Commit Graph

1666 Commits

Author SHA1 Message Date
Saryev Rustam 7b52cef2e6 feat(ai): add OpenRouter OAuth support (#6927)
Closes #6814
2026-07-22 15:48:39 +02:00
Armin Ronacher 5dc40fee33 feat(ai): derive generated model types from JSON 2026-07-22 13:13:36 +02:00
David Brailovsky 906b40a753 Merge pull request #6955 from earendil-works/fix/handle-openai-previous-response-not-found-error
handle openai websocket previous_response_not_found error
2026-07-22 12:41:58 +02:00
David Brailovsky c5dcb26000 handle openai websocket previous_response_not_found error
fixes #6931
2026-07-22 10:26:24 +00:00
Matthew bc41f612da fix(ai): cache OpenRouter tool results
closes #6940
2026-07-22 11:48:33 +02:00
Mario Zechner 6f95a33888 fix(ai): enable cache control for OpenRouter aliases
closes #6940
2026-07-22 11:46:21 +02:00
Christian Klotz 33e40c3e15 fix(ai): retry DNS transport failures (#6946)
Fixes #6904
2026-07-22 11:26:19 +02:00
zay a5afc3f171 feat(ai): add Kimi Code subscription OAuth login (#6935)
Add a device authorization grant flow (RFC 8628) for the kimi-coding
provider, mirroring the official Kimi Code CLI: device authorization and
token polling against https://auth.kimi.com, refresh-token rotation with
retry/backoff, and Bearer auth via toAuth headers. The provider now
offers 'Sign in with Kimi Code' alongside the existing KIMI_API_KEY
auth. Host is overridable via KIMI_CODE_OAUTH_HOST / KIMI_OAUTH_HOST.

Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
2026-07-22 08:35:03 +02:00
David Brailovsky 1ae064099c generate-models: use reasoning options from models.dev (#6928)
* generate-models: use reasoning options from models.dev

* fix tests
2026-07-22 08:33:34 +02:00
Mario Zechner dd6bea41ef Add [Unreleased] section for next cycle 2026-07-21 18:40:11 +02:00
Mario Zechner 20be4b18d4 Release v0.81.1 2026-07-21 18:40:08 +02:00
Mario Zechner b9e5c5d941 fix(agent): restore streamFn extension compatibility
Keep streamFn required for typed callers while preserving the legacy runtime fallback for extensions that omit it.\n\nfixes #6915
2026-07-21 18:37:07 +02:00
Armin Ronacher a82289637b feat(ai): add new Gemini generated models 2026-07-21 18:25:27 +02:00
David Brailovsky 243f64be59 report aborted retry attempts as unsuccessful 2026-07-21 15:34:31 +00:00
David Brailovsky ceac988635 Merge remote-tracking branch 'origin/main' into fix/issue-6647-retry-summary-requests-2 2026-07-21 17:15:54 +02:00
David Brailovsky 959cc1897e fix moonshot/kimi3 compat properties 2026-07-21 16:49:36 +02:00
Mario Zechner 3dcb411e89 Add [Unreleased] section for next cycle 2026-07-21 15:28:05 +02:00
Mario Zechner 9c480b6ad2 Release v0.81.0 2026-07-21 15:28:05 +02:00
Mario Zechner c23b58a6d8 feat(ai): update generated image models 2026-07-21 14:51:14 +02:00
Mario Zechner c901d9a877 docs: audit unreleased changelogs 2026-07-21 14:47:00 +02:00
David Brailovsky 162179af5a add branch/compact retries to agent-harness 2026-07-21 12:11:39 +00:00
David Brailovsky 8e53e0e49c compaction & branch summarization follow retry policy
fixes #6647

compaction (auto & manual) and branch summarization retry on transient failures.
use the same retry policy from settings.
emit events for the tui to show indication of retries
2026-07-21 10:07:20 +00:00
Armin Ronacher 54fad505b9 fix(coding-agent): prefer newer generated model catalogs 2026-07-21 11:11:08 +02:00
David Brailovsky 890b3547af run generate-models
fixes #6891
2026-07-21 07:48:27 +00:00
Armin Ronacher c8c3cd499f fix(ai): validate generated model data before builds 2026-07-20 22:29:06 +02:00
Armin Ronacher 3a40794ea1 feat(ai): regenerate models 2026-07-20 17:19:40 +02:00
Mario Zechner f8b74a4507 fix: complete extension usage accounting
closes #6509
2026-07-20 17:06:22 +02:00
David Brailovsky 2fd3868401 add usage info to branch summary, compaction and tool result entries (#6671)
* add usage info to branch summary entries

* add usage to compaction entries

* allow custom tools to report llm usage in tool results

* allow observing and patching usage in tool_result hooks

* agent-harness: save usage in entries

for compaction, branch summaries and tool results
2026-07-20 16:41:43 +02:00
Cristina Poncela Cubeiro 1942b2600f fix: env section ignored (#6864) 2026-07-20 16:20:49 +02:00
Mario Zechner 13437ca828 fix(ai): normalize Kimi K2.7 to the canonical coding model
Treat the models.dev k2p7 entry as an alias for kimi-for-coding and regenerate provider catalogs. This restores consistency between generated model types and values and unblocks repository type checks.
2026-07-20 14:04:21 +02:00
QuintinShaw bbb91fa8ae feat(ai): add Qwen Token Plan as built-in provider (#6858)
Add Alibaba Cloud Model Studio Token Plan subscription service as two
built-in API-key providers: qwen-token-plan (international, Singapore)
and qwen-token-plan-cn (China, Beijing).

Each provider exposes 15 text-generation models (Qwen, DeepSeek, GLM,
Kimi, MiniMax) via the OpenAI-compatible endpoint with DashScope
enable_thinking support. Model metadata is sourced from models.dev;
qwen3.8-max-preview is hardcoded until models.dev includes it.

Also fixes kimi-coding test references (k2p7 -> kimi-for-coding) after
models.dev catalog update picked up by generate-models.

Closes #6850
2026-07-20 13:53:30 +02:00
Cristina Poncela Cubeiro d9f7f81473 fix: tool_call_id error when switching (#6854) 2026-07-20 13:51:16 +02:00
Aadish Verma 35f12c8c72 fix: gpt 5.6 context window (#6853) 2026-07-20 12:22:22 +02:00
David Brailovsky 21f92b319d run generate-models 2026-07-20 10:21:34 +00:00
David Brailovsky da95649b95 lint fix 2026-07-20 10:19:01 +00:00
David Brailovsky 8b93737078 kimi: add low,high to k3 and remove k2p7 references 2026-07-20 09:00:15 +00:00
Federico Jaramillo Martinez 916de90dbf fix(pi-ai): normalize bin path to avoid consumer lockfile churn (#6812)
The npm registry normalizes bin paths in packument metadata
("dist/cli.js") while the published tarball keeps the authored
"./dist/cli.js". npm consumers get perpetual one-line
package-lock.json flips depending on whether resolution used
registry metadata or the extracted package.

Drop the "./" prefix to match the registry-normalized form and the
sibling coding-agent package.

Fixes #6811
2026-07-20 09:18:14 +02:00
Alexey Zaytsev 94373d815d feat(ai): add shared contentText utility (#6840)
Co-authored-by: Armin Ronacher <armin.ronacher@active-4.com>
2026-07-20 01:50:36 +02:00
Armin Ronacher 75cb0b873a fix(ai): support responses API for OpenCode Go 2026-07-20 01:28:57 +02:00
Alexey Zaytsev d2f8dafb0f fix(ai,agent,coding-agent): share UUIDv7 and use for Codex (#6834) 2026-07-20 01:23:47 +02:00
Armin Ronacher 956074697f fix(ai): replace generic record checks 2026-07-19 22:21:31 +02:00
David Brailovsky 5124c61b25 buildfix: fix tests referencing old models 2026-07-17 13:24:11 +00:00
David Brailovsky ce48d9b4ef fix(ai): preserve GitHub Copilot long-context pricing tiers, closes #6668 2026-07-17 12:38:12 +02:00
Armin Ronacher a9f6a3159a feat(ai): separate generated model data (#6765) 2026-07-17 11:08:48 +02:00
David Brailovsky b0c2a90e51 fix(coding-agent): retry OpenAI Responses early EOF
closes #6727
2026-07-17 11:00:03 +02:00
Armin Ronacher 8881e17625 fix(ai): show implied Kimi Coding subscription costs 2026-07-17 10:01:22 +02:00
Alexey Zaytsev 056c8cbb80 feat(ai): make model generation explicit (#6742) 2026-07-17 09:01:42 +02:00
Armin Ronacher 216e672e7c Add [Unreleased] section for next cycle 2026-07-16 23:59:44 +02:00
Armin Ronacher 8dc78834cd Release v0.80.10 2026-07-16 23:59:41 +02:00
Armin Ronacher b8575f60fa fix(ai): use adaptive thinking for Kimi Coding 2026-07-16 20:59:54 +02:00