Commit Graph

249 Commits

Author SHA1 Message Date
Mutasem Aldmour ef13ad0abc fix(core): Report what credential setup actually selected (#37019)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-27 09:31:43 +00:00
Predrag Ristic 6170b2bf18 build(core): Update Instance AI dependencies (#36635) 2026-08-24 13:35:16 +00:00
José Braulio González Valido 5ec90c5331 test(ai-builder): Pin threadIds in the eval-results dispatcher contract (no-changelog) (#36884)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-24 13:19:28 +00:00
RomanDavydchuk f41cf0cbd6 feat(editor): Move AI Assistant connections from the sidebar to a "+" button in the text input (#36585) 2026-08-21 13:37:06 +00:00
Bernhard Wittmann 9c4b439122 fix(core): Stop code editors mangling values typed by browser_type (no-changelog) (#36804) 2026-08-21 13:08:05 +00:00
Bernhard Wittmann 44041d5d3c test(core): Add openai, gemini and slack credential-setup eval fixtures (no-changelog) (#36461)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-21 06:27:16 +00:00
oleg 884a781ef0 fix(core): Correct chainLlm structured-output shape in eval verifier guidance (no-changelog) (#36283) 2026-08-19 11:07:12 +00:00
Rodrigo Santos da Silva 69ba5a8618 feat(ai-builder): Let the eval harness mint Simplified Custom Auth credentials from setup-card recipes (no-changelog) (#36192)
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
2026-08-19 08:44:23 +00:00
Milorad FIlipović a37b9a0c49 feat(core): Extend evaluations to support node groups (no-changelog) (#35629)
Co-authored-by: Miguel Ángel Moreno <1411774+miguelsaddress@users.noreply.github.com>
2026-08-19 08:42:53 +00:00
Predrag Ristic 59efcb95b2 fix(core): Handle managed credentials in workflow codegen (#36210) 2026-08-18 15:04:36 +00:00
Elias Meire fdbf88b469 test(core): Add MCP registry discovery evals (no-changelog) (#36063) 2026-08-18 12:28:05 +00:00
Jaakko Husso e1a6ede450 fix(core): Handle projects better on AIA workflow listing (#36413)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 11:58:35 +00:00
Jaakko Husso 6ace2a5b4f fix(core): Remember skipped Instance AI credential setup for the rest of a thread (#36308)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 12:53:22 +00:00
Robin Braumann 6b656c97af refactor(core): Consolidate agent workspace string replacement tools (no-changelog) (#36178)
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Riqwan Thamir <rmthamir@gmail.com>
2026-08-17 11:11:51 +00:00
oleg 51aa6fb519 feat(core): Add one-off operation flow and insertion-semantics rules to AI Assistant (#36184) 2026-08-14 11:50:10 +00:00
Iván Ovejero c0acde43a1 ci: Run PR pipeline on Node 26 (#34032)
Co-authored-by: Danny Martini <danny@n8n.io>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-14 07:54:25 +00:00
Bernhard Wittmann 62d5de3ec7 feat: Add the credential-setup browser eval lane (no-changelog) (#35982)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-13 15:56:24 +00:00
Rodrigo Santos da Silva 2d37afc13d test(ai-builder): Let a case declare a credential already broken before the conversation started (no-changelog) (#36029)
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-13 13:33:11 +00:00
Riqwan Thamir 91ebeecb4e feat(core): Improve Instance AI model experiments (no-changelog) (#35034)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-13 10:15:03 +00:00
Ricardo Espinoza b9496b2fa6 refactor(core): Consolidate the node search engine into @n8n/ai-utilities (no-changelog) (#35546) 2026-08-13 09:28:06 +00:00
Robin Braumann 01ce4490d0 feat(core): Add writable workspaces to agents (#36033)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-12 12:24:33 +00:00
Arvin A 45f243419d test(core): Drive external workflow edits from the user proxy (#35736) 2026-08-12 08:42:20 +00:00
Svetoslav Dekov 9205eb3f19 test(core): Support credential seeding in MCP workflow evals (no-changelog) (#35782)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Ricardo Espinoza <ricardo@n8n.io>
2026-08-10 19:56:03 +00:00
Raúl Gómez Morales 53841f1b0e feat: Add Simplified Custom Auth credential with recipe-guided setup in the AI Assistant (#35056) 2026-08-07 09:22:36 +00:00
Svetoslav Dekov ff37ef5b3f ci(ai-builder): Gate the mcp-gate eval tier absolutely (no-changelog) (#35762)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-06 14:37:04 +00:00
José Braulio González Valido 9b8f964a55 feat(ai-builder): Support seeding agents alongside workflows in eval threads (no-changelog) (#35548)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-06 12:40:14 +00:00
José Braulio González Valido 9ac12d212f test(ai-builder): Let seeded eval credentials pass their connection test (no-changelog) (#35675)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-06 09:40:27 +00:00
José Braulio González Valido 1575fce711 fix(ai-builder): Bound eval lane requests and stop abandoned mocked executions (no-changelog) (#35228)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-06 08:23:37 +00:00
José Braulio González Valido 166771c77d feat(ai-builder): Push a seeded case, and hand the agent its workflow (no-changelog) (#35304)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 16:09:01 +00:00
oleg f9bddc7ff3 fix: Include node behavior flags in instance-ai eval judge context (no-changelog) (#35644) 2026-08-05 14:59:37 +00:00
José Braulio González Valido 7c61f2826a fix(ai-builder): Give a case's scenario data tables per-run names (no-changelog) (#35543)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 12:48:00 +00:00
José Braulio González Valido d57a81ac60 fix(ai-builder): Keep model-provider outages out of eval builder scores (no-changelog) (#35293)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-04 10:52:11 +00:00
José Braulio González Valido 5d8f2353bf fix(ai-builder): Give a restored seed workflow a unique name and evict leftovers (no-changelog) (#35299)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-03 17:26:21 +00:00
José Braulio González Valido e62417356f feat(ai-builder): Collapse the eval case's three seed keys into one seed union (no-changelog) (#35292)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-03 14:37:06 +00:00
Mutasem Aldmour 05a809867e feat(ai-builder): Add eval check for secrets placed in HTTP node parameters (no-changelog) (#35421)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-03 13:43:24 +00:00
José Braulio González Valido c6917a194f fix(ai-builder): Record the served wire envelope in the eval LLM mock ledger (no-changelog) (#34929)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-03 13:16:45 +00:00
José Braulio González Valido a2b8383bf9 feat(ai-builder): Let eval cases set up a working credential (no-changelog) (#35410)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-03 11:21:11 +00:00
Rodrigo Santos da Silva a25a1ec608 feat: Add manual credential-setup path to instance-ai eval harness (no-changelog) (#35197)
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-03 09:11:25 +00:00
José Braulio González Valido be12a4ccdc feat(ai-builder): Let eval runs exercise the builder's web search (no-changelog) (#35274)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 07:31:10 +00:00
Riqwan Thamir bbd7b7db88 feat(core): Add workflow SDK validation framework for Instance AI (#35045)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 15:18:11 +00:00
José Braulio González Valido c3b50283fd fix(ai-builder): Report an unparseable LLM check verdict as errored (no-changelog) (#35198)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-30 08:18:36 +00:00
José Braulio González Valido aad2fa5577 feat(ai-builder): Add a Google Drive credential template to the eval seeder (no-changelog) (#35200)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 22:17:11 +00:00
Mutasem Aldmour 22c8117321 fix(ai-builder): Route eval report artifacts through --output-dir (no-changelog) (#35083)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 11:04:42 +00:00
José Braulio González Valido 2ae18ad9f6 feat(ai-builder): Validate the eval conversation-seed message envelope (no-changelog) (#35138)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 08:58:55 +00:00
Luka Zivkovic 650d893151 feat(ai-builder): Emit transcriptPerRun and buildErrorPerRun in eval-results.json (no-changelog) (#35078)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 19:25:22 +00:00
Tomi Turtiainen b964ed6f4b refactor(core): Move sleep into @n8n/utils and unify sleep/sleepWithAbort (#35057) 2026-07-28 18:47:18 +00:00
José Braulio González Valido 632ef22c0c feat(ai-builder): Carry an eval case's conversation seed in the case body (no-changelog) (#35074) 2026-07-28 16:26:08 +00:00
José Braulio González Valido 6d8b01dc79 fix(ai-builder): Enforce declared field names on eval pin data (no-changelog) (#34960)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 13:11:02 +00:00
Michael Kret b2af755502 fix(core): Prefer n8n credits covered nodes in Instance AI workflow builds (#35019) 2026-07-28 11:58:42 +00:00
José Braulio González Valido 66408a0cd5 feat(ai-builder): Push agent intent eval cases from data/agents and drop synced case files (no-changelog) (#34957)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 07:25:30 +00:00