live: heartbeat sync 2026-10-27T18:58:49-07:00 (Refs #11)

2026-10-27 18:58:49 -07:00
1 parent 702847cefd
commit 9df5c50fda
@@ -85,7 +85,7 @@ compaction:
    - handoff
    - remote
  idleThresholdTokens: 100000
-  thresholdPercent: 95
+  thresholdPercent: 85
  idleEnabled: true
  thresholdTokens: -1
  dropUseless: false
@@ -96,7 +96,7 @@ compaction:
  experimentalContextManagement: false
 interruptMode: immediate
 defaultThinkingLevel: xhigh
-hideThinkingBlock: false
+hideThinkingBlock: true
 proseOnlyThinking: false
 terminal:
  showProgress: true
@@ -0,0 +1,32 @@
+---
+name: snapcompact-reader-recall-probe
+description: Measure bitmap-frame OCR recall and true per-frame token billing of a custom vision endpoint to pick snapcompact shape and price it correctly.
+---
+
+# Snapcompact reader recall probe
+
+Decide snapcompact settings for a non-frontier (custom/local) vision model: which frame shape its tower actually reads, and what the endpoint really bills per frame (vs the harness's blind `FRAME_TOKEN_ESTIMATE`=5024 floor).
+
+## Fact sources (in trust order)
+1. `omp://compaction.md` (Snapcompact method section) + `cfg://snapcompact` + `cfg://compaction` — mechanism + resolved values/defaults.
+2. Upstream ground truth: `raw.githubusercontent.com/can1357/oh-my-pi/main/packages/snapcompact/CHANGELOG.md` — per-model eval winners and the `toolbench` re-tune (spacing-tuned cells beat dense; ~16px/char OCR floor). `research/` dir has the eval scripts.
+3. Live bundle truth: grep minified `dist/cli.js` (`~/.bun/install/global/node_modules/@oh-my-pi/pi-coding-agent/dist/`) for string literals: `grep -o '\[\[/[^;]\{0,400\}' cli.js` shows the ideal-shape regex table (`claude→11on16-bw, gemini→8on22-bw@2048, gpt|codex→8on22-bw, kimi→8on22-bw, glm→8on16-bw`); `unknown:"8on22-bw"` is the openai-compat wire fallback. Unmeasured ids (no qwen matcher) get the wire-family shape.
+4. Reachability of pricing knobs (proved 2026-10-27 on 18.12.5): the user-row merge chain (`grep -o '.\{80\}t\.imageCountBudget.\{200\}' cli.js`) forwards `imageCountBudget` ONLY — `imageTokenization` resolves through the compiled catalog identity (no user-row key reaches it, so custom endpoints can never mark frames `verified` and always eat the 5024 floor in sizing). Regimes: `openai-patch | anthropic-patch | deepseek-patch | fixed` (`"fixed":return e.tokens`) — catalog-side only.
+
+## Probe recipe
+Scratch dir: `bun init -y && bun add @oh-my-pi/snapcompact` (ships TS source; native renderer via pi-natives). npm version may drift a patch ahead of the harness bundle — geometry caveat, note it.
+
+`probe.ts` legs against the endpoint's `/v1/chat/completions`:
+- Build ~120k-char tool-traffic transcript in snapcompact scope format (`¶user:`, `¶call:` + `<out>…</out>`, `¶ai:`) with N planted unique spelled-out facts (spell digits as words so filler can't collide; keep filler digit-free); score recall by `content.includes(value)`.
+- Legs: plain-text baseline, then images per candidate shape via `resolveShape({api, id}, variant)` + `renderMany(text, {shape})`; send as `{type:"image_url", image_url:{url:"data:<mime>;base64,<data>", detail:"original"}}` with a reading-guide text part.
+- Replicate the harness's real request shape: same `chat_template_kwargs` (enable_thinking/preserve_thinking) and sampling from the models.yml row.
+- True per-frame billing = `(prompt_tokens − text-scaffold) / frames`, compare vs `plannedFrameTokens(shape)`/`frameBilling`.
+
+Then: declare `imageCountBudget: <proven count>` on the models.yml row (custom providers inherit the unknown-provider floor of 5 images/request; llama.cpp has no such limit) — that lifts the count clamp; token pricing stays floor-bound until upstream prices the wire family. Measured baseline (frank-archon, omp 18.12.5): auto `8on22-bw` 8/8 recall at 47 % of text's billed tokens, ~2,370 tok/frame true vs 5,024 charged; dense grids (8on16/11on16) drop characters — keep `shape: auto`.
+
+## Gotchas
+- `log()` is an eval-kernel global, NOT a bun global — define a console wrapper or the script dies at first call.
+- bash `async` + `name` = service mode (rejects async); drop `name` for finite jobs; `timeout: 0` disables the 600s deadline for multi-leg vision runs.
+- edit tool needs the absolute path (not bare filename) for /tmp files; `PUT <N` inserts BEFORE line N.
+- Vision gate: row must declare `input: [text, image]` or snapcompact is skipped silently.
+- Fleet follow-ups live in `omp-docs/core/snapcompact.md` (dank/command-center).
@@ -1,6 +1,6 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1792646195391,
+	"lastConsolidatedAt": 1793150228978,
 	"lastResult": {
 		"at": 1791599865775,
 		"sessions": 1,
@@ -1,4 +1,4 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1792627210418
+	"lastConsolidatedAt": 1793151249086
 }
@@ -1,4 +1,4 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1793148876450
+	"lastConsolidatedAt": 1793152476466
 }
@@ -0,0 +1,4 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1793152689890
+}
@@ -47,6 +47,18 @@ providers:
        # (arch/common/rad_block_vit.h). Video preprocessing configs ship
        # too; images are the contract that matters here.
        input: [text, image]
+        # Catalog image-count rules never match custom providers, so the
+        # unknown-provider floor (5 images/request) would silently cap the
+        # snapcompact archive at ~5 frames per rebuild. Radiance has no
+        # image-count limit and accepted 14 frames in one measured probe
+        # (2026-10-27, recall 8/8); the real clamp stays the archive sizing
+        # law (frames get half the room under the compaction threshold).
+        # NOTE: per-frame token pricing (imageTokenization) is catalog-only
+        # — no user-row key exists — so frames keep being charged the
+        # 5,024-token floor estimate against a measured ~2,400. Archive
+        # capacity is count-bound until upstream prices openai-completions
+        # vision honestly.
+        imageCountBudget: 16
        compat:
          # radiance's --reasoning-format defaults to auto: thinking
          # comes back in `reasoning_content` (config.cpp). No parser