README: clean tag block (fix best-agent typo, drop the 3 non-Field-Guide tags into a descriptive group) + add Output examples (real Modal-run outputs)
Tags: official tracks/sponsors/badges + descriptive build tags. Adds an 'Output examples' <details> with real single-turn GGUF outputs generated ON Modal (backs the best-use-of-modal claim).
- point refs to final public homes + drop placeholder (e093f6402a31d17704ca748b6df0e490b15c19db)
- README: add GitHub code repo link (Katehuuh/MiniCPM5-1B-Agent) for the OpenAI Codex track (e8ca94b48ee7b24ba07a0c9e82b6a690d448a5be)
fix double-box user bubble: Gradio nests .message.user > [data-testid=user]; my selector styled BOTH -> two stacked boxes. Now the OUTER is the single bubble, the INNER is flattened (transparent/no box). Verified via live CSS injection.
fix chart blank: 1B was WRITING chart.png as TEXT (623-byte bogus png -> 0x0 render). write tool now REFUSES image-ext text-writes + steers to matplotlib savefig; _render_media_file skips files without a real image magic-number (no blank bubble).
fix REGRESSION: prompt hardening ('write then final answer is one sentence') made the 1B SKIP the bash run + hallucinate 'saved chart.png' without running -> no image. Restore: after writing a runnable script you MUST run it with bash + read output before answering; never claim you ran code you did not.
fix chart/media not displaying: the 1B savefig's to an absolute /workspace/ path inside the script (bash rewrite can't reach in-code paths), so the PNG landed outside the scanned sandbox. Now: ensure /workspace exists at startup + _extra_media scans it this-turn-only (no cross-session leak; concurrency_limit=1). Refactored shared _render_media_file.
