Neighbor is a Project Think agent on gpt-oss-120b. Its execute tool
runs model-written code in a dynamic worker; MowerConnector puts the
mower there as the `mower.*` namespace (start/push/turn/stop, each
taking an args object). makeMower is the Logo-turtle mower on a
wrapping yard; for now it lives inside the agent's DO.
Getting to green, one symptom at a time:
- chatted instead of acting: say it acts by running code
- reply cut mid-sentence: maxOutputTokens 4096 via beforeTurn
- execute failed creating codemode's runtime facet ("Incorrect type
for the 'class' field"): declare CodemodeRuntime as a DO class
- looked for the mower in the workspace filesystem: activeTools
["execute"], and name the namespace in the prompt
- found the mower, then asked for lawn dimensions: "don't ask me
questions: put it to use"
Green: 36 mower calls, a 30-cell rectangle.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
codeModeMessages turns what I say plus `about` into a prompt: a
neighbor persona, rules for the reply (one async arrow function over
`env`), and the lent things' types. Things are remote and calls on one
are delivered in order, so a lamp example shows pipelining: await only
for a value, or on a batch's last call. With only the rule, the model
awaited every call; with the example, it pipelines.
aboutMower gives the Mower type with Promise returns. The model test
checks the code calls only Mower methods, pushes, and awaits less often
than it calls; it saves the code to itest-output/ via a reporter, since
the test runs in workerd, which can't write files. Model tests get 60s.
Green: both model tests.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
gpt-oss-120b reasons before it answers, and Workers AI's default
max_tokens (256) ran out mid-thought: finish_reason "length", content
null. Ask for 4096, and when there's no reply text, say which choice
and message keys came back instead.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
makeWorkersAiModel narrows the AI binding to one model's chat
completion: the harness gets `complete`, not `run` on any model at
any cost. gpt-oss-120b replies in the OpenAI shape (checked with a
one-off probe), so the text is choices[0].message.content; anything
else throws, naming the keys it got.
Green: the model counts 3 rs in strawberry.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
dckcandClaude Opus 5.5