fix(prompt): add coding-quality exceptions to token-minimization rules

[chicagoist]

Problem

The system prompt in packages/opencode/src/session/prompt/default.txt contains three instructions that conflict with writing reliable code:

1. "minimize output tokens as much as possible" — causes AI agents to omit model names from logs, skip tests, and skip guard clauses for None/edge cases.
2. "MUST answer concisely with fewer than 4 lines" — prevents consequence research, error analysis, and code planning (the most token-costly but most critical activities).
3. "DO NOT ADD ANY COMMENTS" — complex fallback/rotation logic needs inline explanations for future maintainers.

Proposal

Add exceptions for coding tasks so these instructions don't override code quality:

1. Token minimization: explicitly state "never sacrifice correctness, debuggability, or completeness for token efficiency"
2. 4-line limit: exempt code planning, consequence research, error analysis
3. No comments: exempt complex logic, workarounds, security-critical sections

Impact

Only default.txt needs changes (~3 line modifications). All other prompt files (anthropic.txt, gpt.txt, gemini.txt, plan.txt, etc.) can be updated similarly if maintainers agree.

[github-actions]

This issue does not follow our contributing guidelines.

What needs to be fixed:

• The issue does not use one of the three required templates: Bug Report, Feature Request, or Question. Please resubmit using the appropriate template. If this is a feature request, the title should start with [FEATURE]: and include the required verification checkbox.

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

---

This issue may be a duplicate of an existing issue. Please check:

• Default system prompt degrades kimi-k2.5 performance on coding benchmarks #20258: Raises the same concerns about the default system prompt degrading coding performance — specifically calling out the same "minimize output tokens", "MUST answer concisely with fewer than 4 lines", and conflicting instructions that suppress planning and reasoning.

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new issue that follows our issue templates.