feat: improve agent execution controls

[Viking602]

Summary

• Adds per-run and cumulative session budgets with continuation-safe execution state.
• Adds model connection, total-request, and stream-idle timeouts with typed errors.
• Adds bounded orchestration duration and per-dispatch timeouts while retaining concurrency limits.
• Adds context fitting, optional typed context selection, control/resume handling, and durable checkpoint coverage.
• Preserves failed tool and process feedback for model correction and converts recoverable panics into typed failures.
• Extends provider adapters and structured-output handling with compatibility and ownership tests.

Applications continue to own session identity, routing, persistence, provider credentials, and deployment policy.

Validation

• make ci-local
• make verify
• go test -race -timeout=10m ./...

[cursor]

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_f2c43a98-3db6-42ef-b11b-762dda3c1c22)

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	⚠️ Failed 2026-09-20T08:09:59.209908Z	fb4996e	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.