Commit Graph

4447 Commits (e0b4f3b995cc69920c19e67edbde13bcc3d4c105)

Author SHA1 Message Date
Peter Steinberger 51633fc13a
fix: respect disabled heartbeat guidance 8 months ago
Peter Steinberger d51f527cca
feat: add gh-read GitHub app helper 8 months ago
Peter Steinberger c0aed59fca
refactor: move qa suite definitions into markdown 8 months ago
Gustavo Madeira Santana cfe71e2e44 Docs: document approval adapter subpaths 8 months ago
Gustavo Madeira Santana b78202d44e fix(exec): harden stale/replay/live requests 8 months ago
Bruce MacDonald 86f35a9bc0
chore(ollama): update suggested onboarding models (#62626)
Merged via squash.

Prepared head SHA: 48c083b88ae26d76ad9a6086efe43629ec124fb2
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Reviewed-by: @BruceMacD
8 months ago
Gustavo Madeira Santana d78512b09d
Refactor: centralize native approval lifecycle assembly (#62135)
Merged via squash.

Prepared head SHA: b7c20a7398e91fcba5a1cf6dc5dc0811547107b4
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
8 months ago
DhruvBhatia0 12331f0463
feat: add pluggable compaction provider registry (#56224)
Merged via squash.

Prepared head SHA: 0cc9cf3f30972ad86914ec9d439b3e68591e7130
Co-authored-by: DhruvBhatia0 <69252327+DhruvBhatia0@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
8 months ago
Peter Steinberger e973275fd0
fix: harden claude-cli live switch smoke 8 months ago
Peter Steinberger 9d4b0d551d
fix: support inferrs string-only completions 8 months ago
nv-kasikritc d43cc470c6
refactor(nvidia-endpoints): updated language & default models (#59866)
* fix(nvidia-endpoints): updated language & default models

* fix(nvidia-endpoints): updated link for api key

* fix(nvidia-endpoints): removed unused const

* fix(nvidia-endpoints): edited max tokens

* fix(nvidia-endpoints): fixed typo

---------

Co-authored-by: Devin Robison <drobison00@users.noreply.github.com>
8 months ago
Tak Hoffman ac6693986b
docs: rename and improve infer docs 8 months ago
Tak Hoffman 365c30fbfe
docs infer cli examples and alias note 8 months ago
Tak Hoffman 97c031a8db
feat: Add first-class infer CLI for inference workflows (#62129)
* refresh infer branch onto latest main

* flatten infer media commands

* fix tts runtime facade export

* validate explicit web search providers

* fix infer auth logout persistence
8 months ago
Vincent Koc dfb6c9c920 perf(plugin-sdk): split channel secret runtime helpers 8 months ago
Peter Steinberger 1cec37184c
fix: harden qa memory dreaming sweep 8 months ago
Peter Steinberger e5716394ca
Config: sync generated schema baseline 8 months ago
Peter Steinberger 4d4dbe8e15
test: share live probes with acp bind 8 months ago
Peter Steinberger c2f9de3935
feat: unify live cli backend probes 8 months ago
Peter Steinberger 124cd5e307
feat: auto-reload qa lab fast refresh 8 months ago
Peter Steinberger 54a884865e
feat: add fast qa lab ui refresh mode 8 months ago
Peter Steinberger 65f9fc397e
perf(test): split support boundary shard 8 months ago
Peter Steinberger 0af808b457
test: add cli backend live matrix metadata 8 months ago
Vincent Koc 9e9730a55e chore(plugin-sdk): refresh api baseline hash 8 months ago
Vincent Koc 294ee477ac fix(memory-wiki): stabilize compiled digest prompts 8 months ago
Vincent Koc 2988203a5e feat(context-engine): add memory prompt helper 8 months ago
Vincent Koc 947a43dae3 feat(memory-wiki): add belief-layer digests and compat migration 8 months ago
Vincent Koc 49fbecbf16 perf(plugin-sdk): add web fetch contract artifacts 8 months ago
Neerav Makwana b9179ee4b6 Docs: match Greptile wording for magistral-* line
Made-with: Cursor
8 months ago
Neerav Makwana 68bfc6fcf5 Mistral: enable reasoning_effort for mistral-small-latest
Made-with: Cursor
8 months ago
Peter Steinberger 37dccb52ed
test: add gemini acp bind docker coverage 8 months ago
Peter Steinberger 13a60aa93b
docs: document shared mention policy 8 months ago
Vincent Koc e318f48ff2 perf(secrets): narrow channel secret-ref imports 8 months ago
Peter Steinberger a3b2fdf7d6
feat(agents): add prompt override and heartbeat controls 8 months ago
Peter Steinberger ce1d2c1004
test: cover claude and codex acp bind docker smoke 8 months ago
Gustavo Madeira Santana 9fd47a5aed
Matrix: prompt invite auto-join during onboarding (#62168)
Merged via squash.

Prepared head SHA: aec7a2249a5e3b491a2901b40f932ef43a9587de
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
8 months ago
Praktika Engineer b8c8139138
feat(slack): add thread.requireExplicitMention config option (#58276)
* feat(slack): add thread.requireExplicitMention config option

When requireMention is true in a Slack channel, replying inside a thread
where the bot previously participated currently bypasses mention gating
via implicit mention detection. This makes the bot respond to every
thread message even without an explicit @mention.

Add channels.slack.thread.requireExplicitMention (default: false) which,
when set to true, suppresses implicit thread mentions. Only explicit
@bot mentions will trigger replies inside threads.

Closes #34389
Closes #49972

* slack: refresh changelog and generated config artifacts

* slack: restore bundled channel metadata generation

---------

Co-authored-by: praktika-devops <devops@praktika.ai>
Co-authored-by: George Pickett <gpickett00@gmail.com>
8 months ago
Peter Steinberger 191f867ef6
perf(test): split ui and bundled full-suite shards 8 months ago
Peter Steinberger 425592cf9c
refactor: share media normalization across runtimes 8 months ago
Vincent Koc 4603f231c3 perf(secrets): add web search contract sdk seam 8 months ago
Vincent Koc 2a6e8dca47 fix(plugin-sdk): add web-search contract subpath 8 months ago
Peter Steinberger a463a33eee
feat: preserve media intent across provider fallback 8 months ago
Vincent Koc 78639eff76 perf(secrets): narrow channel secret sdk seam 8 months ago
Peter Steinberger 8ff570ee42 refactor: resolve channel env vars from plugin manifests 8 months ago
Peter Steinberger bc18e69fbf fix: separate arcee auth envs from openrouter 8 months ago
arthurbr11 95106be59b feat: enhance Arcee AI provider with OpenRouter support and update onboarding instructions 8 months ago
arthurbr11 5ac2f58c57 feat: add Arcee AI provider plugin
Add a bundled Arcee AI provider plugin with ARCEEAI_API_KEY onboarding,
Trinity model catalog (mini, large-preview, large-thinking), and
OpenAI-compatible API support.

- Trinity Large Thinking: 256K context, reasoning enabled
- Trinity Large Preview: 128K context, general-purpose
- Trinity Mini 26B: 128K context, fast and cost-efficient
8 months ago
Peter Steinberger f9c721d5bf
fix: add vydra kling live lane 8 months ago
Peter Steinberger 7a736bff90
perf(test): split reply queue seams and unit shards 8 months ago
Peter Steinberger ec55902989
perf(test): tighten reply fast paths and split unit shards 8 months ago