41 Commits
Author SHA1 Message Date
Kieran KlukasandGitHub 6f91b0ca22 fix(tools): switch bufio scanner for reader (#2884)
* fix(tools): switch bufio scanner for reader

* chore(tests): update golden files
2026-05-12 17:00:19 -04:00
Kieran KlukasandKieran Klukas 0485adc477 chore(tests): update golden files 2026-05-12 12:16:03 -04:00
Kieran KlukasandKieran Klukas 651abb48ae chore(golden): rerecord vhs 2026-05-12 10:54:58 -04:00
Greg SlepakandGitHub 2235a49d0d fix: limit view size checks to returned content (#2785) 2026-05-11 20:36:11 +00:00
Andrey Nering 5d8f924061 test: re-record test fixtures 2026-04-30 18:30:04 -03:00
Christian Rocha b9fdf72e87 chore(hooks,skills): update crush-hooks skill per recent changes 2026-04-26 18:37:52 -04:00
Christian RochaandGitHub dc003bf728 feat: PreToolUse hook (#2598) 2026-04-26 09:24:36 -04:00
Andrey Nering 8ab740f5bb test: re-record vcr cassettes 2026-04-24 17:09:53 -03:00
Andrey Nering 4d7c55e298 test: re-record vcr cassettes 2026-04-22 10:32:48 -03:00
Christian RochaandAndrey Nering e64db33eeb feat(prompt): require loading appropriate skills before acting
Models frequently skipped viewing a skill's SKILL.md and inferred its
behavior from the description alone; making the load mandatory in
<critical_rules> prevents LLMs from taking that shortcut.
2026-04-20 17:23:35 -03:00
Andrey Nering 8bab8b3f7b test: re-record vcr cassettes 2026-04-16 17:54:19 -03:00
Andrey Nering fa50f36dd1 test: re-record vcr cassettes 2026-04-16 17:41:30 -03:00
Andrey Nering 076cb1c42b test: re-record vcr cassettes 2026-04-16 16:40:25 -03:00
Andrey Nering c83a6d8ad2 test: re-record vcr cassettes 2026-04-15 10:32:55 -03:00
Christian RochaandAndrey Nering ff003b4615 chore(tests): re-record vcr cassettes
Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>
2026-04-11 09:54:56 -04:00
Andrey Nering ffff334d10 test: re-record vcr cassettes after system prompt change 2026-03-25 16:10:27 -03:00
f1bdb9c9b8 feat: add configurable auto-background threshold for bash tool (#2183)
Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>
2026-03-12 17:53:45 -03:00
Andrey Nering d3b4ab23fe test: re-record test fixtures 2026-03-12 14:12:00 -03:00
Christian RochaandGitHub c6e7e3904a chore(prompt): small edits (#1915) 2026-01-19 15:04:24 +01:00
88831a1b00 feat: todo tool
Co-authored-by: Christian Rocha <christian@rocha.is>
2025-12-12 18:16:13 +01:00
Kujtim HoxhaandGitHub bbd0887700 feat: support image results from tools (#1549) 2025-12-08 15:35:18 +01:00
Kujtim HoxhaandGitHub 5c96ab406c chore: improve prompt (#1502) 2025-12-04 16:31:07 +01:00
Andrey Nering e9048a81b0 test: record vcr cassettes 2025-11-13 14:40:40 -03:00
Andrey Nering b095afd649 chore: record all cassettes after fantasy update 2025-11-12 11:34:46 -03:00
Andrey Nering 5186beffcc test: record vcr cassettes for #1379 2025-11-12 10:59:35 -03:00
4401d5b37f feat: background jobs & remove persistent shell (#1328)
Co-authored-by: Christian Rocha <christian@rocha.is>
Co-authored-by: Raphael Amorim <rapha850@gmail.com>
Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>
2025-11-07 13:11:14 +01:00
51a2144e77 feat: agentic fetch tool (#1315)
Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>
2025-11-05 16:32:27 +01:00
Kujtim HoxhaandGitHub df4d66b410 feat: keep successful edits even if some fail (#1327) 2025-10-31 11:04:36 +00:00
Andrey Nering d32831ebad fix(test): normalize output of download tool to make tests pass on windows 2025-10-28 17:55:46 -03:00
Andrey Nering 6b206a870d test: re-record vcr cassettes 2025-10-28 17:55:46 -03:00
Kujtim Hoxha 139749a72e fix(tests): remove embedded providers, regenerate fixtures 2025-10-27 13:53:52 +01:00
kujtimiihoxha 95e7d7fb90 chore: small system prompt improvemets & fantasy 2025-10-23 19:34:37 +02:00
Andrey Nering 8445bf5bd3 test: re-record 2 tests to make suite green 2025-10-23 14:13:23 -03:00
kujtimiihoxha 7daf3b21ab fix(tests): regenerate tests and skip some 2025-10-23 16:22:35 +02:00
kujtimiihoxha ac97adcf71 fix(tests): regenerate tests 2025-10-13 06:37:32 +02:00
kujtimiihoxha 9c04ddaa4d chore: fix tool calls 2025-10-02 14:47:09 +02:00
Kujtim Hoxha c58a4d43c0 chore: merge master 2025-10-02 06:14:32 +02:00
Kujtim Hoxha 12b9f87f37 fix(test): make prompt deterministic 2025-10-01 18:51:15 +02:00
Kujtim Hoxha 8fce31ead1 test: test all the tool calls 2025-10-01 18:51:15 +02:00
Kujtim Hoxha 1f0fb3d5a9 test: add more tests and make it easy to add tests for multiple models 2025-10-01 18:51:15 +02:00
kujtimiihoxha 4a54d63669 test: add coder agent 2025-10-01 18:51:15 +02:00