24 Commits

Author SHA1 Message Date
Michał Pierzchała 819d7dc8aa feat: expose structured MCP command tools (#593)
* feat: expose semantic MCP tools

* docs: remove semantic mcp prd

* refactor: deepen semantic command surface

* refactor: add mcp execution seam

* refactor: deepen command grammar

* refactor: remove legacy command definitions

* refactor: collapse semantic cli wrappers

* refactor: remove local mcp placeholders

* refactor: derive semantic cli routing

* refactor: trim mcp status metadata

* refactor: derive semantic input contracts

* refactor: split semantic grammar modules

* refactor: derive batch input schema

* refactor: centralize cli command schema catalog

* refactor: share semantic cli output projections

* refactor: remove legacy cli output paths

* refactor: consolidate command interface surface

* docs: align command contract wording

* refactor: split command projection from cli grammar

* refactor: trim projection exports

* fix: satisfy fallow command contract audit

* refactor: structure public batch steps

* chore: clean batch architecture references

* fix: keep legacy cli batch steps working

* fix: serialize mcp batches

* chore: tighten command surface cleanup

* fix: serialize mcp stdin requests

* chore: keep mcp config out of command contracts

* fix: project structured batch targets

* chore: harden command input typing

* fix: project maestro backend for replay tests

* fix: preserve session mcp request options
2026-05-28 09:20:55 +02:00
Michał Pierzchała a5fffc6e49 feat: add Maestro YAML replay compatibility (#581)
* feat: add Maestro replay compatibility

* fix: harden Maestro replay compatibility

* fix: address Maestro replay review feedback

* fix: finalize Maestro replay compatibility

* refactor: tighten Maestro replay compatibility boundary

* refactor: reduce Maestro replay quality debt

* refactor: satisfy Maestro replay fallow audit

* fix: stabilize Android provider snapshot tests
2026-05-27 21:45:51 +02:00
Michał Pierzchała bbe7c06fb6 feat: auto-reverse Android localhost opens (#590)
* feat: auto-reverse Android localhost opens

* test: cover Android localhost reverse edge cases

* fix: reduce Android reverse error complexity

* docs: simplify Android Metro reverse guidance

* docs: prefer scripted SkillGym checks

* test: clarify Android Metro SkillGym plan
2026-05-26 10:44:51 +02:00
Michał Pierzchała ea21793154 feat: support ios transform gesture (#586) 2026-05-26 09:58:33 +02:00
Michał Pierzchała c72cf0e1d2 fix: clarify Android gesture transform behavior (#584)
* fix: clarify Android gesture transform behavior

* fix: stabilize Android transform injection
2026-05-26 09:47:07 +02:00
Michał Pierzchała 47b981c8ad feat: add gesture command coverage (#576)
* feat: add gesture command coverage

* fix: align iOS fling provider fixture

* feat: group gesture commands

* fix: clarify android gesture support

* feat: add android multitouch gestures

* fix: address gesture review feedback

* refactor: simplify gesture plumbing

* fix: keep gesture subcommands internal

* fix: update iOS provider pan transcript
2026-05-22 18:01:58 +02:00
Michał Pierzchała 168de53bee fix: improve Android snapshot fidelity (#580)
* fix: improve Android snapshot fidelity

* fix: address Android snapshot review edge cases

* refactor: simplify Android snapshot cleanup helpers

* test: guard SkillGym external runners in sandbox
2026-05-22 15:14:50 +02:00
Michał Pierzchała 67aa89af58 feat: add iOS repro evidence capabilities (#573) 2026-05-21 13:39:52 +02:00
Michał Pierzchała b0e19c9d1e perf: improve recording and interaction flows (#563)
* perf: improve recording and interaction flows

* feat: add React Native overlay dismiss command

* test: cover RedBox overlay dismissal

* fix: simplify React Native overlay snapshot hint

* fix: address daemon and scroll review feedback

* fix: unblock ci after recording polish

* chore: refresh fallow health baseline

* test: stabilize android provider suites

* test: cover rn overlay provider command
2026-05-20 20:32:08 +02:00
Michał Pierzchała f71371ebb8 fix: handle platform alerts (#562)
* fix: handle Android platform alerts

* fix: handle iOS alerts in runner

* chore: type alert metadata

* refactor: colocate Android alert handling
2026-05-20 14:51:17 +02:00
Michał Pierzchała 896adcc625 feat: add maestro replay compatibility (#561) 2026-05-19 20:49:34 +02:00
Michał Pierzchała b5cd1c49fe fix: handle busy Android RN snapshots (#554) 2026-05-16 16:55:18 +02:00
Michał Pierzchała 8f722c3c5f docs: guide bounded react devtools profiling (#548) 2026-05-15 18:56:05 +02:00
Michał Pierzchała c1550721ce fix: collapse Android snapshot row noise (#545)
* fix: collapse Android snapshot row noise

* docs: clarify agent-facing snapshot text

* fix: preserve semantics when collapsing Android snapshots

* fix: trim redundant Android collapse hints

* fix: collapse passive Android duplicate children

* refactor: drop unused Android snapshot hint code

* docs: clarify Android Metro verification guidance

* test: cover Android Metro reverse planning

* test: fix codex skillgym runner

* fix: satisfy fallow snapshot checks

* docs: clarify PR validation guidance
2026-05-15 18:52:11 +02:00
Michał Pierzchała 801c2ae0b3 fix: improve rn agent-device stability guidance (#519) 2026-05-14 17:30:45 +02:00
Michał Pierzchała 517b5198b4 docs: clarify agent-device binary resolution (#511) 2026-05-13 14:52:46 +02:00
Michał Pierzchała 5df37ec9c9 fix: improve android fill verification diagnostics (#495) 2026-05-11 20:06:59 +02:00
Michał Pierzchała 076f0c0788 chore: upgrade skillgym to 0.8.0 (#493) 2026-05-11 17:09:47 +02:00
Michał Pierzchała 7ea8d9eea3 feat: discover cloud config during connect (#488)
* feat: discover cloud config during connect

* test: isolate cloud connect profile coverage

* docs: document cloud connect discovery

* fix: honor no-login after cloud auth reuse

* fix: validate cloud connection profiles

* refactor: require object cloud profiles

* refactor: trim cloud connect compatibility code
2026-04-30 16:16:56 -04:00
Michał Pierzchała f7c8f451ed build: upgrade skillgym to 0.6.0 (#473)
* build: upgrade skillgym to 0.6.0

* test: raise skillgym parallel cap

* test: use skillgym command assertions

* test: use structured skillgym command matchers

* test: rely on skillgym default parallel cap

* test: accept bare planned commands

* test: run skillgym cases in parallel
2026-04-29 14:38:01 -04:00
Michał Pierzchała bbb1d363c2 fix: handle iOS keyboard Done dismiss controls (#469) 2026-04-28 21:20:09 -04:00
Michał Pierzchała 6c368bf792 docs: update agent-device guidance (#467) 2026-04-28 17:07:33 -04:00
Michał Pierzchała 140fe338c2 docs: replace bulky skills with versioned CLI help (#352)
* docs: move agent guidance into help workflows

* test: address skill help review feedback

* docs: surface agent workflow in top-level help

* docs: strengthen dogfood help workflow

* docs: improve react devtools performance routing

* test: thin skillgym prompt

* docs: gate skills on help topic version

* test: stabilize thin help skillgym

* docs: restore dogfood QA guidance

* test: cover truncated text scoped snapshots

* docs: clarify remote help wording

* test: cover rn overlays and expo launch guidance

* test: cover expo launch after app lookup miss

* test: refine rn warning overlay workflow

* docs: restore react devtools advanced guidance

* test: cover restored agent guidance gaps

* test: cover device workflow edge cases

* docs: clarify agent-device install guidance

* docs: route known limitations through help

* docs: clarify bootstrap help for small models

* docs: tighten debug workflow guidance

* docs: remove local test note from workflow help
2026-04-28 14:14:55 -04:00
Michał Pierzchała 7c5b7670c8 feat: add skillgym tests (#453) 2026-04-26 20:49:59 -04:00