github-mirror/n8n
1
0
Fork 0
mirror of https://github.com/n8n-io/n8n.git synced 2026-07-30 12:34:59 +02:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity Graph
22,315 Commits 1,607 Branches 2,093 Tags 2.5 GiB
test-validate
Commit Graph

539 Commits

Author SHA1 Message Date
Riqwan Thamir
41e31a11c3
chore: wip 2026-07-27 01:23:20 +02:00
Riqwan Thamir
351ddabdbc
chore: wip 2026-07-26 23:33:00 +02:00
Riqwan Thamir
c16cc7f85c
chore: wip 2026-07-26 20:27:35 +02:00
Riqwan Thamir
3e63ae95a0
chore: wip 2026-07-26 16:01:10 +02:00
Riqwan Thamir
a9135e79ed
chore: wip 2026-07-25 22:05:18 +02:00
Riqwan Thamir
fc0c0c45fc
chore: wip 2026-07-25 22:02:47 +02:00
Riqwan Thamir
59b1ec0f1a
chore: wip 2026-07-25 21:56:14 +02:00
Riqwan Thamir
a121aff730
chore: wip 2026-07-25 18:35:53 +02:00
Riqwan Thamir
38688aafe4
ci: Throttle Instance AI evals for Baseten rate limits 
Expose lanes/eval-concurrency knobs and auto-set 1/2 (plus a 10h timeout)
when model is baseten/*, so GLM experiments fit Basic verified TPM/RPM.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:35:51 +02:00
Riqwan Thamir
509719d27c
chore: add opus 5 2026-07-25 18:35:48 +02:00
Riqwan Thamir
f556fd381e
feat(instance-ai): Add Baseten GLM 5.2 provider support and eval options 
Integrate @ai-sdk/baseten for native GLM routing, map GLM 5.2 thinking to high effort, raise the default max output token cap to avoid reasoning-only truncation, and wire Baseten models into Instance AI eval experiments via EVALS_BASETEN_KEY.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:35:43 +02:00
Riqwan Thamir
a19d2d9cfe
ci: Add openai/gpt-5.6-luna to Instance AI evals model options (no-changelog) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:35:40 +02:00
Riqwan Thamir
6466dbd6ea
feat(core): Pin OpenAI Instance AI thinking to medium for GPT-5.6 Sol (no-changelog) 
Use AI SDK reasoningEffort medium by default, expand OpenAI effort types for
GPT-5.6, bump @ai-sdk/openai, and route openai/* evals through EVALS_OPENAI_KEY.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:35:38 +02:00
Riqwan Thamir
c4532b5692
feat(core): Raise default Instance AI thinking effort to medium (no-changelog) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:35:01 +02:00
Riqwan Thamir
677b96d1f9
feat(core): Pin low Anthropic adaptive thinking effort (no-changelog) 
Forward adaptive effort through Anthropic provider options and default
Instance AI / agent builder to effort=low.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:34:58 +02:00
Riqwan Thamir
a6ae91804e
feat(core): Pin low reasoning effort for Grok 4.5 (no-changelog) 
Also enable xAI thinking capability and default low effort for
grok-4.5 via OpenRouter or native xAI.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:34:57 +02:00
Riqwan Thamir
e4b2df9230
feat(core): Pin low OpenRouter reasoning effort for Kimi K3 (no-changelog) 
Enable OpenRouter thinking in provider capabilities and default Instance AI
to reasoning.effort=low for kimi-k3 model ids.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-25 18:34:53 +02:00
Riqwan Thamir
55e92cc283
refactor(core): Consolidate sandbox and skill guidance in system prompt (no-changelog) (#34909) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-24 15:50:37 +00:00
Anne Aguirre
decb3228c5
feat(ai-builder): Tidy up tool names and agent builder tool UX (#34646)
Some checks failed
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Details
Build: Benchmark Image / build (push) Has been cancelled
Details
Util: Sync API Docs / sync-public-api (push) Has been cancelled
Details
2026-07-24 15:26:08 +00:00
Robin Braumann
8017b3d85f
feat(core): Add telemetry events for agent publishing, builder capabilities, and interactive flows (#34887) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-24 14:34:11 +00:00
Riqwan Thamir
50789b1553
fix(core): Guiding data-table skill routing better (no-changelog) (#34882) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-24 12:12:04 +00:00
Riqwan Thamir
765129c436
refactor(core): Slim system prompt into skills and tool descriptions (no-changelog) (#34816) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-24 09:58:06 +00:00
José Braulio González Valido
e904939db2
fix(ai-builder): Halt workflow verification at send-and-wait gates on loops (#34809) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-24 08:50:41 +00:00
José Braulio González Valido
cbe5710c4c
feat(ai-builder): Report per-case claude build cost for MCP eval builds (no-changelog) (#34777) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-23 18:42:09 +00:00
Riqwan Thamir
b0a14728d7
refactor(core): Remove unused templates and list_skills AI tools (no-changelog) (#34741) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-23 15:38:41 +00:00
Robin Braumann
e5b1ac9f38
feat(core): Build agent drafts before asking for setup in the agent builder (no-changelog) (#34615) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-23 12:55:51 +00:00
José Braulio González Valido
b93a99945b
feat(ai-builder): Harden the eval harness — crash-recovery journal, parity fixes, extension points (no-changelog) (#34747) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-23 12:25:55 +00:00
Raúl Gómez Morales
a8c90f84fe
fix(core): Fall back to the run's resolved model for AI Assistant verification LLM calls (#34627) 2026-07-23 11:16:03 +00:00
Raúl Gómez Morales
5a647443ad
fix(ai-builder): Keep assistant replies in the user's language during tool-heavy turns (#34761) 2026-07-23 10:08:31 +00:00
Raúl Gómez Morales
206a2581e4
fix(core): Preserve the underlying error as cause on Instance AI workspace file reads (#34759) 2026-07-23 10:08:06 +00:00
José Braulio González Valido
3f63b73d38
fix(ai-builder): Scope user-proxy decisions to the conversation moment (no-changelog) (#34719) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-23 00:04:17 +00:00
José Braulio González Valido
ce6416fe04
docs(ai-builder): Add a source-linking provenance step to the eval-authoring skill (no-changelog) (#34721)
Some checks are pending
Build: Benchmark Image / build (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Details
Util: Sync API Docs / sync-public-api (push) Waiting to run
Details 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 22:35:13 +00:00
José Braulio González Valido
463d50b1bd
refactor(ai-builder): Decompose the eval CLI into phase modules with typed seams (no-changelog) (#34691) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 16:25:44 +00:00
Riqwan Thamir
94e505a972
fix(core): Strip null optional node fields from AI-generated workflows (#34668) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-22 15:38:56 +00:00
Riqwan Thamir
c0fe8ba4db
feat(editor): Track Instance AI entry point as action_source on builder messages (#34671) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-22 13:24:29 +00:00
José Braulio González Valido
5a1aa3feef
fix(ai-builder): Detect datasets changes when re-pushing eval cases to LangTracer (no-changelog) (#34658) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 11:55:48 +00:00
José Braulio González Valido
ee46e64d50
chore(ai-builder): Typecheck the eval harness and pin its external contracts (no-changelog) (#34673) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 08:18:41 +00:00
Arvin A
babc0b7344
fix(core): Fix eval-collection scoring, re-run and progress states (no-changelog) (#34475) 2026-07-21 16:08:38 +00:00
José Braulio González Valido
5fd800de20
feat(ai-builder): Support execution scenarios for first-class agents in evals (#34384)
Some checks failed
Build: Benchmark Image / build (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Details
Util: Sync API Docs / sync-public-api (push) Waiting to run
Details
Test: E2E Performance / prepare-docker (push) Has been cancelled
Details
Release: Storybook / Cloudflare Pages (push) Has been cancelled
Details
Test: E2E Performance / build-and-test-performance (push) Has been cancelled
Details
Test: E2E Performance / Canvas Perf Sentinels (push) Has been cancelled
Details 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-21 13:54:06 +00:00
Raúl Gómez Morales
bd89cfc041
fix(core): Classify masked Instance AI stream failures as quota exhaustion via credit re-check (#34553) 2026-07-21 12:37:17 +00:00
n8n-assistant[bot]
662a23c202
🚀 Release 2.32.0 (#34600) 
Co-authored-by: n8n-release-helper[bot] <265227495+n8n-release-helper[bot]@users.noreply.github.com>
 2026-07-21 07:14:52 +00:00
Albert Alises
080c3ccc8c
fix(core): Alert on unusable Instance AI sandbox snapshots and gate the release on snapshot health (#34344) 2026-07-20 18:21:53 +00:00
Riqwan Thamir
267fd853cd
fix(core): Cancel Instance AI workspace tools promptly on stop (#34551) 
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Robin Braumann <50590409+bjorger@users.noreply.github.com>
 2026-07-20 16:40:44 +00:00
José Braulio González Valido
32d4c1a123
ci(ai-builder): Point eval workflows at the consolidated LangTracer baseline suite (no-changelog) (#34402) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-20 13:55:41 +00:00
Riqwan Thamir
4f8fef13ca
fix(core): Cancel Instance AI tool runs promptly when generation is stopped (#34433) 
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Robin Braumann <50590409+bjorger@users.noreply.github.com>
 2026-07-20 11:23:16 +00:00
Robin Braumann
5cb674ed37
feat: Validate agent configuration before publishing (#34452) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-20 10:46:29 +00:00
Mutasem Aldmour
02af123574
feat: Add typed seed data tables with rows on execution scenarios (#34420) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-17 17:30:19 +00:00
Michael Drury
969a68e217
fix(core): Prefer direct tools for agent capabilities (#34466) 2026-07-17 15:57:03 +00:00
Eugene
74be136828
fix(editor): Show agent name instead of Untitled in AI assistant artifacts (no-changelog) (#34395) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-17 15:29:47 +00:00
Mutasem Aldmour
7d6fd4ca9c
fix: Report an unverifiable unit as notVerified, not a silent pass (#34421) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-17 14:23:10 +00:00