fix(grok): correct opencode provider (Responses API), stdin, reasoning cost

A live opencode run against api.x.ai/v1 surfaced three real bugs:

1. Provider package — grok-build-0.1 is driven via the OpenAI Responses API
   (opencode calls model.responses()). @ai-sdk/openai-compatible is
   chat/completions only and errors "responses is not a function". Switch the
   generated opencode.json provider + the grok image to @ai-sdk/openai.
2. Headless hang — `opencode run` blocks after init without a TTY; close stdin
   (`< /dev/null`) in the entrypoint so it proceeds to the model call.
3. Reasoning-token cost — grok-build-0.1 is a reasoning model; reasoning tokens
   bill as output but opencode stores them in a separate column. cost_for_session
   folds tokens_reasoning into output (else ~22x undercount).

Verified end-to-end against a real session row (input=6120, output=1,
reasoning=226, cache_read=1856): our pricing reproduces opencode's stored USD
cost ($0.0069452) exactly. Tests anchored to that real row.

docker/agent-grok.Dockerfile

@@ -12,11 +12,12 @@ FROM roboco-agent-base
 
 USER root
 
-# opencode — the OpenAI-protocol agent runtime. The @ai-sdk/openai-compatible
-# package backs the custom xAI provider declared in the generated opencode.json;
-# opencode also resolves it at runtime, but pre-installing keeps first spawn off
-# the network.
-RUN npm install -g opencode-ai @ai-sdk/openai-compatible \
+# opencode — the OpenAI-protocol agent runtime. grok-build-0.1 is driven via the
+# OpenAI Responses API, so the provider package is @ai-sdk/openai (NOT
+# @ai-sdk/openai-compatible, which is chat/completions only and errors with
+# "responses is not a function"). opencode resolves it at runtime, but
+# pre-installing keeps first spawn off the network.
+RUN npm install -g opencode-ai @ai-sdk/openai \
     && npm cache clean --force \
     && rm -rf /root/.npm /tmp/*
 

docker/scripts/grok-agent-entrypoint.sh

@@ -16,6 +16,10 @@ python -m roboco.llm.providers.opencode_config
 # positional); `--` separates it from flags so a prompt starting with `--`
 # cannot be parsed as CLI options. The model also comes from the rendered
 # config; --model is passed explicitly as belt-and-suspenders.
+#
+# `< /dev/null` is REQUIRED: without a closed stdin, `opencode run` hangs after
+# init in a headless / no-TTY environment (it blocks waiting on stdin). Verified
+# live — closing stdin lets the run proceed to the model call and exit cleanly.
 exec opencode run \
   --model "xai/${ROBOCO_AGENT_MODEL:-grok-build-0.1}" \
-  -- "${ROBOCO_INITIAL_PROMPT:-}"
+  -- "${ROBOCO_INITIAL_PROMPT:-}" < /dev/null