What does this PR do?

Prevents automatic context compression from discarding conversation turns when summary generation fails.

Previously, if the summary LLM/provider failed, ContextCompressor.compress() inserted a static "summary unavailable" marker and still dropped the middle turns. That is risky for long-running sessions because the visible transcript can remain available while the model-facing context loses recent work and keeps an old protected head.

This changes failed-summary compression to fail closed: record warning state for callers, but return the original messages unchanged.

Related Issue

Fixes #25585

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 🔒 Security fix
• 📝 Documentation update
• ✅ Tests (adding or improving test coverage)
• ♻️ Refactor (no behavior change)
• 🎯 New skill (bundled or hub)

Changes Made

• agent/context_compressor.py
  • Return the original message list when _generate_summary() returns no summary.
  • Keep _last_summary_fallback_used, _last_summary_dropped_count, and _last_summary_error available so callers can surface warnings.
  • Do not increment compression_count for failed compression.
  • Update no-provider warning text so it no longer claims middle turns will be dropped.
• tests/agent/test_context_compressor.py
  • Replace the old static-fallback truncation expectation with a regression test that failed summaries preserve the original messages.
  • Keep successful-summary compression coverage explicit by mocking call_llm where tests expect compression.
• tests/agent/test_context_compressor_summary_continuity.py
  • Keep continuity tests exercising the actual summary window instead of sitting on the minimum-message boundary.

How to Test

1. scripts/run_tests.sh tests/agent/test_context_compressor.py tests/agent/test_context_compressor_summary_continuity.py tests/agent/test_compress_focus.py tests/gateway/test_compress_command.py tests/gateway/test_compress_focus.py tests/run_agent/test_compressor_fallback_update.py tests/run_agent/test_compression_persistence.py
2. python3 - <<'PY'\nimport py_compile\npy_compile.compile('agent/context_compressor.py', doraise=True)\nprint('py_compile ok')\nPY
3. git diff --check

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform: macOS, Python 3.11.15

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A

For New Skills

N/A

Screenshots / Logs

Focused test run:

100 passed in 6.59s

git diff --check completed with no output.