can1357/oh-my-pi v16.3.11 on GitHub

@oh-my-pi/pi-ai

Fixed openai-codex-responses fresh plan execution requests that contained only system/developer guidance by mirroring the final instruction as user input so Codex accepts the first turn. (#4714)
Fixed Codex WebSocket compact/resume delta diagnostics to record request shape and raw-vs-displayed usage buckets, so persistent server-reported uncached suffixes without orchestration_* fields are visible in debug stats. (#4707)

Improved session title generation reliability by moving to marker-based parsing for all models

Fixed session titles occasionally showing raw {"title": "..."} JSON. Online title generation now always uses the <title>...</title> marker prompt instead of a forced set_title tool call — hosts that ignored or rejected forced tool_choice echoed the prompt's JSON example verbatim as the title — and JSON-shaped responses (bare, code-fenced, marker-wrapped, or truncated) are unwrapped to the bare title.
Fixed Linux startup prompt construction to read the CPU model from /proc/cpuinfo instead of os.cpus(), avoiding per-core sysfs frequency probes on many-core hosts (#4712).
Fixed llama.cpp model discovery to honor per-model architecture.input_modalities from /v1/models, so router presets that advertise image input are no longer treated as text-only (#4719).

fix(tool): include ignored files for empty grep glob discovery by @roboomp in #4710
fix(ai): record Codex compact usage diagnostics by @roboomp in #4713
fix(cli): avoid os.cpus during startup prompt by @roboomp in #4717
fix(ai): mirror Codex instruction-only plan input by @roboomp in #4718
fix(coding-agent): detect llama.cpp per-model vision metadata by @roboomp in #4721

Full Changelog: v16.3.10...v16.3.11