vava-nessa/free-coding-models v0.5.58

on GitHub

Added

• ⚡ Persistent probe-cache with TTL + auto-hide broken models (#144) — every health probe result is now cached to ~/.free-coding-models/probe-cache.json for 24 hours, shared across all surfaces (CLI TUI, Web Dashboard / daemon, Tauri Desktop).

  • Warm start in <500ms: the full ranking renders from the cache instantly, then only models that are due (broken or TTL-expired) get re-pinged. Cold start with no cache behaves identically to before — no regression.
  • Broken models stay hidden across sessions: a model that 401s today won't appear in tomorrow's default view. Recovery is automatic — if a previously-broken model comes back ok, the next probe un-hides it.
  • Honors XDG_CACHE_HOME when set (Linux/macOS convention), else falls back to ~/.free-coding-models/. File uses 0600 perms and is written atomically (tmp + rename) to survive crashes mid-flush.
  • Concurrency-safe: debounced flush + atomic rename + read-merge-write means a running daemon and an interactive CLI can share the file without clobbering each other. Worst case: one batch of deltas is lost, never the whole file.
  • probeVersion constant (currently 2): bump this when ping behaviour changes (new endpoint, new prompt, etc.) and the entire cache invalidates automatically — no manual purge.

• 🔘 Shift+B hotkey toggles visibility of probe-cache-broken models in the TUI. Footer chip shows ⚡ N cached · 🔴 M broken (Shift+B) (becomes 🔴 M broken (visible) when toggled on).

• 🛠️ New CLI flags:

  • --reprobe / --no-cache — force-rebuild the probe-cache this run (ping everything fresh).
  • --probe-ttl <ms> — override the 24h TTL (e.g. --probe-ttl 3600000 for 1h, useful when debugging model health).
  • --show-broken — don't auto-hide broken models this run (one-shot override for --reprobe style workflows).

• 📊 Daemon /stats now exposes probeCache with total, ok, broken, freshCount, staleCount, dueCount, hiddenCount, providers — the Web Dashboard renders it live so users can see cache hit rate at a glance.

Changed

• 🩺 Daemon health-probe loop (runProbeBurst) now skips models that are fresh + ok in the persistent cache. Broken models naturally pass through, so recovery detection keeps working unchanged. This cuts daemon-side probe traffic by ~85% on warm starts.

• 📁 Per-provider probe results are mirrored from the in-memory circuit-breaker windows into the persistent cache via recordProbeResult in src/core/router-daemon.js. Debounced 2s flush avoids filesystem thrash during probe bursts.

Maintenance

• 🧪 +40 unit tests (test/probe-cache.test.js, 36 → 76): covers freshness rules 1–5, path resolution (XDG_CACHE_HOME), corrupt-JSON recovery, version migration, multi-model fan-out, isCacheFresh per-condition checks, recordProbeResults validation + garbage dropping, getCacheStats aggregates, getCachedResultsForProvider filtering, pruneStaleEntries, end-to-end reload, 4 concurrency tests (other-process deltas survive, stale lastProbedAt is overwritten, missing-file path, corrupt-file recovery).
• 🧪 628 → 632 tests passing (pnpm test), 107 → 118 suites.
• 🧹 vite build succeeds.
• 📖 README updated with a new 🧠 Persistent probe cache section (where the file lives, CLI flags, TUI keys, daemon /stats shape).

Files

• New: src/core/probe-cache.js (335 lines), test/probe-cache.test.js (332 lines), changelog/v0.5.58.md.
• Modified: src/tui/app.js (probe-cache load + apply + record), src/tui/key-handler.js (Shift+B handler), src/tui/render-table.js (footer chip), src/tui/tui-state.js (5 new state fields), src/tui/cli-help.js (3 new flag entries), src/core/utils.js (parseArgs gains --reprobe / --probe-ttl / --show-broken), src/core/router-daemon.js (full integration: load on boot, mirror probe results, skip fresh in runProbeBurst, expose in /stats, flush on shutdown), README.md, tasks/t1.md, package.json (test script), changelog/.

Inspiration

This implementation is informed by apmantza/pi-free's lib/provider-probe.ts + lib/probe-cache.ts (which itself credits us: "Inspired by free-coding-models' extractQuotaPercent"). The inspiration flows both ways — we're reclaiming the lead on the probe-cache axis by going cross-surface (CLI / daemon / Tauri share one file) and concurrency-safe (read-merge-write vs pi-free's single-writer Pi-only model).