Commit Graph

4820 Commits

Author SHA1 Message Date
Vegard Stikbakke 6757561546 fix(coding-agent): abort stuck context hooks
closes #6234
2026-07-02 10:02:32 +02:00
github-actions[bot] 9f91da2145 chore: approve contributor xz-dev 2026-07-02 08:01:30 +00:00
Vegard Stikbakke ec857fece5 fix(coding-agent): set executionMode: sequential on question example tool
The question extension tool blocks on ctx.ui.custom() but omitted
executionMode, so multiple question calls in one assistant turn ran
under the default parallel mode and raced on the editor slot. Only the
last question rendered; earlier calls hung pending forever.

Set executionMode: "sequential" so the agent loop serializes the
batch. Wrappers already propagate the field to the core.

closes #6189
2026-07-02 09:01:15 +02:00
github-actions[bot] 45c0fe7833 chore: approve contributor cyzlmh 2026-07-02 06:35:24 +00:00
Vegard Stikbakke e285e90fdb fix(ai): remove Copilot Sonnet 5 fallback in generate-models 2026-07-01 23:01:33 +02:00
Vegard Stikbakke f8bec25f34 fix(coding-agent): surface auth storage save failures
closes #6223
2026-07-01 21:24:26 +02:00
Vegard Stikbakke f58c115626 fix(coding-agent): serialize split-turn compaction summaries
closes #5536
2026-07-01 15:37:00 +02:00
Vegard Stikbakke e2ccdc8509 fix(ai): delay Copilot device-code token polling
closes #6187
2026-07-01 13:48:11 +02:00
Mario Zechner ba10b60b51 fix(coding-agent): add entry renderers for session entries 2026-07-01 11:30:26 +02:00
Vegard Stikbakke 8c9436407c fix(ai): remove stale model metadata fallbacks 2026-07-01 10:53:09 +02:00
Vegard Stikbakke 1da1cdb2fb chore(ai): regenerate models
Picked up upstream models.dev/OpenCode catalog drift while
regenerating for the Fireworks GLM 5.2 Fast fix: Cloudflare AI Gateway
and OpenCode gain Claude Sonnet 5; OpenCode gains Kimi K2.7 Code and
MiniMax-M3; MiniMax model name formatting normalized to MiniMax-Mx.x.
2026-07-01 10:35:38 +02:00
Vegard Stikbakke 844d175eaf fix(ai): align Fireworks GLM 5.2 Fast with GLM 5.2
Broaden the Fireworks GLM 5.2 special-case in generate-models.ts from
an exact id match to a glm-5p2 substring match, so the router variant
accounts/fireworks/routers/glm-5p2-fast also uses the OpenAI-compatible
endpoint and thinkingLevelMap instead of falling back to the default
Anthropic Messages config.

closes #6195
2026-07-01 10:34:46 +02:00
Vegard Stikbakke 040f0a5197 feat(coding-agent): expose model resolution helpers
closes #6201
2026-07-01 10:22:35 +02:00
Vegard Stikbakke 1d061b3f45 fix(ai): remove stale model metadata fallbacks 2026-07-01 10:03:26 +02:00
Vegard Stikbakke 4206376410 feat(ai): add Copilot Claude Sonnet 5
closes #6200
2026-07-01 09:57:04 +02:00
Vegard Stikbakke 85b7c24741 fix(coding-agent): reject non-positive bash timeouts 2026-07-01 09:03:00 +02:00
Vegard Stikbakke cbcf4e04c3 fix(coding-agent): reject oversized bash timeouts
closes #6181
2026-07-01 08:49:31 +02:00
Vegard Stikbakke 0ac3cfe09b feat(ai): use zstd compression for codex sse transport 2026-07-01 08:42:46 +02:00
Vegard Stikbakke a3cc169d97 fix(ai): avoid codex user-agent race
The Codex provider previously loaded node:os asynchronously during module evaluation. A fresh process that imports the provider and immediately starts an SSE request can build headers before that promise callback runs, so the first request reports User-Agent: pi (browser) in Node/Bun.

Reproduced against parent fd6659dd with a stubbed-fetch harness: 50/50 immediate first requests reported pi (browser) in both Node and Bun. The same harness on this fix reports the OS-specific user agent 50/50 in both runtimes.

Use process.getBuiltinModule("node:os") behind the existing Node/Bun runtime guard so OS metadata is available synchronously while still avoiding top-level runtime Node builtin imports that break browser/Vite builds.
2026-07-01 08:41:38 +02:00
Mario Zechner dd87c02cbf Add [Unreleased] section for next cycle 2026-06-30 22:29:44 +02:00
Mario Zechner a23abe4a69 Release v0.80.3 2026-06-30 22:29:41 +02:00
Mario Zechner f98a154d87 docs: audit changelog entries 2026-06-30 22:24:42 +02:00
Mario Zechner 5c1a2977bc fix(ai): update generated model catalogue 2026-06-30 22:12:48 +02:00
Mario Zechner fd6659dd5d fix(coding-agent): preserve run prompt during tool refresh
closes #6162
2026-06-30 14:08:48 +02:00
Mat e547bb9f41 fix(coding-agent): refresh session state before next turn 2026-06-30 13:56:04 +02:00
Mario Zechner 9be55bc773 fix(coding-agent): apply output padding to user messages
closes #6168
2026-06-30 11:55:40 +02:00
Alexey Zaytsev 6564d94717 feat(coding-agent): add configurable assistant output padding
Closes #6168
2026-06-30 11:44:34 +02:00
Mario Zechner 2117b61c6b fix(coding-agent): handle undici mid-stream client errors
closes #6133
2026-06-30 11:44:14 +02:00
Mario Zechner 939c39ab84 Merge pull request #6175 from xl0/session-info-changed
fix(coding-agent): emit session name changes to extensions
2026-06-30 11:35:20 +02:00
Vegard Stikbakke 3d6acb37b9 fix(ai): regenerate model catalog
Includes updated Xiaomi MiMo pricing from models.dev. Closes #6138
2026-06-30 08:33:18 +02:00
Alexey Zaytsev 726a9c526c fix(coding-agent): emit session name changes to extensions 2026-06-30 00:40:15 -05:00
Mario Zechner 927e98068c fix(coding-agent): fix compaction event regression test 2026-06-29 17:12:19 +02:00
Mario Zechner 6fbeba51af Merge pull request #5832 from stephanmck/fix/provider-error-body-passthrough-5763
fix(ai): surface provider HTTP error body instead of opaque SDK message
2026-06-29 16:58:24 +02:00
Mario Zechner 5d499272a8 fix(coding-agent): stabilize interactive status indicators
Closes #6026
2026-06-29 16:53:39 +02:00
github-actions[bot] 541d11f725 chore: approve contributor skhoroshavin 2026-06-29 06:41:07 +00:00
Vegard Stikbakke b91bdd5a3e fix(ai): preserve Z.AI thinking content
closes #6083
2026-06-29 08:40:20 +02:00
Armin Ronacher 54113731b2 fix(ai): use HTTP timeout for Codex SSE headers
Refs #4945
2026-06-28 19:57:47 +02:00
Armin Ronacher 8f64353e65 fix: restrict bot gate bypasses
Refs #6127
2026-06-28 18:59:34 +02:00
Mario Zechner a8c692c712 Merge pull request #6074 from yzhg1983/private/pre-prompt-compaction-no-continue
fix(coding-agent): avoid pre-prompt compaction continue
2026-06-28 17:49:12 +02:00
Mario Zechner 234c2ad54c Merge pull request #6078 from geraschenko/rpc-get-entries-tree
feat(coding-agent): add get_entries and get_tree RPC commands
2026-06-28 17:46:26 +02:00
Armin Ronacher 5a073885b5 feat(coding-agent): add external editor setting
Closes #6122
2026-06-27 23:57:46 +02:00
Armin Ronacher f2e9d75388 fix(coding-agent): preserve backslash escapes in user messages
closes #6105
2026-06-27 19:24:14 +02:00
Armin Ronacher 622eca7608 feat(coding-agent): add installer lock generation 2026-06-26 14:45:15 +02:00
Cristina Poncela Cubeiro 87ad8243cb feat(experimental): pi orchestrator 2026-06-26 13:46:22 +02:00
Cristina Poncela Cubeiro 0760bbae9b fix: lockfile drift 2026-06-26 13:30:29 +02:00
Cristina Poncela Cubeiro 988990f1c2 fix: lockfile drift 2026-06-26 13:12:43 +02:00
Cristina Poncela Cubeiro 2f853bbce0 fix: class RpcProcessInstance as state machine 2026-06-26 12:47:09 +02:00
Cristina Poncela Cubeiro 9505389beb fix: git url 2026-06-26 12:37:06 +02:00
Cristina Poncela Cubeiro 7f9300763e fix: orch (dynamic) version 2026-06-26 12:36:07 +02:00
Cristina Poncela Cubeiro 122527b22a fix: rpc-entry and bun support 2026-06-26 10:01:16 +02:00