dsh-llm-pi-ai-image-offload
恢复 pi-ai 路由的 request-image 令牌计价，使 dsh-spill-policy 能够卸载过大的 base64 图像，避免超出上下文窗口。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:ender-candle/dsh-llm-pi-ai-image-offload#f5e152629aa86ba61835bb48c716489c16a3f6c8Llm Pi Ai Image Offload 以 dsh-llm-pi-ai-image-offload 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
中文文档：README.zh-CN.md
Restores request-image token pricing for adapter routes that declare none
— in practice every route served by @deepseek-ai/dsh-llm-pi-ai.
Naming: the package is called image-offload after the capability it restores,
not after the method it patches. The patched method is imageRequestPricing,
whose job is to price an image in tokens so the budget checks can compare it
against maxInlineTokens and offload what does not fit. "Pricing" here is token
accounting, not billing.
LlmAdapter.imageRequestPricing() returns undefined by default, meaning "this
route declares no image pricing". Only dsh-llm-deepseek overrides it. pi-ai
does not.
@deepseek-ai/dsh-spill-policy asks for that calculator whenever a tool result
carries images:
const calculator = ctx.get("llm")?.imageRequestPricing(provider, model);
if (calculator === undefined) throw new Error("the current model has no image token calculator");
That throw is caught by the plugin's own outer try, which logs
spill-policy: ...; keeping the inline content and returns nothing. The tool
result therefore stays completely inline: a multi-megabyte base64 image goes to
the provider verbatim and consumes the context window.
@deepseek-ai/dsh-token-meter degrades the same way, falling back to a fixed
structural heuristic instead of pricing the bytes actually sent.
It installs imageRequestPricing on adapter instances that return no
pricing, and re-applies on every llm/adapters-updated event.
@deepseek-ai/dsh-llm.These routes publish no vision-token accounting, so each occurrence is priced by the bytes actually transmitted for it:
transmitted = min(attachment.bytes, imageRequestTarget(...).maxBytes)
visualTokens = ceil(base64Length(transmitted) / charsPerToken)
base64Length(b) = ceil(b / 3) * 4, matching the harness's own byte accounting.
This is the same unit spill-policy compares against maxInlineTokens, which is
what lets it shed an oversized image instead of keeping it inline.
For the reported failure case — a 2048×2048 JPEG at 1,266,320 bytes on a route
with a 1 MiB request budget — that is base64(1048576) / 4 = 349,526 tokens,
comfortably above the default maxInlineTokens: 12500.
All fields optional.
| field | default | meaning |
|---|---|---|
enabled | true | turn the patch off entirely |
charsPerToken | 4 | base64 character density per token |
maxVisualTokens | 400000 | per-occurrence ceiling |
providers | (all) | allowlist of provider route ids |
debug | false | log each patched route to the harness logger |
Example profile patch:
- id: llm-pi-ai-image-offload
name: dsh-llm-pi-ai-image-offload
config:
debug: true
Shedding does not delete the image from the session, and does not touch the
workspace file. The model receives spill-policy's notice plus a path it can
re-read with read_image, so the image is recoverable rather than lost.
The harness logger writes to an in-memory ring buffer that has no file sink, so a
warn is not observable after the fact. Use debug: true plus a large generated
image, and check the session log for image/offload events — before this patch
that signal never appears.
dsh plugin --profile <profile> add github:ender-candle/dsh-llm-pi-ai-image-offload
Pin a commit for a reproducible install:
dsh plugin --profile <profile> add github:ender-candle/dsh-llm-pi-ai-image-offload#<sha>
dsh plugin --profile <profile> add /absolute/path/to/dsh-llm-pi-ai-image-offload
Either install path puts the package in the profile's node_modules. Add the
name to dsh.profile.bundles in the profile package.json:
{
"dsh": {
"profile": {
"bundles": ["...", "dsh-llm-pi-ai-image-offload"]
}
}
}
The bundle's own cordis.patch.yml inserts the host row, so no manual patch
editing is needed. Restart the harness afterwards — bundles load at startup.
dsh plugin addwrites bothpackage.jsonandpnpm-lock.yaml, so the install stays consistent with the profile's package manager state.
node test/offload.test.mjs # 18 unit checks, no dependencies
The plugin has zero runtime dependencies, so the unit test runs anywhere. A
separate integration check (not shipped) runs against host modules extracted
from app.asar and asserts the descriptor text is byte-identical to the
shipped requestImageHandleText / offloadedImageText serializers.
LlmAdapter instance fields are not a documented extension point. If the
registry shape changes, the patch silently does nothing — by design, since a
missing patch restores exactly the pre-existing behaviour.usage remains the authoritative accounting anchor.