Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(fs): add a minimal read_image tool over the attachment and fs seams

Browse Source 
The model reads a PNG/JPEG/WebP/GIF file, the bytes commit through the
durable attachment lifecycle, and the tool result carries the real
ImageBlock so the image enters context from the next request onward.
FileSystem gains a bounded readBytes primitive (local + E2B providers);
registration is conditional on the attachment store, and a strict
execution gate refuses routes that do not declare image input, so a
text route's durable history stays free of image blocks. llm-replay
models may declare inputModalities, letting keyless ACP snapshots pin
both the sha256-referenced success and the verbatim refusal.

Supersedes the withdrawn route-scoped design of PR #598; the decision
record is .agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md.
This commit is contained in:
creatixchu
2026-08-10 15:09:07 +08:00
parent 3764ce62a5
commit 1861a3fc7c
65 changed files with 1973 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/support/llm-replay/tests/llm-replay.spec.ts
View File

@@ -592,7 +592,7 @@ describe('installLlmReplay (through the real LlmService)', () => {
backoff: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
},
models: [
{ id: 'flash', contextWindow: 128_000 },
{ id: 'flash', contextWindow: 128_000, inputModalities: ['text', 'image'] },
{ id: 'pro', name: 'Pro', description: 'Larger model' },
],
},
@@ -605,13 +605,15 @@ describe('installLlmReplay (through the real LlmService)', () => {
{ id: 'empty', name: 'empty' },
])
await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
{ provider: 'deepseek', id: 'flash', name: 'flash' },
{ provider: 'deepseek', id: 'flash', name: 'flash', inputModalities: ['text', 'image'] },
{ provider: 'deepseek', id: 'pro', name: 'Pro', description: 'Larger model' },
])
await expect(ctx.llm.listModels('empty')).resolves.toEqual([])
await expect(ctx.llm.resolveModelInfo('deepseek', 'flash')).resolves.toMatchObject({
context: { contextWindow: 128_000 },
inputModalities: ['text', 'image'],
})
await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('inputModalities')
await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('context')
await expect(ctx.llm.resolveModelInfo('deepseek', 'unlisted')).resolves.not.toHaveProperty('context')
await expect(ctx.llm.resolveModelInfo('empty', 'unlisted')).resolves.not.toHaveProperty('context')