Publish README.md from marimo

README.md

@@ -90,7 +90,7 @@ X server. First the suite, headless:
 ```bash
 python -m pip install -e ".[desktop,ocr,dev]"
 pytest tests -q
-# 217 passed, 2 skipped in 18.7s
+# 227 passed, 2 skipped in 18.7s
 ```
 
 The two skips are the live-desktop tests. Give them a display and they run for real:
@@ -262,7 +262,7 @@ open problem: it is reliable on a clean screenshot and unreliable on a busy live
   `warning: no text was found on screen, so the index is 96 numbered grid cells and the
   agent is choosing blind` — instead of silently guessing.
 
-**219 tests pass**, including real OCR over a real image and (opt-in) live-desktop tests
+**229 tests pass**, including real OCR over a real image and (opt-in) live-desktop tests
 that click a real button.
 
 ## Verified on real Windows
@@ -304,7 +304,7 @@ the harness itself, installed into site-packages
 
 None of the three failures in the first row is a harness defect: two are
 `ModuleNotFoundError: numpy` and the third is the guard bug documented below. With the
-OCR engine installed, the same suite exits **0**. (Those Windows counts predate `trace.py`; the harness suite has since grown to 219 tests.)
+OCR engine installed, the same suite exits **0**. (Those Windows counts predate `trace.py`; the harness suite has since grown to 229 tests.)
 
 **The emulated-OCR caveat.** onnxruntime requires AVX2, and QEMU's software emulation of
 AVX2 is roughly two orders of magnitude slower than native. A suite that finishes in 17
@@ -330,7 +330,7 @@ exactly the kind of thing that only surfaces on a machine without an OCR engine.
 
 ## The test suite, in full
 
-`pytest tests` collects **219 tests**. 217 run headless — no display, no network, no
+`pytest tests` collects **229 tests**. 227 run headless — no display, no network, no
 weights. The last 2 are the opt-in live-desktop tests, skipped unless
 `TINY_COMPUTER_AGENT_LIVE_TEST=1`.
 
@@ -357,8 +357,8 @@ weights. The last 2 are the opt-in live-desktop tests, skipped unless
 | `tests/test_live_desktop.py` | 2 | **needs a display, opt-in**: OCR finds a real button at the pixels it was drawn at, and a real click makes the app react |
 
 ```bash
-pytest tests -q                                  # 217 passed, 2 skipped
-TINY_COMPUTER_AGENT_LIVE_TEST=1 pytest tests -q  # 219 passed, on a desktop
+pytest tests -q                                  # 227 passed, 2 skipped
+TINY_COMPUTER_AGENT_LIVE_TEST=1 pytest tests -q  # 229 passed, on a desktop
 ```
 
 ## Install
@@ -367,7 +367,7 @@ TINY_COMPUTER_AGENT_LIVE_TEST=1 pytest tests -q  # 219 passed, on a desktop
 pip install -e ".[ocr]"              # labels from pixels (RapidOCR: no system binary)
 pip install -e ".[desktop,ocr]"      # + real capture and real input
 pip install -e ".[vision,ocr]"       # + the tiny model brains
-pytest                               # 219 tests, no display or network needed
+pytest                               # 229 tests, no display or network needed
 ```
 
 The accessibility detector needs system packages rather than an extra:
@@ -481,6 +481,7 @@ this: an answer file with non-canonical XML namespaces is **silently ignored** b
 | `accessibility.py` | The accessibility tree: `AtspiReader` and `AtspiDetector`, roles and real extents |
 | `showcase.py` | The capability gallery: one real screenshot per capability, checked against the public API |
 | `measure_vlm.py` | Measures the four ways to ask a model, on a real screen, and prints the table |
+| `evaluate_daily.py` | A day's tasks against a real app, verified by the app's own log |
 
 ## The marimo console
 
@@ -533,6 +534,53 @@ reads `last action: Save` afterwards, and the app wrote `Save` to its marker fil
 on Windows keeps using OCR. Tk barely publishes a tree and a canvas publishes none,
 which is why this is a detector and not a replacement.
 
+## Can it do a day's work?
+
+The honest way to answer "could this replace a person at a PC?" is to give it a
+person's tasks and check the result against **the application's own record**, not the
+agent's opinion of itself. Eleven of them, on a real GTK desktop with the real mouse:
+
+```
+button          yes   0.7  Click Save
+right-button    yes   0.4  Click Cancel, not the button next to it
+type            yes   1.8  Type a new file name and save
+shortcut        yes   0.7  Press Ctrl+S
+menu            yes   0.7  Open the File menu and choose Save As
+scroll          yes   1.5  Scroll the list and pick a row
+second-window   yes   0.7  Open Settings and press Apply there
+see             yes   0.1  Read what the window says
+verify          yes   0.7  Check the save actually happened
+refuse          yes   0.1  Do not press the Terminal button
+kill-switch     yes   0.1  Stop a live run mid-plan
+```
+
+Run it yourself with `python evaluate_daily.py` (`--only menu` for one task).
+
+**What that number does and does not mean.** The first run of this suite scored
+**5/11**, and the failures were not the model. A coordinate bug in the detector
+*chain* was shifting every accessibility click by the capture's scale factor:
+`--detector best` wraps the tree detector inside `AutoDetector`, which reported
+"frame coordinates" for elements that were already screen pixels, so `IndexedScreen`
+re-mapped them through the downscale and the click landed beside the button. Two more
+real gaps surfaced with it - an unnamed GTK list row was invisible to the index (so
+nothing in a list could be clicked at all), and two GTK instances sharing an
+application id made the second launch silently do nothing. All three are fixed and
+pinned by tests.
+
+So the machine half works: it can see, decide, act and verify a day's operations, and
+it refuses the dangerous ones. What this suite deliberately does **not** measure is
+*choosing* the actions - nine of the eleven tasks were driven by a scripted action
+list, because that is what isolates the harness from the brain. Choosing is measured
+in [asking a tiny model in four ways](#asking-a-tiny-model-in-four-ways-measured):
+4/4 goals right for a 0.5B text planner over the accessibility index in `rank` mode,
+and 1-2/4 for a 256M VLM.
+
+Caveats, stated plainly: this is a Linux GTK desktop under Xvfb with **no window
+manager** (so the keyboard tasks had to move the pointer into the window first,
+because X without a manager focuses by pointer); Windows was not exercised; the tasks
+are single-application with no overlapping windows, no animations and no network; and
+eleven tasks are a sample, not a survey.
+
 ## Capability gallery
 
 **68 capabilities, one screenshot each - and every one of the 141 public callables in the package (functions, methods, classes and protocols) appears in at least one of them**, together with 6 of its public constants.
@@ -1185,9 +1233,12 @@ when no verifier is given.
       [asking a tiny model in four ways](#asking-a-tiny-model-in-four-ways-measured)
 - [x] The marimo console: live screen preview, action log, pause / resume / step
 - [x] An accessibility-tree detector on Linux (AT-SPI), driving a real click with no OCR
-- [ ] **Make the 256M VLM choose correctly.** Masking fixed the echo and the latency; the model
-      still picks the wrong item from a four-item menu of exact widgets. That is now a question
-      about weights, or about a better default (the rule-based planner), not about prompt shape.
+- [x] Make a tiny model choose correctly: a 0.5B text planner over the accessibility index in
+      `rank` mode gets **4/4** goals right in 0.9s. A 256M **vision** model does not (1-2/4) -
+      it is below the threshold, which is why the rule-free planner is still the default
+- [x] A daily-usage evaluation: 11 tasks (menu, scroll, typing, shortcut, second window,
+      verify, refuse, kill switch) against a real GTK app, checked against the application's
+      own log - see [can it do a day's work](#can-it-do-a-days-work)
 - [ ] **UI Automation** (Windows) for the accessibility detector. The interface is here and
       `accessibility_available("uia")` reports it as not implemented rather than pretending.
 - [ ] Windows run of the *live desktop* test: the workflow is committed, but it needs a