Skip to content

Conversation

@seanmcguire12
Copy link
Member

@seanmcguire12 seanmcguire12 commented Dec 12, 2025

why

what changed

test plan


Summary by cubic

Allow act() cache hits even when variable values change by caching on variable keys and resolving values at execution time. Addresses STG-1065.

  • Bug Fixes
    • Cache key now uses sorted variableKeys, not variable values; entries store variableKeys.
    • Cache hit requires matching variable keys and provided values; logs a miss when values are missing.
    • Variables are passed into action execution and resolved at runtime; cached actions keep placeholder arguments.
    • Updated types to make variables optional and include variableKeys; write cache entries with variableKeys.

Written for commit 590fc8b. Summary will update automatically on new commits.

@changeset-bot
Copy link

changeset-bot bot commented Dec 12, 2025

🦋 Changeset detected

Latest commit: 590fc8b

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 3 packages
Name Type
@browserbasehq/stagehand Patch
@browserbasehq/stagehand-evals Patch
@browserbasehq/stagehand-server Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

@seanmcguire12
Copy link
Member Author

@greptileai

@greptile-apps
Copy link
Contributor

greptile-apps bot commented Dec 12, 2025

Greptile Overview

Greptile Summary

This PR enables act() cache hits even when variable values change by caching on variable keys instead of values and resolving values at execution time.

Key changes:

  • Cache key generation now uses sorted variable keys (variableKeys) instead of variable values, allowing cache hits when the same variables are used with different values
  • Variable substitution moved from getActionFromLLM to takeDeterministicAction, so cached actions store placeholder arguments (e.g., %username%) that are resolved at runtime
  • Added validation in cache replay to ensure all required variable keys are present with values before attempting replay
  • Updated types to reflect variableKeys as the stored cache property instead of full variable values

This is a well-structured change that improves cache efficiency for parameterized actions without compromising correctness.

Confidence Score: 5/5

  • This PR is safe to merge - it's a well-designed improvement to cache efficiency with proper validation.
  • The changes are logically sound and consistent. Variable keys are properly sorted before storage and comparison. The validation logic correctly ensures variable values are present before replay. The variable substitution is correctly deferred to execution time while preserving placeholder arguments in the cache.
  • No files require special attention.

Important Files Changed

File Analysis

Filename Score Overview
.changeset/fruity-badgers-sort.md 5/5 Standard changeset file documenting a patch release for allowing act() cache hits when variable values change.
packages/core/lib/v3/cache/ActCache.ts 5/5 Core cache changes: cache key now uses sorted variableKeys instead of values, adds validation for variable keys matching and value presence during replay, passes variables to action execution for runtime substitution.
packages/core/lib/v3/handlers/actHandler.ts 5/5 Deferred variable substitution: moved from getActionFromLLM to takeDeterministicAction; actions now store placeholder arguments in cache, resolved at execution time.
packages/core/lib/v3/types/private/cache.ts 5/5 Type updates: ActCacheContext now has variableKeys array (required) and variables (optional); CachedActEntry stores variableKeys instead of variable values.
packages/core/lib/v3/v3.ts 5/5 Pass variables to takeDeterministicAction for runtime substitution when acting on observe results.

Sequence Diagram

sequenceDiagram
    participant User
    participant V3
    participant ActCache
    participant ActHandler

    User->>V3: act("click %button%", {variables: {button: "submit"}})
    V3->>ActCache: prepareContext(instruction, page, variables)
    ActCache->>ActCache: Build cache key from instruction + URL + sorted variableKeys
    ActCache-->>V3: ActCacheContext {variableKeys: ["button"], variables: {button: "submit"}}
    
    V3->>ActCache: tryReplay(context, page)
    ActCache->>ActCache: Read cache entry
    ActCache->>ActCache: Validate variableKeys match
    ActCache->>ActCache: Validate all variable values present
    
    alt Cache Hit
        ActCache->>ActHandler: takeDeterministicAction(action, page, ..., variables)
        ActHandler->>ActHandler: substituteVariablesInArguments(%button% -> "submit")
        ActHandler->>ActHandler: Execute action with resolved args
        ActHandler-->>ActCache: ActResult
        ActCache-->>V3: Cached ActResult (with placeholder args preserved)
    else Cache Miss
        V3->>ActHandler: act(instruction, variables)
        ActHandler->>ActHandler: getActionFromLLM (returns placeholders)
        ActHandler->>ActHandler: takeDeterministicAction (resolves at execution)
        ActHandler-->>V3: ActResult
        V3->>ActCache: store(context, result)
        Note over ActCache: Stores variableKeys, not values
    end
    
    V3-->>User: ActResult
Loading

Copy link
Contributor

@greptile-apps greptile-apps bot left a comment

Choose a reason for hiding this comment

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

4 files reviewed, no comments

Edit Code Review Agent Settings | Greptile

@seanmcguire12 seanmcguire12 marked this pull request as ready for review December 16, 2025 00:19
Copy link
Contributor

@greptile-apps greptile-apps bot left a comment

Choose a reason for hiding this comment

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

4 files reviewed, no comments

Edit Code Review Agent Settings | Greptile

Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

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

No issues found across 5 files

@seanmcguire12 seanmcguire12 merged commit e822f5a into main Dec 16, 2025
20 checks passed
miguelg719 pushed a commit that referenced this pull request Dec 27, 2025
This PR was opened by the [Changesets
release](https://github.com/changesets/action) GitHub action. When
you're ready to do a release, you can merge this and the packages will
be published to npm automatically. If you're not ready to do a release
yet, that's fine, whenever you add more changesets to main, this PR will
be updated.


# Releases
## @browserbasehq/[email protected]

### Patch Changes

- [#1461](#1461)
[`0f3991e`](0f3991e)
Thanks [@tkattkat](https://github.com/tkattkat)! - Move hybrid mode out
of experimental

- [#1433](#1433)
[`e0e22e0`](e0e22e0)
Thanks [@tkattkat](https://github.com/tkattkat)! - Put hybrid mode
behind experimental

- [#1456](#1456)
[`f261051`](f261051)
Thanks [@shrey150](https://github.com/shrey150)! - Invoke page.hover for
agent move action

- [#1473](#1473)
[`e021674`](e021674)
Thanks [@shrey150](https://github.com/shrey150)! - Add safety
confirmation support for OpenAI + Google CUA

- [#1399](#1399)
[`6a5496f`](6a5496f)
Thanks [@tkattkat](https://github.com/tkattkat)! - Ensure cua agent is
killed when stagehand.close is called

- [#1436](#1436)
[`fea1700`](fea1700)
Thanks [@miguelg719](https://github.com/miguelg719)! - Fix auto-load key
for act/extract/observe parametrized models on api

- [#1439](#1439)
[`5b288d9`](5b288d9)
Thanks [@tkattkat](https://github.com/tkattkat)! - Remove base64 from
agent actions array ( still present in messages object )

- [#1408](#1408)
[`e822f5a`](e822f5a)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - allow for
act() cache hit when variable values change

- [#1472](#1472)
[`638efc7`](638efc7)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - fix: agent
cache not refreshed on action failure

- [#1424](#1424)
[`a890f16`](a890f16)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - fix:
"Error: -32000 Failed to convert response to JSON: CBOR: stack limit
exceeded"

- [#1418](#1418)
[`934f492`](934f492)
Thanks [@miguelg719](https://github.com/miguelg719)! - Cleanup handlers
and bus listeners on close

- [#1430](#1430)
[`bd2db92`](bd2db92)
Thanks [@shrey150](https://github.com/shrey150)! - Fix CUA model
coordinate translation

- [#1465](#1465)
[`51e0170`](51e0170)
Thanks [@miguelg719](https://github.com/miguelg719)! - Add media
resolution high provider option to gemini 3 hybrid agent

- [#1431](#1431)
[`05f5580`](05f5580)
Thanks [@tkattkat](https://github.com/tkattkat)! - Update the cache
handling for agent

- [#1432](#1432)
[`f56a9c2`](f56a9c2)
Thanks [@tkattkat](https://github.com/tkattkat)! - Deprecate cua: true
in favor of mode: "cua"

- [#1406](#1406)
[`b40ae11`](b40ae11)
Thanks [@tkattkat](https://github.com/tkattkat)! - Add support for
hovering with coordinates ( page.hover )

- [#1407](#1407)
[`0d2b398`](0d2b398)
Thanks [@tkattkat](https://github.com/tkattkat)! - Clean up page methods

- [#1412](#1412)
[`cd01f29`](cd01f29)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - fix: load
GOOGLE_API_KEY from .env

- [#1462](#1462)
[`a734fca`](a734fca)
Thanks [@shrey150](https://github.com/shrey150)! - fix: correctly pass
userDataDir to chrome launcher

- [#1466](#1466)
[`b342acf`](b342acf)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - move
playwright to optional dependencies

- [#1440](#1440)
[`2987cd1`](2987cd1)
Thanks [@tkattkat](https://github.com/tkattkat)! - [Feature] support
excluding tools from agent

- [#1455](#1455)
[`dfab1d5`](dfab1d5)
Thanks [@seanmcguire12](https://github.com/seanmcguire12)! - update
aisdk client to better enforce structured output with deepseek models

- [#1428](#1428)
[`4d71162`](4d71162)
Thanks [@tkattkat](https://github.com/tkattkat)! - Add "hybrid" mode to
stagehand agent

## @browserbasehq/[email protected]

### Minor Changes

- [#1459](#1459)
[`abb3469`](abb3469)
Thanks [@monadoid](https://github.com/monadoid)! - Added building of
binaries

- [#1457](#1457)
[`5fc1281`](5fc1281)
Thanks [@monadoid](https://github.com/monadoid)! - First changeset for
stagehand-server

- [#1469](#1469)
[`d634d45`](d634d45)
Thanks [@monadoid](https://github.com/monadoid)! - Bump to test binary
builds

### Patch Changes

- Updated dependencies
\[[`0f3991e`](0f3991e),
[`e0e22e0`](e0e22e0),
[`f261051`](f261051),
[`e021674`](e021674),
[`6a5496f`](6a5496f),
[`fea1700`](fea1700),
[`5b288d9`](5b288d9),
[`e822f5a`](e822f5a),
[`638efc7`](638efc7),
[`a890f16`](a890f16),
[`934f492`](934f492),
[`bd2db92`](bd2db92),
[`51e0170`](51e0170),
[`05f5580`](05f5580),
[`f56a9c2`](f56a9c2),
[`b40ae11`](b40ae11),
[`0d2b398`](0d2b398),
[`cd01f29`](cd01f29),
[`a734fca`](a734fca),
[`b342acf`](b342acf),
[`2987cd1`](2987cd1),
[`dfab1d5`](dfab1d5),
[`4d71162`](4d71162)]:
    -   @browserbasehq/[email protected]

## @browserbasehq/[email protected]

### Patch Changes

- [#1373](#1373)
[`cadd192`](cadd192)
Thanks [@tkattkat](https://github.com/tkattkat)! - Update screenshot
collector in agent evals cli

- Updated dependencies
\[[`0f3991e`](0f3991e),
[`e0e22e0`](e0e22e0),
[`f261051`](f261051),
[`e021674`](e021674),
[`6a5496f`](6a5496f),
[`fea1700`](fea1700),
[`5b288d9`](5b288d9),
[`e822f5a`](e822f5a),
[`638efc7`](638efc7),
[`a890f16`](a890f16),
[`934f492`](934f492),
[`bd2db92`](bd2db92),
[`51e0170`](51e0170),
[`05f5580`](05f5580),
[`f56a9c2`](f56a9c2),
[`b40ae11`](b40ae11),
[`0d2b398`](0d2b398),
[`cd01f29`](cd01f29),
[`a734fca`](a734fca),
[`b342acf`](b342acf),
[`2987cd1`](2987cd1),
[`dfab1d5`](dfab1d5),
[`4d71162`](4d71162)]:
    -   @browserbasehq/[email protected]

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants