fix(pi-ai): honor onPayload replacement payloads in openai-completions, bedrock and cursor

The onPayload hook contract (README, docs/extensions.md) is that a non-undefined
return replaces the provider request payload, and every provider except these
three implements it (anthropic, openai-responses family, google, ollama — see
the earlier fix for the responses providers). openai-completions, amazon-bedrock
and cursor invoked the hook fire-and-forget and sent the original payload, so
extensions hooking before_provider_request could never transform the wire body
on these providers.

- openai-completions: await the hook and apply a non-undefined replacement to
  the params used for the request body, raw request dump and error-path
  fallback state
- amazon-bedrock: same for the ConverseStream command input
- cursor: await the hook for the AgentRunRequest; buildGrpcRequest becomes
  async and is exported for direct testing (transport is HTTP/2)
- devin-agent intentionally unchanged: it does not fire the hook at all (its
  payload is a protobuf object), which is a feature gap rather than a dropped
  replacement; documented in README/docs instead
- regression tests: captured wire body reflects async/sync replacement, and an
  undefined return keeps the original payload (completions + bedrock over a
  mocked fetch; cursor by decoding the serialized run request)

docs/extensions.md

@@ -245,7 +245,7 @@ Cancelable pre-events:
 
 - `input`
 - `before_agent_start`
-- `before_provider_request` (may replace provider request payload)
+- `before_provider_request` (may replace provider request payload — the replacement is applied by every provider that fires the hook, which is all of them except `devin-agent`, which does not fire it)
 - `after_provider_response`
 - `context`
 - `agent_start` / `agent_end` — agent loop lifecycle notification; `agent_end` remains notification-only