Skip to content

feat(cli,sdk): compaction hook - #1420

Merged
ccurme (ccurme) merged 49 commits into
mainfrom
mdrxy/manual-summarize
Feb 27, 2026
Merged

feat(cli,sdk): compaction hook#1420
ccurme (ccurme) merged 49 commits into
mainfrom
mdrxy/manual-summarize

Conversation

@mdrxy

@mdrxy Mason Daugherty (mdrxy) commented Feb 19, 2026 •
edited
Loading

Copy link
Copy Markdown
Member

Add two paths for conversation compaction — a compact_conversation tool that the agent can invoke proactively, and a /compact slash command for manual use.

Both operate using SummarizationMiddleware internals, writing a summarization event into checkpointed state so older messages are virtually hidden without deletion.

Full history is written to backend storage before compaction (when possible).

@github-actions github-actions Bot added cli Related to `deepagents-cli` internal User is a member of the `langchain-ai` GitHub organization feature New feature/enhancement or request for one labels Feb 19, 2026
ccurme
ccurme (ccurme) reviewed Feb 19, 2026
View reviewed changes

@ccurme ccurme (ccurme) left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we provide any feedback to the model as to the percent of token budget used?

Might be worth an experiment, even without a working tool implementation, to see how / when it elects to compact.

Comment thread libs/cli/deepagents_cli/app.py Outdated
Comment thread libs/cli/deepagents_cli/compact_tool.py Outdated
Comment thread libs/cli/deepagents_cli/compact_tool.py Outdated
Comment thread libs/cli/deepagents_cli/compact_tool.py Outdated
@github-actions github-actions Bot added the deepagents Related to the `deepagents` SDK / agent harness label Feb 19, 2026
@mdrxy Mason Daugherty (mdrxy) changed the title feat(cli): manual compaction feat(cli,sdk): compaction hook Feb 19, 2026
@github-actions github-actions Bot added feature New feature/enhancement or request for one and removed feature New feature/enhancement or request for one labels Feb 19, 2026
@github-actions github-actions Bot added feature New feature/enhancement or request for one and removed feature New feature/enhancement or request for one labels Feb 19, 2026
@github-actions github-actions Bot added feature New feature/enhancement or request for one and removed feature New feature/enhancement or request for one labels Feb 19, 2026
@github-actions github-actions Bot added feature New feature/enhancement or request for one and removed feature New feature/enhancement or request for one labels Feb 20, 2026
ccurme
ccurme (ccurme) approved these changes Feb 27, 2026
View reviewed changes

@ccurme ccurme (ccurme) left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Excluded SummarizationToolMiddleware from default middleware stack until 0.5 release (needs testing in AB frontend).

@ccurme
ccurme (ccurme) merged commit e87cdad into main Feb 27, 2026
26 checks passed
@ccurme
ccurme (ccurme) deleted the mdrxy/manual-summarize branch February 27, 2026 03:29
@github-actions github-actions Bot mentioned this pull request Feb 27, 2026
Merged
james8814 pushed a commit to james8814/deepagents that referenced this pull request Mar 1, 2026
@mdrxy Developer
feat(cli,sdk): compaction hook (langchain-ai#1420)
1438afe
@mdrxy
Mason Daugherty (mdrxy) restored the mdrxy/manual-summarize branch March 2, 2026 14:55
@mdrxy
Mason Daugherty (mdrxy) deleted the mdrxy/manual-summarize branch March 2, 2026 14:57
@github-actions github-actions Bot added feature New feature/enhancement or request for one and removed feature New feature/enhancement or request for one labels Mar 2, 2026
@mdrxy Mason Daugherty (mdrxy) mentioned this pull request Mar 2, 2026
Merged
Mason Daugherty (mdrxy) added a commit that referenced this pull request Mar 2, 2026
@mdrxy
feat(cli): /compact command (#1579)
46e9e95 
Closes #1073
Finishes work started in #1420

---
@github-actions github-actions Bot added feature New feature/enhancement or request for one and removed feature New feature/enhancement or request for one labels Mar 2, 2026
Mason Daugherty (mdrxy) added a commit that referenced this pull request Mar 3, 2026
@github-actions @mdrxy
release(deepagents-cli): 0.0.26 (#1480)
e2724c4 
🤖 I have created a release *beep* *boop*
---


##
[0.0.26](deepagents-cli==0.0.25...deepagents-cli==0.0.26)
(2026-03-03)


### Features

* Compaction hook
([#1420](#1420))
([e87cdad](e87cdad))
* `/compact` command
([#1579](#1579))
([46e9e95](46e9e95))
* Add `--profile-override` CLI flag
([#1605](#1605))
([1984099](1984099))
* Add model profile overrides to config
([#1603](#1603))
([d3d6899](d3d6899))
* Show summarization status and notification
([#919](#919))
([2e3cb74](2e3cb74))

### Bug Fixes

* Fix image path pasting qualms
([#1560](#1560))
([8caaf3e](8caaf3e))
* Load `.agents` skill alias directories at interactive startup
([#1556](#1556))
([af0a759](af0a759))
* Coerce execute timeout to int before formatting tool display
([#1588](#1588))
([04b8c72](04b8c72)),
closes [#1586](#1586)
* Add missing flags to help screen
([#1619](#1619))
([6067749](6067749))
* Align compaction messaging across `/compact` and
`compact_conversation`
([#1583](#1583))
([d455a6b](d455a6b))
* Apply profile overrides in `/compact`
([#1612](#1612))
([a9dc2c5](a9dc2c5))
* Disambiguate `/tokens` vs `/compact` token reporting
([#1618](#1618))
([51c3347](51c3347))
* Make LangSmith URL lookups non-blocking
([#1595](#1595))
([572eaee](572eaee))
* Only exit input mode on backspace, not text clear
([#1479](#1479))
([da0965e](da0965e))
* Retry langsmith project url lookup until project exists
([#1562](#1562))
([e137a63](e137a63))
* Show model info in `/tokens` before first usage
([#1607](#1607))
([7b01ae7](7b01ae7))
* Support `timeout=0` for sandbox `execute()`
([#1558](#1558))
([ed14443](ed14443))
* Unreachable `except` block
([#1535](#1535))
([0e17e35](0e17e35))

### Performance Improvements

* Optimize thread resume path with prefetch and batched hydration
([#1561](#1561))
([068d112](068d112))
* Parallelize detection scripts for faster first-turn
([#1541](#1541))
([dad8b6e](dad8b6e))
* Speed up `/threads` first-open
([#1481](#1481))
([b248b15](b248b15))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
james8814 pushed a commit to james8814/deepagents that referenced this pull request Mar 6, 2026
@github-actions @mdrxy Developer
release(deepagents-cli): 0.0.26 (langchain-ai#1480)
affe906 
🤖 I have created a release *beep* *boop*
---


##
[0.0.26](langchain-ai/deepagents@deepagents-cli==0.0.25...deepagents-cli==0.0.26)
(2026-03-03)


### Features

* Compaction hook
([langchain-ai#1420](langchain-ai#1420))
([e87cdad](langchain-ai@e87cdad))
* `/compact` command
([langchain-ai#1579](langchain-ai#1579))
([46e9e95](langchain-ai@46e9e95))
* Add `--profile-override` CLI flag
([langchain-ai#1605](langchain-ai#1605))
([1984099](langchain-ai@1984099))
* Add model profile overrides to config
([langchain-ai#1603](langchain-ai#1603))
([d3d6899](langchain-ai@d3d6899))
* Show summarization status and notification
([langchain-ai#919](langchain-ai#919))
([2e3cb74](langchain-ai@2e3cb74))

### Bug Fixes

* Fix image path pasting qualms
([langchain-ai#1560](langchain-ai#1560))
([8caaf3e](langchain-ai@8caaf3e))
* Load `.agents` skill alias directories at interactive startup
([langchain-ai#1556](langchain-ai#1556))
([af0a759](langchain-ai@af0a759))
* Coerce execute timeout to int before formatting tool display
([langchain-ai#1588](langchain-ai#1588))
([04b8c72](langchain-ai@04b8c72)),
closes [langchain-ai#1586](langchain-ai#1586)
* Add missing flags to help screen
([langchain-ai#1619](langchain-ai#1619))
([6067749](langchain-ai@6067749))
* Align compaction messaging across `/compact` and
`compact_conversation`
([langchain-ai#1583](langchain-ai#1583))
([d455a6b](langchain-ai@d455a6b))
* Apply profile overrides in `/compact`
([langchain-ai#1612](langchain-ai#1612))
([a9dc2c5](langchain-ai@a9dc2c5))
* Disambiguate `/tokens` vs `/compact` token reporting
([langchain-ai#1618](langchain-ai#1618))
([51c3347](langchain-ai@51c3347))
* Make LangSmith URL lookups non-blocking
([langchain-ai#1595](langchain-ai#1595))
([572eaee](langchain-ai@572eaee))
* Only exit input mode on backspace, not text clear
([langchain-ai#1479](langchain-ai#1479))
([da0965e](langchain-ai@da0965e))
* Retry langsmith project url lookup until project exists
([langchain-ai#1562](langchain-ai#1562))
([e137a63](langchain-ai@e137a63))
* Show model info in `/tokens` before first usage
([langchain-ai#1607](langchain-ai#1607))
([7b01ae7](langchain-ai@7b01ae7))
* Support `timeout=0` for sandbox `execute()`
([langchain-ai#1558](langchain-ai#1558))
([ed14443](langchain-ai@ed14443))
* Unreachable `except` block
([langchain-ai#1535](langchain-ai#1535))
([0e17e35](langchain-ai@0e17e35))

### Performance Improvements

* Optimize thread resume path with prefetch and batched hydration
([langchain-ai#1561](langchain-ai#1561))
([068d112](langchain-ai@068d112))
* Parallelize detection scripts for faster first-turn
([langchain-ai#1541](langchain-ai#1541))
([dad8b6e](langchain-ai@dad8b6e))
* Speed up `/threads` first-open
([langchain-ai#1481](langchain-ai#1481))
([b248b15](langchain-ai@b248b15))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Marcelo5444 pushed a commit to Marcelo5444/deepagents that referenced this pull request Jul 30, 2026
@mdrxy
feat(cli,sdk): compaction hook (langchain-ai#1420)
b3026ca
Marcelo5444 pushed a commit to Marcelo5444/deepagents that referenced this pull request Jul 30, 2026
@mdrxy
feat(cli): /compact command (langchain-ai#1579)
f0afc51 
Closes langchain-ai#1073
Finishes work started in langchain-ai#1420

---
Marcelo5444 pushed a commit to Marcelo5444/deepagents that referenced this pull request Jul 30, 2026
@github-actions @mdrxy
release(deepagents-cli): 0.0.26 (langchain-ai#1480)
94c3506 
🤖 I have created a release *beep* *boop*
---


##
[0.0.26](langchain-ai/deepagents@deepagents-cli==0.0.25...deepagents-cli==0.0.26)
(2026-03-03)


### Features

* Compaction hook
([langchain-ai#1420](langchain-ai#1420))
([e87cdad](langchain-ai@e87cdad))
* `/compact` command
([langchain-ai#1579](langchain-ai#1579))
([46e9e95](langchain-ai@46e9e95))
* Add `--profile-override` CLI flag
([langchain-ai#1605](langchain-ai#1605))
([1984099](langchain-ai@1984099))
* Add model profile overrides to config
([langchain-ai#1603](langchain-ai#1603))
([d3d6899](langchain-ai@d3d6899))
* Show summarization status and notification
([langchain-ai#919](langchain-ai#919))
([2e3cb74](langchain-ai@2e3cb74))

### Bug Fixes

* Fix image path pasting qualms
([langchain-ai#1560](langchain-ai#1560))
([8caaf3e](langchain-ai@8caaf3e))
* Load `.agents` skill alias directories at interactive startup
([langchain-ai#1556](langchain-ai#1556))
([af0a759](langchain-ai@af0a759))
* Coerce execute timeout to int before formatting tool display
([langchain-ai#1588](langchain-ai#1588))
([04b8c72](langchain-ai@04b8c72)),
closes [langchain-ai#1586](langchain-ai#1586)
* Add missing flags to help screen
([langchain-ai#1619](langchain-ai#1619))
([6067749](langchain-ai@6067749))
* Align compaction messaging across `/compact` and
`compact_conversation`
([langchain-ai#1583](langchain-ai#1583))
([d455a6b](langchain-ai@d455a6b))
* Apply profile overrides in `/compact`
([langchain-ai#1612](langchain-ai#1612))
([a9dc2c5](langchain-ai@a9dc2c5))
* Disambiguate `/tokens` vs `/compact` token reporting
([langchain-ai#1618](langchain-ai#1618))
([51c3347](langchain-ai@51c3347))
* Make LangSmith URL lookups non-blocking
([langchain-ai#1595](langchain-ai#1595))
([572eaee](langchain-ai@572eaee))
* Only exit input mode on backspace, not text clear
([langchain-ai#1479](langchain-ai#1479))
([da0965e](langchain-ai@da0965e))
* Retry langsmith project url lookup until project exists
([langchain-ai#1562](langchain-ai#1562))
([e137a63](langchain-ai@e137a63))
* Show model info in `/tokens` before first usage
([langchain-ai#1607](langchain-ai#1607))
([7b01ae7](langchain-ai@7b01ae7))
* Support `timeout=0` for sandbox `execute()`
([langchain-ai#1558](langchain-ai#1558))
([ed14443](langchain-ai@ed14443))
* Unreachable `except` block
([langchain-ai#1535](langchain-ai#1535))
([0e17e35](langchain-ai@0e17e35))

### Performance Improvements

* Optimize thread resume path with prefetch and batched hydration
([langchain-ai#1561](langchain-ai#1561))
([068d112](langchain-ai@068d112))
* Parallelize detection scripts for faster first-turn
([langchain-ai#1541](langchain-ai#1541))
([dad8b6e](langchain-ai@dad8b6e))
* Speed up `/threads` first-open
([langchain-ai#1481](langchain-ai#1481))
([b248b15](langchain-ai@b248b15))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@ccurme ccurme (ccurme) ccurme approved these changes

Assignees

No one assigned

Labels

cli Related to `deepagents-cli` deepagents Related to the `deepagents` SDK / agent harness feature New feature/enhancement or request for one internal User is a member of the `langchain-ai` GitHub organization

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@mdrxy @ccurme