Michael Kret
b60aafc809
feat(core): Make Instance AI aware of n8n Connect ( #33524 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-07-13 11:14:07 +00:00
José Braulio González Valido
3bc2292c78
test(ai-builder): Treat answer-only cases as valid without a built workflow (no-changelog) ( #33942 )
...
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.16.0) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 21:54:14 +00:00
José Braulio González Valido
13c95f2c05
fix(ai-builder): Eliminate non-builder noise families in workflow evals (no-changelog) ( #33944 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 13:25:29 +00:00
José Braulio González Valido
7dd065a77b
feat(ai-builder): Scale eval budgets by case complexity and bound the heaviest prompts (no-changelog) ( #33950 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 12:58:17 +00:00
Arvin A
e6dee743e6
test(ai-builder): Add advanced user-behavior multi-turn eval cases (no-changelog) ( #31758 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: José Braulio González Valido <jose.gonzalez@n8n.io>
Co-authored-by: José Braulio González Valido <josebragv@gmail.com>
2026-07-09 18:13:42 +00:00
oleg
a1df115aef
fix(core): Report auto-bound credentials from AI Assistant workflow builds ( #33802 )
2026-07-08 13:01:29 +00:00
oleg
2d42b3fecf
fix(core): Reconcile stale AI Assistant mocked-credential simulation plan before workflow verification ( #33808 )
2026-07-08 13:01:08 +00:00
Benjamin Schroth
48e7900db0
test(ai-builder): Add eval cases for evaluation generation ( #33719 )
Build: Benchmark Image / build (push) Waiting to run
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.16.0) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Util: Sync API Docs / sync-public-api (push) Waiting to run
2026-07-07 15:29:42 +00:00
Albert Alises
e83512dfd8
test(core): Add Instance AI eval cases for recently merged builder changes (no-changelog) ( #33763 )
2026-07-07 14:12:08 +00:00
Robin Braumann
f25699fe2c
test(core): Extend Instance AI intent eval fixtures (no-changelog) ( #33224 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-07 12:49:32 +00:00
Albert Alises
3aa3ffd13b
fix(core): Report node errors in workflow verification ( #33576 )
2026-07-07 08:21:38 +00:00
Riqwan Thamir
d21a499462
test(core): Add Instance AI loop pattern workflow eval cases (no-changelog) ( #33712 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-07 07:26:51 +00:00
Milorad FIlipović
c5d65998da
test: Reduce non-builder noise in MCP workflow evals (no-changelog) ( #33565 )
2026-07-06 13:48:11 +00:00
José Braulio González Valido
4d11639cf1
test(ai-builder): Add plan-rejection eval and harden multi-turn eval consistency (no-changelog) ( #33433 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-06 06:11:22 +00:00
Albert Alises
2be4092c4d
fix(core): Improve Instance AI workflow-building reliability ( #33530 )
2026-07-03 13:27:45 +00:00
oleg
6f0d30fbb1
fix: Improve AI Assistant post-build follow-ups ( #33419 )
2026-07-02 11:34:21 +00:00
Albert Alises
4192c9554e
feat(core): Prefer predefined credentials over generic auth on HTTP Request nodes ( #33298 )
2026-07-02 07:50:49 +00:00
José Braulio González Valido
2ad33a1303
fix(ai-builder): Fix AI-node eval mock-execution timeouts (no-changelog) ( #33323 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-01 08:33:51 +00:00
José Braulio González Valido
65f375bbd4
feat(ai-builder): Make eval executionScenarios optional for build-only cases (no-changelog) ( #33252 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-30 09:41:14 +00:00
José Braulio González Valido
7ea6900e58
feat(ai-builder): Honor seedThread.liveTurnRunId in eval reconstruction (no-changelog) ( #33251 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-30 09:34:10 +00:00
Mutasem Aldmour
b67ef426e8
test: Add Instance AI flight-status-change workflow eval ( #33228 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-30 06:55:40 +00:00
José Braulio González Valido
1d28330d18
feat(ai-builder): Dual-tenant LangSmith reads for Instance AI evals (no-changelog) ( #33230 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 17:17:14 +00:00
Riqwan Thamir
6d550faf7d
chore(core): Add test on voice based agent ( #33226 )
2026-06-29 14:23:40 +00:00
José Braulio González Valido
23d70d1bb9
feat(ai-builder): Source eval test cases from LangTracer (no-changelog) ( #33067 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 10:17:49 +00:00
Albert Alises
de8f2984ed
fix(core): Stop the builder from re-running a workflow it just verified (no-changelog) ( #33141 )
2026-06-29 08:10:44 +00:00
Jaakko Husso
691d39d9c8
fix(core): Ground WhatsApp Trigger verify-token guidance and add regression evals (no-changelog) ( #33095 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 07:39:08 +00:00
José Braulio González Valido
1f012f8cb5
test(ai-builder): Reproduce explicit scenario values in eval mocks (no-changelog) ( #33166 )
...
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.16.0) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Util: Update Node Popularity / update-popularity (push) Has been cancelled
Util: Update Node Popularity / approve-and-automerge (push) Has been cancelled
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-28 15:15:15 +00:00
oleg
a00ac2722c
fix(core): Make AI Assistant workflow verification and setup repeatable ( #33085 )
...
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2026-06-26 13:39:28 +00:00
Jaakko Husso
3b27616b41
fix(core): Settle failed workflow verification instead of looping (no-changelog) ( #33111 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 13:14:04 +00:00
José Braulio González Valido
d78aba164e
test(ai-builder): Add absolute green-gate verdict for pr-tier evals (no-changelog) ( #32984 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 10:00:06 +00:00
Albert Alises
9161865a72
fix(core): Improve builder handling of errored expressions (no-changelog) ( #33059 )
2026-06-26 09:23:39 +00:00
Jaakko Husso
713203a1c5
fix(core): Surface infeasible core capabilities instead of silently downgrading (no-changelog) ( #33063 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 09:19:17 +00:00
Albert Alises
cf8ef2b1b7
test(core): Add eval ensuring builder decides technical choices instead of asking (no-changelog) ( #33053 )
Build: Benchmark Image / build (push) Waiting to run
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.16.0) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Util: Sync API Docs / sync-public-api (push) Waiting to run
Release: Schedule Patch Release PRs / Create patch release PR (${{ matrix.track }}) (beta) (push) Has been cancelled
Release: Schedule Patch Release PRs / Create patch release PR (${{ matrix.track }}) (stable) (push) Has been cancelled
Release: Schedule Patch Release PRs / Create patch release PR (${{ matrix.track }}) (v1) (push) Has been cancelled
2026-06-25 22:33:38 +00:00
Albert Alises
02df832dd2
fix: Prefer placeholders over pre-build setup questions ( #32969 )
Build: Benchmark Image / build (push) Waiting to run
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.16.0) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Util: Sync API Docs / sync-public-api (push) Waiting to run
2026-06-25 17:39:39 +00:00
Riqwan Thamir
58fb6ca742
feat(core): Add more use case evaluations to instance ai (no-changelog) ( #32963 )
2026-06-25 14:15:30 +00:00
Milorad FIlipović
5b77a717b0
fix(core): Handle array-style conversations in mcp evals (no-changelog) ( #33013 )
2026-06-25 11:53:57 +00:00
Riqwan Thamir
b3a399553f
fix(core): Broken workflow verification loop in iAI (no-changelog) ( #32979 )
...
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2026-06-25 08:20:46 +00:00
Milorad FIlipović
d3dd105aae
feat(core): Make instanceAI evals more mcp-friendly (no-changelog) ( #32916 )
2026-06-25 06:33:50 +00:00
Riqwan Thamir
436bfbc875
feat(core): Add test for whatsapp support agent (no-changelog) ( #32953 )
2026-06-24 15:49:50 +00:00
José Braulio González Valido
d7a331afd4
test(ai-builder): Detect excessive build-workflow failures in instance-ai evals (no-changelog) ( #32808 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 09:56:59 +00:00
José Braulio González Valido
365fb7ec6d
test(ai-builder): Add multi-turn context-carry eval case (no-changelog) ( #32868 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 08:51:49 +00:00
Albert Alises
5f4d196001
fix(core): Route clarifying questions through ask-user ( #32871 )
2026-06-24 06:48:14 +00:00
José Braulio González Valido
fe11536df1
feat(ai-builder): Add conversation pre-seeding to workflow evals (no-changelog) ( #32196 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-23 17:30:30 +00:00
Albert Alises
846e2cb36d
fix(core): Require verification evidence before Instance AI claims a fix works (no-changelog) ( #32835 )
2026-06-23 17:30:03 +00:00
Albert Alises
842b01f08e
fix(core): Guide AI builder to create exact Data Table schemas and repair mismatches (no-changelog) ( #32811 )
2026-06-23 13:56:10 +00:00
José Braulio González Valido
13239d1cfe
feat(ai-builder): Add per-test-case eval credentials via thread credential-view pinning (no-changelog) ( #32161 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-22 14:02:57 +00:00
Albert Alises
9ce241b8bf
fix(core): Stop re-asking answered or skipped clarifying questions ( #32755 )
2026-06-22 13:30:45 +00:00
Albert Alises
d5dd4923a5
fix: Handle HTTP raw body validation loops ( #32277 )
2026-06-18 12:05:40 +00:00
Riqwan Thamir
9d7ed01e95
feat(core): Add eval + trim builder prompt (no-changelog) ( #32484 )
2026-06-18 07:55:33 +00:00
Albert Alises
15da27bc52
fix(core): Guide workflow builder to handle list-shaped HTTP responses (no-changelog) ( #32144 )
2026-06-16 15:15:32 +00:00
