Add pruning fallback and character truncation for large context

[continue]

Summary

This PR addresses CON-4274 by adding two improvements to handle large context in the CLI:

1. Pruning fallback: When context length validation fails before sending chat messages, we now use the existing compileChatMessages pruning logic from core/llm/countTokens.js as a fallback. This removes older messages while preserving the system message, tools, and the most recent user/tool sequence.

2. Bash tool output truncation: The Bash tool now truncates output by both:

   • Lines: 5000 lines (existing)
   • Characters: 200,000 characters (new)

   Whichever limit is hit first will trigger truncation with an appropriate message.

Changes

• extensions/cli/src/stream/streamChatResponse.ts: Added pruning fallback in processStreamingResponse when context validation fails
• extensions/cli/src/tools/runTerminalCommand.ts: Added character-based truncation to Bash tool output

Testing

• The pruning logic reuses the well-tested compileChatMessages function from core
• Character truncation follows the same pattern as the existing line truncation

Fixes CON-4274

---

This agent session was co-authored by nate and Continue.

---

Summary by cubic

Prevents oversized contexts from breaking CLI requests by pruning chat history and truncating Bash tool output. Fixes CON-4274 and improves reliability with large conversations and long command results.

• New Features
  • Prunes chat history when context-length validation fails using compileChatMessages; preserves system, tools, and the latest exchange.
  • Truncates Bash tool output to 5000 lines or 200,000 characters (whichever comes first) and adds a clear truncation notice.

[chezsmithy]

I'd recommend a different truncation strategy for the bash output. Perhaps keep the last X lines from the end backwards to capture the outcome of tests and installs.

[github-actions]

⚠️ PR Title Format

Your PR title doesn't follow the conventional commit format, but this won't block your PR from being merged. We recommend using this format for better project organization.

Expected Format:

<type>[optional scope]: <description>

Examples:

• feat: add changelog generation support
• fix: resolve login redirect issue
• docs: update README with new instructions
• chore: update dependencies

Valid Types:

feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert

This helps with:

• 📝 Automatic changelog generation
• 🚀 Automated semantic versioning
• 📊 Better project history tracking

This is a non-blocking warning - your PR can still be merged without fixing this.

[cubic-dev-ai]

No issues found across 2 files

[RomneyDa]

compile chat messages already supports unified history, no need to convert between the two. CLI should just always use compile chat messages, no need for a duplicate token counting validation step.

[RomneyDa]

@continue also implement @chezsmithy's truncation recommendation