'
|
|
import LlmService from '@deepseek-ai/dsh-llm'
|
|
import SessionStore from '@deepseek-ai/dsh-session'
|
|
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
|
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
|
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
|
|
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
|
|
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
|
|
import * as FsPolicy from '@deepseek-ai/dsh-fs-policy'
|
|
import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
|
|
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
|
|
|
/**
|
|
* Shared harness for the fs-tools with-key e2e: a minimal real agent stack (the
|
|
* DeepSeek adapter + the real fs provider + the read-before-write/edit policy +
|
|
* the model-facing read/write/edit tools). Lives outside the *.e2e.ts pattern so
|
|
* importing it never re-registers another file's tests.
|
|
*
|
|
* `fsCwd` is the local backend's default base; a per-session cwd (set via a
|
|
* session header) overrides it, but this harness creates agents without a
|
|
* session cwd, so the provider default IS the workspace.
|
|
*/
|
|
export async function fsHarness(fsCwd: string): Promise<Context> {
|
|
const ctx = new Context()
|
|
await ctx.plugin(LlmService)
|
|
await ctx.plugin(SessionStore)
|
|
await ctx.plugin(SystemPrompt)
|
|
await ctx.plugin(ToolRegistry)
|
|
await ctx.plugin(AgentRegistry)
|
|
await ctx.plugin(AgentLoop, { agents: [] })
|
|
await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
|
|
await ctx.plugin(LocalFileSystem, { cwd: fsCwd })
|
|
await ctx.plugin(FsPolicy)
|
|
await ctx.plugin(ToolFs)
|
|
return ctx
|
|
}
|
|
|
|
export function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
|
|
return new Promise((resolve) => {
|
|
const dispose = ctx.on('agent/status', (subject, status) => {
|
|
if (subject === agent && status === 'idle') {
|
|
dispose()
|
|
resolve()
|
|
}
|
|
})
|
|
})
|
|
}
|