Skip to content

feat(memory): Add passive turn extraction #628

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dcramer wants to merge 13 commits into
base: main
Choose a base branch
from
Open

feat(memory): Add passive turn extraction #628

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
a8285ac
feat(memory): Add passive turn extraction
dcramer Jun 22, 2026
78aa416
fix(memory): Tighten passive extraction boundaries
dcramer Jun 22, 2026
bc79379
fix(memory): Normalize plugin source context
dcramer Jun 23, 2026
5fd6886
fix(memory): Tighten passive extraction QA
dcramer Jun 23, 2026
34f3660
fix(memory): Tighten passive observation inputs
dcramer Jun 23, 2026
24882f3
fix(memory): Preserve source across resumed runs
dcramer Jun 23, 2026
f2bca44
fix(dispatch): Parse legacy records with source
dcramer Jun 23, 2026
e1f97b5
test(oauth): Add source to pending resume fixture
dcramer Jun 23, 2026
b069491
fix(memory): Simplify memory extraction
dcramer Jun 23, 2026
6f70be8
fix(memory): Allow passive learning after recall tools
dcramer Jun 24, 2026
e3a5882
test(plugins): Align Slack source hook expectation
dcramer Jun 24, 2026
a8ea6f0
fix(plugins): Infer Slack source visibility
dcramer Jun 24, 2026
58e95fc
docs(memory): Specify plugin session tasks
dcramer Jun 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions packages/docs/src/content/docs/reference/config-and-env.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ related:
| `JUNIOR_SLASH_COMMAND` | No | Slack slash command for account-management flows. Defaults to `/jr`; the Slack app command must match this value. |
| `AI_MODEL` | No | Primary model selection override for main agent runs. Defaults to `openai/gpt-5.4`; Junior chooses the reasoning effort per run automatically. |
| `AI_FAST_MODEL` | No | Faster model for lightweight tasks and routing/classification passes before the main turn begins. Defaults to `openai/gpt-5.4-mini`. |
| `AI_MEMORY_MODEL` | No | Memory plugin extraction/review model override. When unset, memory uses the host structured-model default. |
| `AI_EMBEDDING_MODEL` | No | Embedding model for plugin-owned vector retrieval. Defaults to `openai/text-embedding-3-small`; memory v1 stores fixed 1536-dimensional vectors. |
| `AI_VISION_MODEL` | No | Dedicated image-understanding model; unset disables vision features. |
| `AI_WEB_SEARCH_MODEL` | No | Override for the `webSearch` tool model. Defaults to `openai/gpt-5.4`; does not fall through to `AI_MODEL`. |
Expand Down
1 change: 1 addition & 0 deletions packages/docs/src/content/docs/start-here/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,7 @@ Set these values before running real turns:
| `JUNIOR_SLASH_COMMAND` | No | Slack slash command name. Defaults to `/jr`. |
| `AI_MODEL` | No | Primary assistant model override. |
| `AI_FAST_MODEL` | No | Lightweight routing/classification model override. |
| `AI_MEMORY_MODEL` | No | Memory plugin extraction/review model override. |
| `AI_EMBEDDING_MODEL` | No | Embedding model override for plugin vector retrieval. |
| `AI_VISION_MODEL` | No | Enables image understanding when set. |
| `AI_WEB_SEARCH_MODEL` | No | Search model override. |
Expand Down
Loading
Loading