mirror of
https://github.com/langchain-ai/deepagentsjs.git
synced 2026-08-24 22:11:26 -04:00
@langchain/quickjs@0.6.1
210 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 github-actions[bot]
|
5af75fffbe |
chore: version packages (#726)
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 ## deepagents-acp@0.1.23 ### Patch Changes - Updated dependencies [[`590c2a5`](https://github.com/langchain-ai/deepagentsjs/commit/590c2a5042473f096d5fac5ddbb4be96e2ace0f2)]: - deepagents@1.12.2 ## deepagents@1.12.2 ### Patch Changes - [#723](https://github.com/langchain-ai/deepagentsjs/pull/723) [`590c2a5`](https://github.com/langchain-ai/deepagentsjs/commit/590c2a5042473f096d5fac5ddbb4be96e2ace0f2) Thanks [@thushanth-bengre-langchain](https://github.com/thushanth-bengre-langchain)! - fix(deepagents): prevent stack overflow in CompositeBackend grep/glob on huge result sets, and add a grep match-count cap `CompositeBackend` accumulated merged `ls`/`grep`/`glob` results with `push(...entries)`, which passes every entry as a separate function argument and overflows the call stack (RangeError: Maximum call stack size exceeded) when a broad search over a large tree returns hundreds of thousands of entries. Results are now accumulated with a plain loop, so no result-set size can overflow the stack. `grep` also gains an optional `maxCount` (backend) / `max_count` (tool) cap, mirroring the Python SDK. When the cap is hit, results are flagged `truncated: true` on `GrepResult`/`GlobResult` and the grep tool appends a note telling the model to narrow the search. The cap defaults to 1000 via the `grepMaxCount` middleware option (set to `null` to disable). `CompositeBackend` splits the budget across routed backends and OR-propagates the `truncated` flag on merged results. ## @deepagents/evals@0.0.22 ### Patch Changes - Updated dependencies [[`590c2a5`](https://github.com/langchain-ai/deepagentsjs/commit/590c2a5042473f096d5fac5ddbb4be96e2ace0f2)]: - deepagents@1.12.2 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
thushanth-bengre-langchain
|
590c2a5042 |
fix(deepagents): prevent stack overflow in CompositeBackend grep/glob (#723)
## Summary
- Fixes `RangeError: Maximum call stack size exceeded` from
`CompositeBackend.glob`/`grep` when a broad search (e.g.
`**/*.{ts,tsx,...}` at `/`) returns hundreds of thousands of entries.
Root cause: results were merged with `push(...entries)`, which passes
each entry as a separate function argument and overflows V8's
argument-stack limit. Now accumulated with a plain loop.
- Ports the Python SDK's grep match-count cap (`ef591e7`): optional
`maxCount` backend param / `max_count` tool arg, `grepMaxCount`
middleware option (default 1000, `null` disables), `truncated` flag on
`GrepResult`/`GlobResult`, and a truncation note in the grep tool
output. `CompositeBackend` splits the budget across routes and
OR-propagates `truncated`.
## Backward compatibility
- `truncated` is optional; `maxCount` defaults to unset everywhere. No
required changes for existing or new users.
## Test plan
- [x] Regression test: mocked backend returning 200k entries —
`glob`/`grep` complete without `RangeError` (verified it fails with the
old spread).
- [x] Cap enforcement, `truncated` propagation across composite routes,
middleware note rendering.
- [x] `pnpm test` (format + lint + all lib tests) passes.
|
||
|
github-actions[bot]
|
064b1724de |
chore: version packages (#715)
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 ## deepagents-acp@0.1.22 ### Patch Changes - Updated dependencies [[`ffec5de`](https://github.com/langchain-ai/deepagentsjs/commit/ffec5de0e66ed5ab64bc4c6bee2ff90effb4bfa1)]: - deepagents@1.12.1 ## deepagents@1.12.1 ### Patch Changes - [#713](https://github.com/langchain-ai/deepagentsjs/pull/713) [`ffec5de`](https://github.com/langchain-ai/deepagentsjs/commit/ffec5de0e66ed5ab64bc4c6bee2ff90effb4bfa1) Thanks [@gethin-langchain](https://github.com/gethin-langchain)! - fix(deepagents): grep/glob match when `path` points directly at a file ## @deepagents/evals@0.0.21 ### Patch Changes - Updated dependencies [[`ffec5de`](https://github.com/langchain-ai/deepagentsjs/commit/ffec5de0e66ed5ab64bc4c6bee2ff90effb4bfa1)]: - deepagents@1.12.1 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
gethin-langchain
|
ffec5de0e6 |
fix(deepagents): grep/glob match when path points directly at a file (#713)
## Summary - `grep`/`glob` on `StateBackend`/`StoreBackend` returned zero matches whenever `path` pointed at an exact file (no glob) — the shared `validatePath` helper forced a trailing `/` before prefix-matching, so a file's own key could never match itself+`/`. - Added a `filterFilesByPath` helper that checks for an exact key match in the files map first, falling back to the existing directory-prefix behavior otherwise. ## Test plan - [x] Added regression tests in `utils.test.ts`: exact-file path (no glob) for grep and glob, plus directory + glob/filename non-regression cases for both. - [x] `pnpm --filter deepagents test` — all tests pass. |
||
|
github-actions[bot]
|
bed2d344bc |
chore: version packages (#712)
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 ## deepagents@1.12.0 ### Minor Changes - [#703](https://github.com/langchain-ai/deepagentsjs/pull/703) [`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126) Thanks [@hntrl](https://github.com/hntrl)! - feat(deepagents): adopt more minimal prompting We've observed that current models don't need as verbose of prompting guidance, so we're reducing the amount of perscriptive guidance that deepagents has. This is reflected in the generic system prompt (which is now blank), and in the tool descriptions (which have been simplified). - [#708](https://github.com/langchain-ai/deepagentsjs/pull/708) [`1225a7f`](https://github.com/langchain-ai/deepagentsjs/commit/1225a7ff8673686c2a3c0411636a9511b7d8d0d0) Thanks [@hntrl](https://github.com/hntrl)! - feat(deepagents): make todo middleware opt-in - [#674](https://github.com/langchain-ai/deepagentsjs/pull/674) [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931) Thanks [@hntrl](https://github.com/hntrl)! - feat(filesystem): allow `write_file` to create missing files or completely replace existing files ## deepagents-acp@0.1.21 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`1225a7f`](https://github.com/langchain-ai/deepagentsjs/commit/1225a7ff8673686c2a3c0411636a9511b7d8d0d0), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0 ## @langchain/node-vfs@1.0.0 ### Patch Changes - [#674](https://github.com/langchain-ai/deepagentsjs/pull/674) [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931) Thanks [@hntrl](https://github.com/hntrl)! - fix: allow `VfsBackend.write` to overwrite existing files while continuing to reject symlinks ## @langchain/daytona@1.0.0 ## @langchain/deno@1.0.0 ## @langchain/modal@1.0.0 ## @langchain/quickjs@1.0.0 ## @langchain/sandbox-standard-tests@2.0.0 ## @deepagents/evals@0.0.20 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`1225a7f`](https://github.com/langchain-ai/deepagentsjs/commit/1225a7ff8673686c2a3c0411636a9511b7d8d0d0), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Hunter Lovell
|
b177148922 | chore: exit pre-release (#711) | ||
|
github-actions[bot]
|
149f4585f1 |
chore: version packages (rc) (#709)
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. ⚠️⚠️⚠️⚠️⚠️⚠️ `main` is currently in **pre mode** so this branch has prereleases rather than normal releases. If you want to exit prereleases, run `changeset pre exit` on `main`. ⚠️⚠️⚠️⚠️⚠️⚠️ # Releases ## deepagents@1.12.0-rc.1 ### Minor Changes - [#708](https://github.com/langchain-ai/deepagentsjs/pull/708) [`1225a7f`](https://github.com/langchain-ai/deepagentsjs/commit/1225a7ff8673686c2a3c0411636a9511b7d8d0d0) Thanks [@hntrl](https://github.com/hntrl)! - feat(deepagents): make todo middleware opt-in ## deepagents-acp@0.1.21-rc.1 ### Patch Changes - Updated dependencies [[`1225a7f`](https://github.com/langchain-ai/deepagentsjs/commit/1225a7ff8673686c2a3c0411636a9511b7d8d0d0)]: - deepagents@1.12.0-rc.1 ## @deepagents/evals@0.0.20-rc.1 ### Patch Changes - Updated dependencies [[`1225a7f`](https://github.com/langchain-ai/deepagentsjs/commit/1225a7ff8673686c2a3c0411636a9511b7d8d0d0)]: - deepagents@1.12.0-rc.1 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Hunter Lovell
|
1225a7ff86 |
feat(deepagents): make todo middleware opt-in (#708)
## Summary Makes `todoListMiddleware` opt-in. Default agents and default subagents no longer expose `write_todos` or the `todos` state channel, reducing the default tool surface while preserving explicit opt-in. ## Changes - Remove default todo middleware from the main, general-purpose, and declarative subagent stacks. - Preserve opt-in support through `middleware: [todoListMiddleware()]`; declarative subagents opt in through their own middleware. - Remove `write_todos` from always-present tool typing and built-in name-collision handling. - Update state and subagent documentation plus shared runtime assertions for the optional todo state/tool. ### Harness profiles and coverage - Re-add todo middleware in the Codex harness profile because its model-specific prompt requires `write_todos` - Apply profile `extraMiddleware` to subagent stacks, with profile factories creating fresh instances per stack. - Add coverage for default exclusion, explicit opt-in, main/GP/declarative isolation, profile middleware propagation, and type inference. |
||
|
github-actions[bot]
|
a55022dc2f |
chore: version packages (rc) (#699)
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. ⚠️⚠️⚠️⚠️⚠️⚠️ `main` is currently in **pre mode** so this branch has prereleases rather than normal releases. If you want to exit prereleases, run `changeset pre exit` on `main`. ⚠️⚠️⚠️⚠️⚠️⚠️ # Releases ## deepagents@1.12.0-rc.0 ### Minor Changes - [#703](https://github.com/langchain-ai/deepagentsjs/pull/703) [`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126) Thanks [@hntrl](https://github.com/hntrl)! - feat(deepagents): adopt more minimal prompting We've observed that current models don't need as verbose of prompting guidance, so we're reducing the amount of perscriptive guidance that deepagents has. This is reflected in the generic system prompt (which is now blank), and in the tool descriptions (which have been simplified). - [#674](https://github.com/langchain-ai/deepagentsjs/pull/674) [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931) Thanks [@hntrl](https://github.com/hntrl)! - feat(filesystem): allow `write_file` to create missing files or completely replace existing files ## deepagents-acp@0.1.21-rc.0 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 ## @langchain/daytona@1.0.0-rc.0 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 ## @langchain/deno@1.0.0-rc.0 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 ## @langchain/modal@1.0.0-rc.0 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 ## @langchain/node-vfs@1.0.0-rc.0 ### Patch Changes - [#674](https://github.com/langchain-ai/deepagentsjs/pull/674) [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931) Thanks [@hntrl](https://github.com/hntrl)! - fix: allow `VfsBackend.write` to overwrite existing files while continuing to reject symlinks - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 ## @langchain/quickjs@1.0.0-rc.0 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 ## @langchain/sandbox-standard-tests@2.0.0-rc.0 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 ## @deepagents/evals@0.0.20-rc.0 ### Patch Changes - Updated dependencies [[`d25097f`](https://github.com/langchain-ai/deepagentsjs/commit/d25097f78d0e66741da34e1d74551f3c19991126), [`dd142fe`](https://github.com/langchain-ai/deepagentsjs/commit/dd142fe4fc54c986d5bcf51211d9a839a427e931)]: - deepagents@1.12.0-rc.0 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Hunter Lovell
|
d25097f78d |
feat(deepagents): simplify prompting (#703)
## Summary The SDK currently ships authored base prose plus middleware guidance that largely duplicates the tool schemas. This change adopts a more lean default: no authored base prompt, no duplicate built-in usage prose, and concise tool descriptions. Skills, memory, custom system prompts, custom tool descriptions, and required filesystem routing context remain intact. The legacy base-prompt surface is removed rather than preserved as a default path. ## Changes ### Default prompt - Remove the authored default base prompt and its obsolete public surface. - Suppress LangChain's default todo middleware prompt while leaving deepagents-owned middleware prompt-free by default. - Remove unused filesystem, subagent, async-subagent, and execution prompt constants and exports. ### Durable tool guidance - Keep large-result recovery guidance in `read_file` and `grep` descriptions. - Keep async task status freshness guidance in `check_async_task` and `list_async_tasks` descriptions. - Trim filesystem and task descriptions to their purpose and load-bearing constraints. - Build grep and execute descriptions from the configured filesystem tool set so they do not recommend unavailable tools. ### Token impact Offline (`o200k_base`, default-agent tool schemas): | Tool | Before | After | Delta | | --- | ---: | ---: | ---: | | `task` | 1,664 | 389 | -77% | | `read_file` | 728 | 494 | -32% | | `grep` | 688 | 555 | -19% | | `edit_file` | 273 | 257 | -6% | | `glob` | 217 | 172 | -21% | | `write_file` | 177 | 177 | — | | `delete` | 146 | 146 | — | | `ls` | 111 | 111 | — | | **Total** | **4,005** | **2,302** | **-43%** | For a default-agent `hello` turn, input tokens drop from 5,395 to 1,895 (-65%). ### Evaluation results The lean prompt matched the baseline on correctness (0.81) and solve rate (0.635 vs. 0.634). Unified evaluation macro and micro scores improved from 0.413 to 0.437 and from 0.371 to 0.394, respectively. (see more detailed results in https://github.com/langchain-ai/deepagents/pull/5009 and https://github.com/langchain-ai/deepagents/pull/4859) |
||
|
Hunter Lovell
|
ef794da80b | chore: rc pre-release (#701) | ||
|
Hunter Lovell
|
dd142fe4fc |
feat(deepagents): allow write_file to overwrite files (#674)
## Summary `write_file` now creates missing files and replaces existing files entirely, removing the previous create-only error path while preserving write permissions and symlink protections. ## Changes ### deepagents filesystem backends - Updated `FilesystemBackend`, `StateBackend`, `StoreBackend`, `BaseSandbox`, and `node-vfs` write behavior to allow full-file replacement on existing paths. - Preserved path safety and symlink protections in filesystem-backed writes. - Removed the sandbox existence precheck so writes rely on the upload/write transport. ### Tool prompts and examples - Aligned the `write_file` tool description and schema text with the Python SDK wording. - Updated sandbox example prompts so `write_file` is described as creating or fully replacing files. ### Tests and evals - Updated backend, middleware, and shared sandbox standard tests that previously expected an existing-file error. - Added overwrite coverage for filesystem, sandbox, state, store, middleware, node-vfs, and file-operation evals. ### Release - Added a changeset for `deepagents` documenting the new overwrite behavior. |
||
|
github-actions[bot]
|
60e32118b0 |
chore: version packages (#694)
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 ## deepagents-acp@0.1.20 ### Patch Changes - Updated dependencies [[`2ebb178`](https://github.com/langchain-ai/deepagentsjs/commit/2ebb1785e4625ecf82635582e17fe41fbfbac603)]: - deepagents@1.11.1 ## deepagents@1.11.1 ### Patch Changes - [#693](https://github.com/langchain-ai/deepagentsjs/pull/693) [`2ebb178`](https://github.com/langchain-ai/deepagentsjs/commit/2ebb1785e4625ecf82635582e17fe41fbfbac603) Thanks [@colifran](https://github.com/colifran)! - fix(deepagents): return recoverable errors for invalid/denied filesystem tool paths instead of throwing ## @deepagents/evals@0.0.19 ### Patch Changes - Updated dependencies [[`2ebb178`](https://github.com/langchain-ai/deepagentsjs/commit/2ebb1785e4625ecf82635582e17fe41fbfbac603)]: - deepagents@1.11.1 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Colin Francis
|
2ebb1785e4 |
fix(deepagents): return recoverable errors for invalid/denied filesystem tool paths instead of throwing (#693)
### Summary Invalid (non-absolute, `..`, or `~`) or denied filesystem paths passed by an agent cause the tool to throw which raises a `MiddlewareError` and causes the whole agent run to crash. This PR replaces `enforcePermission` which was re-validating the path without a try/catch with `checkPermission` which returns the error to the model as a normal tool result so the model can correct the path and try again instead of crashing. ### Tests Updated the three permission suites to assert an error result instead of a throw and added a regression block for `~`/relative/`..` paths that returns a recoverable error and never calls the backend. |
||
|
github-actions[bot]
|
f127e3d442 |
chore: version packages (#676)
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 ## deepagents@1.11.0 ### Minor Changes - [#671](https://github.com/langchain-ai/deepagentsjs/pull/671) [`6ae9d1e`](https://github.com/langchain-ai/deepagentsjs/commit/6ae9d1eab92131ea9cfd7bef024cf1ab343641ea) Thanks [@hntrl](https://github.com/hntrl)! - feat(filesystem): add allowlist for filesystem middleware tools - [#669](https://github.com/langchain-ai/deepagentsjs/pull/669) [`4643148`](https://github.com/langchain-ai/deepagentsjs/commit/4643148e8b64c796d3144210bac3ad1c6f5b2091) Thanks [@hntrl](https://github.com/hntrl)! - feat(deepagents): add structured system prompt configuration - [#673](https://github.com/langchain-ai/deepagentsjs/pull/673) [`eb18c70`](https://github.com/langchain-ai/deepagentsjs/commit/eb18c70d8d0871bc72aeb8be6581a98506829c6f) Thanks [@hntrl](https://github.com/hntrl)! - feat(backends): add delete protocol support Adds a `DeleteResult` type and optional backend `delete` method, preserves delete through backend protocol adaptation, and implements file deletion across the built-in state, store, filesystem, composite, context hub, sandbox, and node-vfs backends. ### Patch Changes - [#691](https://github.com/langchain-ai/deepagentsjs/pull/691) [`39a7049`](https://github.com/langchain-ai/deepagentsjs/commit/39a7049e4dbf99a31223c4e31cf79a2ed5115634) Thanks [@colifran](https://github.com/colifran)! - fix(deepagents): backend adapter drops route prefixes - [#672](https://github.com/langchain-ai/deepagentsjs/pull/672) [`cc26c41`](https://github.com/langchain-ai/deepagentsjs/commit/cc26c41df2851acacc86a743878b5c847a8f5d59) Thanks [@hntrl](https://github.com/hntrl)! - fix(deepagents): allow custom middleware to replace defaults by name ## deepagents-acp@0.1.19 ### Patch Changes - Updated dependencies [[`39a7049`](https://github.com/langchain-ai/deepagentsjs/commit/39a7049e4dbf99a31223c4e31cf79a2ed5115634), [`6ae9d1e`](https://github.com/langchain-ai/deepagentsjs/commit/6ae9d1eab92131ea9cfd7bef024cf1ab343641ea), [`cc26c41`](https://github.com/langchain-ai/deepagentsjs/commit/cc26c41df2851acacc86a743878b5c847a8f5d59), [`4643148`](https://github.com/langchain-ai/deepagentsjs/commit/4643148e8b64c796d3144210bac3ad1c6f5b2091), [`eb18c70`](https://github.com/langchain-ai/deepagentsjs/commit/eb18c70d8d0871bc72aeb8be6581a98506829c6f)]: - deepagents@1.11.0 ## @langchain/node-vfs@0.2.1 ### Patch Changes - [#673](https://github.com/langchain-ai/deepagentsjs/pull/673) [`eb18c70`](https://github.com/langchain-ai/deepagentsjs/commit/eb18c70d8d0871bc72aeb8be6581a98506829c6f) Thanks [@hntrl](https://github.com/hntrl)! - feat(backends): add delete protocol support Adds a `DeleteResult` type and optional backend `delete` method, preserves delete through backend protocol adaptation, and implements file deletion across the built-in state, store, filesystem, composite, context hub, sandbox, and node-vfs backends. ## @deepagents/evals@0.0.18 ### Patch Changes - Updated dependencies [[`39a7049`](https://github.com/langchain-ai/deepagentsjs/commit/39a7049e4dbf99a31223c4e31cf79a2ed5115634), [`6ae9d1e`](https://github.com/langchain-ai/deepagentsjs/commit/6ae9d1eab92131ea9cfd7bef024cf1ab343641ea), [`cc26c41`](https://github.com/langchain-ai/deepagentsjs/commit/cc26c41df2851acacc86a743878b5c847a8f5d59), [`4643148`](https://github.com/langchain-ai/deepagentsjs/commit/4643148e8b64c796d3144210bac3ad1c6f5b2091), [`eb18c70`](https://github.com/langchain-ai/deepagentsjs/commit/eb18c70d8d0871bc72aeb8be6581a98506829c6f)]: - deepagents@1.11.0 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Colin Francis
|
39a7049e4d |
fix(deepagents): backend adapter drops route prefixes (#691)
### Summary `adaptBackendProtocol` rebuilds the backend into a v2 backend protocol but drops its `routePrefixes`. Since `resolveBackend` runs every backend through the adapter, a resolved `CompositeBackend` was no longer detected as composite. That made the execute tool's guard fail at invocation and disable the execute tool even when filesystem permissions were correctly scoped to composite routes. This PR fixes this by forwarding `routePrefixes` through `adaptBackendProtocol` instead of dropping them. ### Tests Added unit tests in backends/utils.test.ts to verify that `routePrefixes` is forwarded through `adaptBackendProtocol` and `adaptSandboxProtocol` and not added for non-composite backends. |
||
|
Hunter Lovell
|
cc26c41df2 |
fix(deepagents): merge custom middleware by name (#672)
## Summary Adds middleware override behavior to replace default middleware by `.name` instead of always being appended. ## Changes - Add name-keyed middleware merging so custom middleware replaces matching default middleware in-place and appends novel middleware after the core stack. - Apply default-slot middleware overrides consistently when constructing main-agent and subagent middleware stacks, while preventing parent-only middleware from propagating unless it matches a subagent default slot. - Move harness tool exclusion into a private `_ToolExclusionMiddleware` helper so excluded tools are stripped after tool-injecting middleware has run. - Add coverage for main-agent replacement, subagent/default override propagation, parent-only middleware isolation, profile exclusions, tool-exclusion ordering, and merge precedence. |
||
|
Hunter Lovell
|
f09bc61d7a |
feat(deepagents): implement delete across backends (#680)
## Summary Implements the optional backend `delete` protocol across the built-in backend implementations now that the delete protocol surface is available. This keeps delete behavior backend-local and does not expose a new filesystem tool to agents. ## Changes ### deepagents - Implements `delete(filePath)` for filesystem, store, composite, context hub, and sandbox backends. - Uses backend-specific safety semantics: filesystem deletion goes through existing path resolution and only unlinks files, store deletion treats paths as exact keys, context hub deletion commits null entries, and sandbox deletion uses shell-quoted `rm -f`. - Adds tests covering successful deletion, missing paths, directory rejection where applicable, composite route path restoration, store wildcard literal behavior, and context hub cache updates/failure handling. ### @langchain/node-vfs - Implements `delete(filePath)` for the VFS backend. - Adds tests for file deletion, missing paths, directory rejection, and preserving non-target files. |
||
|
Hunter Lovell
|
6ae9d1eab9 |
feat(deepagents): add filesystem tool allowlist (#671)
## Summary Adds a `tools` allowlist option to `createFilesystemMiddleware` so callers can restrict which built-in filesystem tools are exposed to the model. The middleware now builds the filesystem system prompt from the tools that are actually visible on the request, avoiding instructions for tools that were filtered by the allowlist or backend capability checks. ## Changes - Adds a public `FsToolName` type and `tools` option to `FilesystemMiddlewareOptions`. - Filters filesystem middleware tools at construction time when an explicit allowlist is provided, while preserving existing `execute` backend capability filtering. - Requires `read_file` in explicit allowlists because it is needed for filesystem workflows and large-result recovery. - Generates the filesystem tool prompt dynamically from visible filesystem tools, and only appends execute-specific instructions when `execute` is actually available. - Adds unit and integration coverage for allowlist behavior, prompt filtering, unsupported `execute`, and user-provided non-filesystem tools. |
||
|
Hunter Lovell
|
eb18c70d8d |
feat(deepagents): add delete protocol support (#673)
## Summary
Adds protocol-level delete support for deepagents backends.
## Changes
### deepagents
- Adds `DeleteResult` to the backend protocol exports.
- Adds optional `delete(filePath)` support to v1 and v2 backend
protocols.
- Preserves optional delete implementations when adapting backends to
the v2 protocol.
- Implements `StateBackend.delete()` for zero-argument StateBackend
instances by sending `{ [filePath]: null }` through `__pregel_send`.
- Adds a changeset for the new backend protocol capability.
|
||
|
Hunter Lovell
|
4643148e8b |
feat(deepagents): add structured system prompt configuration (#669)
## Summary Ports the system prompt configuration in langchain-ai/deepagents#4437 |
||
|
github-actions[bot]
|
4507acd92e |
chore: version packages (#670)
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 ## deepagents-acp@0.1.18 ### Patch Changes - Updated dependencies [[`7c8a770`](https://github.com/langchain-ai/deepagentsjs/commit/7c8a770fac90fd50dfe08af67a0ce073a33e4ef7)]: - deepagents@1.10.8 ## deepagents@1.10.8 ### Patch Changes - [#668](https://github.com/langchain-ai/deepagentsjs/pull/668) [`7c8a770`](https://github.com/langchain-ai/deepagentsjs/commit/7c8a770fac90fd50dfe08af67a0ce073a33e4ef7) Thanks [@colifran](https://github.com/colifran)! - fix(deepagents): fast-glob follows directory symlink cycles leading to ELOOP crashes ## @deepagents/evals@0.0.17 ### Patch Changes - Updated dependencies [[`7c8a770`](https://github.com/langchain-ai/deepagentsjs/commit/7c8a770fac90fd50dfe08af67a0ce073a33e4ef7)]: - deepagents@1.10.8 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Colin Francis
|
7c8a770fac |
fix(deepagents): fast-glob follows directory symlink cycles leading to ELOOP crashes (#668)
### Summary `fast-glob` follows symbolic links by default so the `glob`/`grep` tools in `FilesystemBackend` and `LocalShellBackend` walked directory symlink cycles recursively causing `ELOOP` crashes. and aborted the run over a target repo. This PR fixes by adding`followSymbolicLinks: false` to all four `fast-glob` calls. Bonus: this keeps traversal inside the search root. ### Tests Unit tests in `filesystem.test.ts` and `local-shell.test.ts` verifying that a `sub/sub -> .` cycle now traverses cleanly without traversing symlinks. This is an upstream fix for: https://github.com/langchain-ai/openwiki/issues/72 |
||
|
github-actions[bot]
|
3eab2cad6f |
chore: version packages (#660)
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 ## deepagents-acp@0.1.17 ### Patch Changes - Updated dependencies [[`8efde93`](https://github.com/langchain-ai/deepagentsjs/commit/8efde93792dfc324e70b441eacbb810532f347c4)]: - deepagents@1.10.7 ## deepagents@1.10.7 ### Patch Changes - [#659](https://github.com/langchain-ai/deepagentsjs/pull/659) [`8efde93`](https://github.com/langchain-ai/deepagentsjs/commit/8efde93792dfc324e70b441eacbb810532f347c4) Thanks [@Kowshik4593](https://github.com/Kowshik4593)! - Fix: Normalize `path` to `file_path` in filesystem tools (`read_file`, `write_file`, and `edit_file`) and align the prompt documentation examples to prevent validation schema failures on weaker/custom models. ## @deepagents/evals@0.0.16 ### Patch Changes - Updated dependencies [[`8efde93`](https://github.com/langchain-ai/deepagentsjs/commit/8efde93792dfc324e70b441eacbb810532f347c4)]: - deepagents@1.10.7 --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Colin Francis <colin.francis@langchain.dev> |
||
|
Kowshik Padala
|
8efde93792 |
feat(deepagents): implement filesystem state management middleware with atomic update support and testing (#659)
## Problem Addresses #658. When using weaker or custom LLMs (e.g., smaller open-source models) in `deepagents` and consumers like `openwiki`, the agent immediately crashes with a schema validation error on the first filesystem tool call: This occurs because: 1. `ls` defines its directory argument as `path`, but `read_file`, `write_file`, and `edit_file` expect `file_path`. Models often default to `path` across all filesystem tools. 2. The description prompt examples in `fs.ts` and `skills.ts` show `read_file(path, ...)`, instructing models to use the wrong parameter name. ## Proposed Changes This PR solves both prompt inconsistencies and schema validation failures with a fully backward-compatible input normalization helper: 1. **Prompt Alignment**: Fixed references in `fs.ts` and `skills.ts` to instruct the model to use `file_path` (aligned with the prompt fixes in #644). 2. **Schema Input Normalization**: Added a `normalizeFilePathInput` preprocessor helper to the `read_file`, `write_file`, and `edit_file` Zod schemas using `z.preprocess`. This dynamically maps the `path` key to `file_path` if the model still passes `path`. ## Verification & Tests - Added unit tests in `fs.test.ts` to assert that: - `path` parameter normalization maps correctly to `file_path` for `read_file`, `write_file`, and `edit_file`. - All instruction examples contain only valid schema fields. - Verified that `zod-to-json-schema` unwraps the `z.preprocess` layer perfectly, preserving the original schema descriptions and definitions sent to the LLM. - Ran all filesystem tests successfully (`npx vitest run src/middleware/fs.test.ts` passes). |
||
|
github-actions[bot]
|
ff8cc5c4b4 |
chore: version packages (#607)
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 ## @langchain/quickjs@0.6.0 ### Minor Changes - [#606](https://github.com/langchain-ai/deepagentsjs/pull/606) [`3c8f8b2`](https://github.com/langchain-ai/deepagentsjs/commit/3c8f8b2ea6f0204353c63bf49c3fdc6655bf1069) Thanks [@colifran](https://github.com/colifran)! - chore(quickjs): disallow task as a configurable ptc tool ## deepagents-acp@0.1.16 ### Patch Changes - Updated dependencies [[`d7ecab2`](https://github.com/langchain-ai/deepagentsjs/commit/d7ecab2d9f9d41321a043eed6edc3366a1381a67), [`1a2b2df`](https://github.com/langchain-ai/deepagentsjs/commit/1a2b2df5528f0f61870b054fff8291355f6a2a0b), [`42f34b6`](https://github.com/langchain-ai/deepagentsjs/commit/42f34b65ededf4a1fbf3cd4bbff486ddfeb320e9), [`0ae10d7`](https://github.com/langchain-ai/deepagentsjs/commit/0ae10d7e26c84203a5273939c9ad7a9c8c8661c6)]: - deepagents@1.10.6 ## deepagents@1.10.6 ### Patch Changes - [#608](https://github.com/langchain-ai/deepagentsjs/pull/608) [`d7ecab2`](https://github.com/langchain-ai/deepagentsjs/commit/d7ecab2d9f9d41321a043eed6edc3366a1381a67) Thanks [@aolsenjazz](https://github.com/aolsenjazz)! - fix(deepagents): forward subagent results as text Fixed a 400 `invalid_request_error` that occurred when a subagent used an Anthropic server-side tool (web search, web fetch, or code execution): the subagent's `server_tool_use`/`*_tool_result` blocks were forwarded to the parent agent as `tool_result` content, which the API rejects. Subagent results are now passed back to the parent as their text content (matching the Python implementation), which resolves the error and also handles a trailing empty `end_turn` message. - [#656](https://github.com/langchain-ai/deepagentsjs/pull/656) [`1a2b2df`](https://github.com/langchain-ai/deepagentsjs/commit/1a2b2df5528f0f61870b054fff8291355f6a2a0b) Thanks [@colifran](https://github.com/colifran)! - fix(deepagents): default unknown file extensions to text/plain - [#611](https://github.com/langchain-ai/deepagentsjs/pull/611) [`42f34b6`](https://github.com/langchain-ai/deepagentsjs/commit/42f34b65ededf4a1fbf3cd4bbff486ddfeb320e9) Thanks [@aolsenjazz](https://github.com/aolsenjazz)! - feat(deepagents): add bedrockPromptCachingMiddleware to default stack Add bedrockPromptCachingMiddleware to default middleware stack. This automatically opts-in to Bedrock prompt caching for Nova and Anthropic models - [#613](https://github.com/langchain-ai/deepagentsjs/pull/613) [`0ae10d7`](https://github.com/langchain-ai/deepagentsjs/commit/0ae10d7e26c84203a5273939c9ad7a9c8c8661c6) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(deepagents): declare LangChain runtime packages as peer dependencies Move `@langchain/core`, `@langchain/langgraph`, `@langchain/langgraph-sdk`, and `langchain` from `dependencies` to `peerDependencies`, and also declare `@langchain/langgraph-checkpoint` as a peer (its `BaseCheckpointSaver`/`BaseStore` types are part of the public API), so they resolve to a single shared instance in the consumer's tree. Previously they were bundled as regular dependencies, which let a consumer end up with two copies of `@langchain/core` (e.g. `1.2.0` vs `1.2.1`). Because these packages ship classes with private/ protected fields, the duplicate copies are treated as nominally distinct types, producing errors like passing a `ChatOpenAI` model to `createDeepAgent` or a compiled graph to the local protocol helpers. As peers, the app controls the version and bumping `@langchain/core` no longer requires a `deepagents` release. ## @langchain/daytona@0.2.1 ### Patch Changes - [#614](https://github.com/langchain-ai/deepagentsjs/pull/614) [`5b462f2`](https://github.com/langchain-ai/deepagentsjs/commit/5b462f2ab2400fba52906e8f1485a500ec5b6e17) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Replace deprecated `@daytonaio/sdk` dependency with `@daytona/sdk`. ## @langchain/modal@0.1.5 ### Patch Changes - [#657](https://github.com/langchain-ai/deepagentsjs/pull/657) [`5f93c11`](https://github.com/langchain-ai/deepagentsjs/commit/5f93c114759399002a3981a93e3df13981514b1d) Thanks [@colifran](https://github.com/colifran)! - fix(modal): modal low level file handle api `sandbox.open` has been removed ## @deepagents/evals@0.0.15 ### Patch Changes - Updated dependencies [[`d7ecab2`](https://github.com/langchain-ai/deepagentsjs/commit/d7ecab2d9f9d41321a043eed6edc3366a1381a67), [`1a2b2df`](https://github.com/langchain-ai/deepagentsjs/commit/1a2b2df5528f0f61870b054fff8291355f6a2a0b), [`42f34b6`](https://github.com/langchain-ai/deepagentsjs/commit/42f34b65ededf4a1fbf3cd4bbff486ddfeb320e9), [`0ae10d7`](https://github.com/langchain-ai/deepagentsjs/commit/0ae10d7e26c84203a5273939c9ad7a9c8c8661c6)]: - deepagents@1.10.6 --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Colin Francis <colin.francis@langchain.dev> |
||
|
Colin Francis
|
1a2b2df552 |
fix(deepagents): default unknown file extensions to text/plain (#656)
### Summary `read_file` couldn't read many common text files and with Anthropic it crashes the whole run. `getMimeType()` mapped any unrecognized extension to `application/octet-stream`, which `isTextMimeType()` treats as binary, so the file got base64-encoded into a document block. This defaults unknown extensions to `text/plain` instead. Known binaries (images, audio, video, PDF/PPT) stay explicitly mapped, so image and PDF handling is unchanged. Files like `.properties`, `.scss`, `.tf`, `.lock`, and extension-less files like `Dockerfile` now read as text. ### Tests Flipped the unknown-extension unit test to expect `text/plain`. |
||
|
Colin Francis
|
5f93c11475 |
fix(modal): modal sandboxes fail to upload files (#657)
### Summary Modal v0.8.0 released the following breaking change: ``` Breaking: Removed the deprecated low-level file-handle API: Sandbox.Open / SandboxFile (Go), and sandbox.open / SandboxFile (JS). Use the Sandbox Filesystem API instead: sandbox.Filesystem() (Go) / sandbox.filesystem (JS). ``` Ref: https://github.com/modal-labs/modal-client/blob/main/CHANGELOG_GO_JS.md This PR updates our implementation to use the sandbox filesystem api ### Tests Updated `sandbox.test.ts` mocks to model `sandbox.filesystem` |
||
|
Christian Bromann
|
5b462f2ab2 |
fix: migrate Daytona SDK dependency [closes #609] (#614)
## Description Closes #609 by updating `@langchain/daytona` to the maintained `@daytona/sdk` at `^0.184.0` while preserving the same SDK API usage. Added a patch changeset; `@daytona/sdk` is Apache-2.0 and maintained by Daytona as the direct replacement for deprecated `@daytonaio/sdk`. ## Self-Hosted Release Note `@langchain/daytona` now depends on `@daytona/sdk` instead of deprecated `@daytonaio/sdk`. ## Test Plan - [ ] Verify package publish metadata resolves `@daytona/sdk` `^0.184.0`. Made by [Open SWE](https://openswe.vercel.app/agents/d6f434c5-39c6-eef7-6cc6-670cf092bb67) Co-authored-by: Christian Bromann <731337+christian-bromann@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Christian Bromann
|
0ae10d7e26 |
fix(deepagents): declare LangChain runtime packages as peer dependencies (#613)
Updates to `@langchain/core` can cause downstream friction with
TypeScript:
```
Type 'ChatOpenAI<ChatOpenAICallOptions>' is not assignable to type 'string | BaseLanguageModel<any, BaseLanguageModelCallOptions> | undefined'.
Type 'ChatOpenAI<ChatOpenAICallOptions>' is not assignable to type 'BaseLanguageModel<any, BaseLanguageModelCallOptions>'.
Types of property 'getGraph' are incompatible.
Type '(_?: import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/runnables/types").RunnableConfig<Record<string, any>> | undefined) => import("/Users/christian.bromann/Sites/L...' is not assignable to type '(_?: import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/runnables/types").RunnableConfig<Record<string, any>> | undefined) => import("/Users/christian.bromann/Sites/L...'.
Types of parameters '_' and '_' are incompatible.
Type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/runnables/types").RunnableConfig<Record<string, any>> | undefined' is not assignable to type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/runnables/types").RunnableConfig<Record<string, any>> | undefined'.
Type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/runnables/types").RunnableConfig<Record<string, any>>' is not assignable to type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/runnables/types").RunnableConfig<Record<string, any>>'.
Types of property 'callbacks' are incompatible.
Type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").Callbacks | undefined' is not assignable to type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").Callbacks | undefined'.
Type 'CallbackManager' is not assignable to type 'Callbacks | undefined'.
Type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManager' is not assignable to type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManager'.
The types returned by 'handleLLMStart(...)' are incompatible between these types.
Type 'Promise<import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManagerForLLMRun[]>' is not assignable to type 'Promise<import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManagerForLLMRun[]>'.
Type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManagerForLLMRun[]' is not assignable to type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManagerForLLMRun[]'.
Type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.0_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManagerForLLMRun' is not assignable to type 'import("/Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith/node_modules/.pnpm/@langchain+core@1.2.1_openai@6.44.0_ws@8.21.0_zod@4.4.3__ws@8.21.0/node_modules/@langchain/core/dist/callbacks/manager").CallbackManagerForLLMRun'.
Property 'inheritableHandlers' is protected but type 'BaseRunManager' is not a class derived from 'BaseRunManager'.ts(2322)
```
to avoid this we should move the LangChain dependency to become peer
deps.
- Moved `@langchain/core`, `@langchain/langgraph`,
`@langchain/langgraph-sdk`, and `langchain` from `dependencies` to
`peerDependencies` in `libs/deepagents`, keeping dev copies for isolated
build/test.
- Lets consumers bump `@langchain/core` without requiring a new
`deepagents` release; a release is only needed to widen the peer range
across a major.
- Note on install contract: npm 7+ and pnpm 8+ auto-install peers; Yarn
only warns, so Yarn users must add the four packages explicitly (worth a
README follow-up).
---------
Signed-off-by: Christian Bromann <git@bromann.dev>
Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com>
|
||
|
Alexander Olsen
|
d7ecab2d9f |
fix(deepagents): forward subagent results as text (#608)
## Summary
A deep agent that delegates to a subagent 400s when that subagent uses
an Anthropic server-side tool (web search, web fetch, code execution,
MCP). The subagent's final-message content blocks e.g.
server_tool_use/..._tool_result were forwarded verbatim as the task
ToolMessage content. On the parent agent's next request they serialize
into a tool_result, which Anthropic rejects:
`400 invalid_request_error
messages.N.content.0.tool_result.content.0: Input tag 'server_tool_use'
found using 'type'
does not match any of the expected tags:
'document','image','search_result','text','tool_reference'`
## Solution
Now matches the Python impl: forward only the subagent's text answer.
returnCommandWithStateUpdate now walks back to the last AIMessage with
non-empty text and uses that text (a string) as the ToolMessage content.
- Confirmed the Python deepagents impl is not affected (it forwards
.text); this aligns JS with Python.
- Reproduced the 400 across {web_search, code_execution, web_fetch} ×
{claude-haiku-4-5, claude-sonnet-4-6} on the latest published packages;
all green after the fix.
## Tests
- New: subagent server-tool blocks are filtered from forwarded content.
- New: walk-back uses the last non-empty AIMessage, skipping a trailing
empty message.
- Updated the #239/#245 tests to assert the (now string) ToolMessage
content.
- No regressions in subagent-related tests in the evals suite
---------
Signed-off-by: Alexander Olsen <aolsenjazz@gmail.com>
Co-authored-by: Christian Bromann <git@bromann.dev>
|
||
|
Alexander Olsen
|
42f34b65ed |
feat(deepagents): add bedrockPromptCachingMiddleware to default stack (#611)
## Summary - Adds `bedrockPromptCachingMiddleware` to the default middleware stack - Adds unit tests for the Bedrock model detection util function covering the different formats of model strings/`ChatModel`s |
||
|
Colin Francis
|
3c8f8b2ea6 |
chore(quickjs): disallow task as a configurable ptc tool (#606)
### Summary The code interpreter now comes with a global `task` tool out of the box. As a result, we should disallow specifying the `task` tool for ptc. This PR implements logic that forbids the task tool as in ptc and throws with a detailed error message if found. This PR also updates the RLM agent example and READMEs. ### Tests Unit tests validating expected behavior for task by name and tool instance with "task" name. |
||
|
github-actions[bot]
|
a9e1ba1b89 |
chore: version packages (#605)
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 ## deepagents-acp@0.1.15 ### Patch Changes - Updated dependencies [[`7c4a11e`](https://github.com/langchain-ai/deepagentsjs/commit/7c4a11eacc11c3720b70d802068300ac3b4d8651)]: - deepagents@1.10.5 ## deepagents@1.10.5 ### Patch Changes - [#598](https://github.com/langchain-ai/deepagentsjs/pull/598) [`7c4a11e`](https://github.com/langchain-ai/deepagentsjs/commit/7c4a11eacc11c3720b70d802068300ac3b4d8651) Thanks [@christian-bromann](https://github.com/christian-bromann)! - refactor(stream): use langchain `run.subagents` instead of bespoke transformer Remove deepagents' custom `createSubagentTransformer` and rely on the native subagent stream that `createAgent` registers (langchain#37739). Keep `DeepAgentRunStream` as a compile-time overlay that narrows `run.subagents` to declared subagent specs. Update streaming tests for `cause` and per-subagent message coverage. ## @langchain/quickjs@0.5.1 ### Patch Changes - [#602](https://github.com/langchain-ai/deepagentsjs/pull/602) [`204cb27`](https://github.com/langchain-ai/deepagentsjs/commit/204cb27414c82c34a0c681c7e5a5336e1834f058) Thanks [@colifran](https://github.com/colifran)! - chore(quickjs): refine dynamic subagent prompt to trigger on workflow keyword and to improve iterative eval behavior - [#604](https://github.com/langchain-ai/deepagentsjs/pull/604) [`0971007`](https://github.com/langchain-ai/deepagentsjs/commit/0971007ab2491e73eb1a78c5426ab934470d5620) Thanks [@colifran](https://github.com/colifran)! - fix(quickjs): unwrap Command/ToolMessage envelopes from tool and subagent results ## @deepagents/evals@0.0.14 ### Patch Changes - Updated dependencies [[`7c4a11e`](https://github.com/langchain-ai/deepagentsjs/commit/7c4a11eacc11c3720b70d802068300ac3b4d8651)]: - deepagents@1.10.5 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
7c4a11eacc |
fix(deepagents): use langchain run.subagents instead of bespoke transformer (#598)
## Summary - Remove deepagents' bespoke `createSubagentTransformer` (~460 lines) and wire `createDeepAgent` to langchain's native `run.subagents` projection from `createAgent` (langchain#37739). - Slim `stream.ts` to type-only exports: re-export `SubagentRunStream` from langchain and keep `DeepAgentRunStream` as a compile-time narrowing over declared subagent specs. - Update streaming tests for `sub.cause` (replacing `taskInput`), add single-subagent `sub.messages` coverage, and document parallel-subagent streaming behavior. - Pin `langchain@1.4.6-dev-1781497519109` and `@langchain/langgraph` / `@langchain/langgraph-checkpoint` to `d2312cf` dev builds (root `pnpm.overrides`) for end-to-end verification until published releases are available. - Clarify `streamTransformers` docs: custom transformers surface on `run.extensions`; built-in streams like `run.subagents` and `run.toolCalls` are separate. fixes #560 |
||
|
Colin Francis
|
0971007ab2 |
fix(quickjs): unwrap Command/ToolMessage envelopes from tool and subagent results (#604)
### Summary The deepagents `task` tool resolves to a LangGraph `Command` (and some tools return a `ToolMessage` or a list of messages), but the quickjs bridges passed these envelopes straight to the REPL so `task(...)` and PTC `tools.*` calls handed the model the wrapper instead of the subagent's actual output, breaking the contract that a `responseSchema` dispatch resolves to a typed value. This PR adds `unwrapToolEnvelope`: a duck-typed unwrap of `Command` / `ToolMessage` / message-list shapes that reverse-scans `update.messages` for the last message with content and reads both live and serialized forms. Non-envelope values pass through unchanged. `unwrapToolEnvelope` is wired into both bridges, i.e., the `task()` dispatch and the PTC `tools.*` bridge. Inspired by the Python's [`coerce_tool_output_for_ptc`](https://github.com/langchain-ai/deepagents/blob/4c347603162e181c721e5e2a5ca8bbff6828e23c/libs/partners/quickjs/langchain_quickjs/_format.py#L93-L119). ### Tests - `coerce.test.ts` provide unit test coverage for `unwrapToolEnvelope`: string/null/undefined passthrough, `Command` (single + multi-message), reverse-scan past empty trailing messages, serialized `kwargs.content`, bare `ToolMessage`, message lists, content-block arrays and plain `{ content }` objects left untouched. - `middleware.test.ts` provides an integration test that the `task()` bridge returns the parsed structured value from a `Command` result. |
||
|
Colin Francis
|
204cb27414 |
chore(quickjs): refine dynamic subagent prompt to trigger on workflow keyword and to improve iterative eval behavior (#602)
### Summary Prompt change only, no runtime behavior change. Reworks the quickjs code-interpreter subagent prompt to steer the orchestrator toward an explore-then-distribute workflow. It explores with its own tools first, hands subagents file paths instead of pasted contents, reuses persisted REPL variables rather than re-pasting prior eval output, and returns results via the last expression instead of `console.log`. Also gates the REPL sandbox note so it only mentions the `tools.*` namespace when PTC is actually exposed. --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
github-actions[bot]
|
750d69c024 |
chore: version packages (#568)
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 ## @langchain/node-vfs@0.2.0 ### Minor Changes - [#575](https://github.com/langchain-ai/deepagentsjs/pull/575) [`5d266a2`](https://github.com/langchain-ai/deepagentsjs/commit/5d266a213d8d3d15c2281e2e00ab71ee30ca3ffe) Thanks [@hntrl](https://github.com/hntrl)! - BREAKING: remove shell execution from the VFS provider `VfsBackend` now operates as a filesystem-only `BackendProtocolV2` implementation and no longer exposes command execution. The provider now implements `read`, `ls`, `grep`, and `glob` directly against the in-memory VFS, path resolution is confined to the virtual workspace root, and legacy `VfsSandbox` / `createVfsSandboxFactory*` aliases are removed. ## @langchain/quickjs@0.5.0 ### Minor Changes - [#590](https://github.com/langchain-ai/deepagentsjs/pull/590) [`7ee3feb`](https://github.com/langchain-ai/deepagentsjs/commit/7ee3feb674c361305b2a031db9132253e3d0543b) Thanks [@colifran](https://github.com/colifran)! - chore(quickjs): remove skills backend and associated plumbing - [#592](https://github.com/langchain-ai/deepagentsjs/pull/592) [`72cfb0c`](https://github.com/langchain-ai/deepagentsjs/commit/72cfb0c0384b30059b5e8028139a2e167c1be882) Thanks [@colifran](https://github.com/colifran)! - feat(quickjs): implement default subagent primitive in code interpreter for programmatic subagent calling ### Patch Changes - [#594](https://github.com/langchain-ai/deepagentsjs/pull/594) [`61db938`](https://github.com/langchain-ai/deepagentsjs/commit/61db9381494f61b4548cd80b715e5af72fdde381) Thanks [@colifran](https://github.com/colifran)! - chore(quickjs): remove configurable concurrency and add subagents option with true default - [#546](https://github.com/langchain-ai/deepagentsjs/pull/546) [`b7a5f26`](https://github.com/langchain-ai/deepagentsjs/commit/b7a5f26fd9cba992b11e1a4cf18607d64533503b) Thanks [@open-swe](https://github.com/apps/open-swe)! - fix(quickjs): scope `CodeInterpreterMiddleware` REPL prompt sandbox bullet to the runtime ## deepagents-acp@0.1.14 ### Patch Changes - Updated dependencies [[`18557db`](https://github.com/langchain-ai/deepagentsjs/commit/18557db7bbdf92052ed5f994512fb70e11989e69), [`773cac5`](https://github.com/langchain-ai/deepagentsjs/commit/773cac5dc7efc7843dd882642d91f7d64d6fde81), [`1ca6dc9`](https://github.com/langchain-ai/deepagentsjs/commit/1ca6dc92fd40a6d845d24b95ba14b8f2643db394), [`03df237`](https://github.com/langchain-ai/deepagentsjs/commit/03df237385fbdfefd862076c5588eb39cb6e43c3), [`84f3c0c`](https://github.com/langchain-ai/deepagentsjs/commit/84f3c0c2f1cad271191bcc138b84ba5b9c9205c9), [`72cfb0c`](https://github.com/langchain-ai/deepagentsjs/commit/72cfb0c0384b30059b5e8028139a2e167c1be882), [`04cc3fc`](https://github.com/langchain-ai/deepagentsjs/commit/04cc3fc26001ee566ed94de44c2dda2cf6adecc4), [`18fbb48`](https://github.com/langchain-ai/deepagentsjs/commit/18fbb4839050e98ae3cfd36ec69b11f0725ad6d6), [`e3d4b53`](https://github.com/langchain-ai/deepagentsjs/commit/e3d4b5367b1825df56c919b483ec4a3e117d631f)]: - deepagents@1.10.4 ## deepagents@1.10.4 ### Patch Changes - [#551](https://github.com/langchain-ai/deepagentsjs/pull/551) [`18557db`](https://github.com/langchain-ai/deepagentsjs/commit/18557db7bbdf92052ed5f994512fb70e11989e69) Thanks [@antonnak](https://github.com/antonnak)! - fix(deepagents): gate cache_control writes on per-call request.model `createCacheBreakpointMiddleware` and `createMemoryMiddleware` were gating the Anthropic-specific `cache_control` write at agent-creation time only. When `modelFallbackMiddleware` swapped `request.model` to a non-Anthropic provider mid-flight (e.g. on Anthropic 5xx), the marker leaked through and the fallback provider rejected the request with `400 Unknown parameter: 'cache_control'`. Both middlewares now also check `isAnthropicModel(request.model)` inside `wrapModelCall`. Fixes [#550](https://github.com/langchain-ai/deepagentsjs/issues/550). - [#591](https://github.com/langchain-ai/deepagentsjs/pull/591) [`773cac5`](https://github.com/langchain-ai/deepagentsjs/commit/773cac5dc7efc7843dd882642d91f7d64d6fde81) Thanks [@colifran](https://github.com/colifran)! - chore(deepagents): expose createSubAgent - [#541](https://github.com/langchain-ai/deepagentsjs/pull/541) [`1ca6dc9`](https://github.com/langchain-ai/deepagentsjs/commit/1ca6dc92fd40a6d845d24b95ba14b8f2643db394) Thanks [@ixchio](https://github.com/ixchio)! - fix getMimeType to return application/octet-stream for unknown file extensions instead of text/plain - [#572](https://github.com/langchain-ai/deepagentsjs/pull/572) [`03df237`](https://github.com/langchain-ai/deepagentsjs/commit/03df237385fbdfefd862076c5588eb39cb6e43c3) Thanks [@hntrl](https://github.com/hntrl)! - fix: scope CompositeBackend grep/glob route fanout by search path CompositeBackend now limits fallback route fanout to routes mounted under the requested search path, instead of querying all routed backends unconditionally. This avoids unrelated routed backend calls (and side-effect errors) for scoped searches like `path="/workspace"`, while preserving full fanout behavior at root (`path="/"`). - [#574](https://github.com/langchain-ai/deepagentsjs/pull/574) [`84f3c0c`](https://github.com/langchain-ai/deepagentsjs/commit/84f3c0c2f1cad271191bcc138b84ba5b9c9205c9) Thanks [@hntrl](https://github.com/hntrl)! - fix(deepagents): add explicit browser and node entrypoints - add `deepagents/browser` and `deepagents/node` subpath exports - route browser bundlers to the browser-safe bundle via the root `browser` export condition - avoid named Node builtin imports in backend utils that can break browser builds - document browser guidance to import from `deepagents/browser` - [#592](https://github.com/langchain-ai/deepagentsjs/pull/592) [`72cfb0c`](https://github.com/langchain-ai/deepagentsjs/commit/72cfb0c0384b30059b5e8028139a2e167c1be882) Thanks [@colifran](https://github.com/colifran)! - feat(quickjs): implement default subagent primitive in code interpreter for programmatic subagent calling - [#566](https://github.com/langchain-ai/deepagentsjs/pull/566) [`04cc3fc`](https://github.com/langchain-ai/deepagentsjs/commit/04cc3fc26001ee566ed94de44c2dda2cf6adecc4) Thanks [@hntrl](https://github.com/hntrl)! - fix(deepagents): propagate subagent `lc_agent_name` during task delegation - Ensure `task` tool subagent invocations override `metadata.lc_agent_name` with the selected `subagent_type`. - Add regression coverage for both compiled subagents (`runnable`) and standard subagent specs to verify tool-time metadata reflects the active subagent. - Update the `langsmith` peer dependency range in `deepagents` to `^0.7.1`. - [#595](https://github.com/langchain-ai/deepagentsjs/pull/595) [`18fbb48`](https://github.com/langchain-ai/deepagentsjs/commit/18fbb4839050e98ae3cfd36ec69b11f0725ad6d6) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(deepagents): count tokens once per model call in summarization middleware `createSummarizationMiddleware` counted tokens twice on every model call—once inside `truncateArgs` and again for the should-summarize check—even when nothing was truncated or summarized. Count once and pass the total into `truncateArgs`; recount only when truncation actually modifies messages. - [#242](https://github.com/langchain-ai/deepagentsjs/pull/242) [`e3d4b53`](https://github.com/langchain-ai/deepagentsjs/commit/e3d4b5367b1825df56c919b483ec4a3e117d631f) Thanks [@alvedder](https://github.com/alvedder)! - feat(deepagents): support direct skill paths as sources in createSkillsMiddleware ## @deepagents/evals@0.0.13 ### Patch Changes - Updated dependencies [[`18557db`](https://github.com/langchain-ai/deepagentsjs/commit/18557db7bbdf92052ed5f994512fb70e11989e69), [`773cac5`](https://github.com/langchain-ai/deepagentsjs/commit/773cac5dc7efc7843dd882642d91f7d64d6fde81), [`1ca6dc9`](https://github.com/langchain-ai/deepagentsjs/commit/1ca6dc92fd40a6d845d24b95ba14b8f2643db394), [`03df237`](https://github.com/langchain-ai/deepagentsjs/commit/03df237385fbdfefd862076c5588eb39cb6e43c3), [`84f3c0c`](https://github.com/langchain-ai/deepagentsjs/commit/84f3c0c2f1cad271191bcc138b84ba5b9c9205c9), [`72cfb0c`](https://github.com/langchain-ai/deepagentsjs/commit/72cfb0c0384b30059b5e8028139a2e167c1be882), [`04cc3fc`](https://github.com/langchain-ai/deepagentsjs/commit/04cc3fc26001ee566ed94de44c2dda2cf6adecc4), [`18fbb48`](https://github.com/langchain-ai/deepagentsjs/commit/18fbb4839050e98ae3cfd36ec69b11f0725ad6d6), [`e3d4b53`](https://github.com/langchain-ai/deepagentsjs/commit/e3d4b5367b1825df56c919b483ec4a3e117d631f)]: - deepagents@1.10.4 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
18fbb48390 |
fix(deepagents): count tokens once per model call in summarization middleware (#595)
## Summary - Port [langchain-ai/deepagents#3877](https://github.com/langchain-ai/deepagents/pull/3877): `createSummarizationMiddleware` now counts tokens once per model call instead of twice on the common pass-through path. - Pass the precomputed total into `truncateArgs` via an optional `totalTokens` parameter; recount only when truncation modifies messages. - Add a regression test asserting `countTokensApproximately` runs exactly once when nothing is truncated or summarized. |
||
|
Colin Francis
|
61db938149 |
chore(quickjs): remove configurable concurrency and add subagents option with true default (#594)
### Summary This PR remove the configurable concurrency option from code interpreter middleware options and adds a subagents option that is true by default |
||
|
Colin Francis
|
72cfb0c038 |
feat(quickjs): implement default task primitive in code interpreter for programmatic subagent calling (#592)
### Summary This PR adds a default task primitive to the code interpreter that allows the agent to natively write code to programmatically dispatch subagents. The task primitive supports passing response schemas for dynamic structured output that helps with more complex orchestration patterns. This PR also removes the swarm task tool in favor of the task primitive. --------- Co-authored-by: Hunter Lovell <40191806+hntrl@users.noreply.github.com> |
||
|
Colin Francis
|
773cac5dc7 |
chore(deepagents): expose createSubAgent (#591)
### Summary Exposes `createSubAgent` as a dedicated function which allows us to reuse the inner subagent factory outside of the middleware (e.g. using it as the single source of truth for defining subagents in quickjs). Port of similar implementation from https://github.com/langchain-ai/deepagents/pull/3846 |
||
|
Colin Francis
|
7ee3feb674 |
chore(quickjs): remove skills backend and associated plumbing (#590)
### Summary Removes skills backend and associated plumbing from code interpreter middleware and options |
||
|
Alexei Vedernikov
|
e3d4b5367b |
feat(deepagents): support direct skill paths as sources in createSkillsMiddleware (#242)
## Description
Previously, sources had to be parent directories (e.g. `/skills/`) whose
subdirectories each contained a SKILL.md. Passing a direct skill path
(e.g. `/skills/my-skill/`) had no effect because `listSkillsFromBackend`
scanned for subdirectories inside the source, found none, and returned
an empty list.
## Real case
The motivating scenario is when a curated list of skills organised as
individual directories under a shared directory. Each skill has a clear
responsibility, and different skills are intentionally assigned to the
orchestrator agent vs. subagents:
```typescript
// Desired: pass individual skill paths — one per capability
const SHARED_SKILLS = ['/skills/web-research/'];
const ORCHESTRATOR_SKILLS = [
'/skills/requirement-completeness-validator/',
'/skills/diff-risk-analyzer/',
];
createDeepAgent({
skills: [...SHARED_SKILLS, ...ORCHESTRATOR_SKILLS],
subagents: subagentsConfig.map(agentConfig => ({
skills: [
...SHARED_SKILLS,
...agentConfig.skills,
]
}))
});
```
The workaround would be to create nested directories like this:
```
skills/
web-research/
web-research/
SKILL.md
equirement-completeness-validator/
equirement-completeness-validator/
SKILL.md
...and so on
```
## What's done
Detection is done by inspecting the lsInfo() result of the source
directory: if a SKILL.md file appears directly in the listing, the
source itself is treated as the skill directory. Otherwise the existing
parent-directory scan runs unchanged.
The two modes can be freely mixed in the sources array:
```ts
sources: [
'/skills/', // parent dir: all subdirs with SKILL.md
'/skills/my-skill/', // direct path: SKILL.md at its root
]
```
---------
Co-authored-by: Hunter Lovell <40191806+hntrl@users.noreply.github.com>
|
||
|
Anton Nak
|
18557db7bb |
fix(deepagents): gate cache_control writes on per-call request.model (#551)
Fixes #550. ## Problem `createCacheBreakpointMiddleware` and `createMemoryMiddleware` write Anthropic-specific `cache_control: { type: "ephemeral" }` markers into the request payload. Both gate the write at **agent-creation time** in `createDeepAgent` (whether the *primary* model is Anthropic). When `modelFallbackMiddleware` swaps `request.model` to a non-Anthropic provider at request time, the markers leak through and the fallback provider rejects the request: ``` 400 Unknown parameter: 'messages[0].content[N].cache_control' ``` Full root-cause writeup, production trace, and reproduction in #550. ## Fix Move the model classification from boot-time to **per-call**, using the existing `isAnthropicModel` helper (`src/utils.ts:9`). - **`src/middleware/cache.ts`** — bail at the top of `wrapModelCall` when `request.model` isn't Anthropic. - **`src/middleware/memory.ts`** — AND the existing `addCacheControl` flag with the same per-call check. `addCacheControl` keeps its current public meaning (opt-in switch); the per-call gate is an additional safety net. - **`src/agent.ts`** — left untouched. The boot-time install gate stays (small perf win when primary is non-Anthropic — middleware isn't installed at all). The new per-call check handles the fallback case where the middleware *is* installed but the model has been swapped. ## Tests Each middleware's `.test.ts` got a `per-call provider gating` block. They build a request with a `ChatAnthropic`-shaped stub vs a `ChatOpenAI`-shaped stub on `request.model`, run `wrapModelCall`, and assert `cache_control` is/isn't written. Also covers `ConfigurableModel` with `modelProvider: "anthropic"` and the string forms (`"anthropic:claude-..."`, `"openai:gpt-5"`). Existing fixtures that didn't set `request.model` now pass a `ChatAnthropic` stub so they keep exercising the write path — they were previously relying on the unconditional behavior. No behavioral assertions changed; only the fixture got more explicit. 31/31 tests pass on `libs/deepagents` (`cache.test.ts` + `memory.test.ts`). ## Compatibility - **No public API change.** `addCacheControl?: boolean` on `MemoryMiddlewareOptions` keeps its existing semantics. - **Anthropic-primary happy path unchanged** — same writes, same cache hits. - **Per-call cost:** one `getName()` / string check inside `wrapModelCall`. Sub-microsecond. - **Failure mode improvement:** users running `createDeepAgent` with an Anthropic primary + non-Anthropic fallback no longer get a 400 from the fallback provider on swap. ## Changeset `patch` bump on `deepagents`. ## Out of scope `request.modelSettings.cache_control` (written by LangChain core's `anthropicPromptCachingMiddleware`) can also leak across the swap. Mentioned in #550 for tracking — that's a LangChain-side fix, not deepagents. --------- Co-authored-by: Anton Nakaliuzhnyi <anakaliuzhnyi@gipartners.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Aman Pandey
|
1ca6dc92fd |
fix(deepagents): return application/octet-stream for unknown MIME types (#541)
Fixes #542. `getMimeType()` falls back to `"text/plain"` for any extension not in the `MIME_TYPES` lookup table. Since `isTextMimeType("text/plain")` returns `true`, this means binary files (.zip, .exe, .wasm, .sqlite, .pyc, .class, .jar, etc.) get treated as text everywhere downstream — grep searches through them and returns garbage, read_file splits their content on newlines and paginates it, and StateBackend can silently corrupt binary data stored via createFileData(). The fix is straightforward: change the default to `"application/octet-stream"`, which is what unknown binary data should be. `isTextMimeType()` already returns `false` for it, so binary files stop getting mangled. To avoid breaking existing behavior for actual text files that were previously relying on the fallback (like .txt, .ts, .py, .json, .js — none of which had explicit entries), this also adds those to the MIME_TYPES map directly. Covers ~67 common text/code extensions. All 386 backend tests pass (10 files). The updated test expectations in utils.test.ts verify both sides: known text extensions still resolve correctly, and unknown/binary extensions now get `application/octet-stream` instead of being misidentified as text. --------- Co-authored-by: Hunter Lovell <40191806+hntrl@users.noreply.github.com> |
||
|
Hunter Lovell
|
5d266a213d |
refactor(node-vfs): make VfsSandbox filesystem-only (#575)
## Summary This PR removes command-execution semantics from `@langchain/node-vfs` and aligns `VfsSandbox` with `BackendProtocolV2` as a filesystem-only backend. The provider no longer uses sandbox execution abstractions and now performs core file operations directly against the in-memory VFS. ## Changes ### Protocol alignment - `VfsSandbox` now implements `BackendProtocolV2` directly instead of extending sandbox/base-execution abstractions. - Removed command execution from the provider surface (`execute` is no longer part of this backend implementation). - Removed `timeout` from `VfsSandboxOptions` and corresponding docs. ### Runtime behavior - Added native backend implementations for: - `read` - `readRaw` - `write` - `edit` - `ls` - `grep` - `glob` - Kept upload/download support and added path confinement handling for invalid traversal paths. - Continued in-memory VFS-only operation (no temp-dir shell sync path). ### Tests and docs - Updated unit and integration tests to remove execute-focused assertions and validate filesystem behavior. - Updated package docs to describe `BackendProtocolV2` usage and removed execute/timeout references. - Added changeset for `@langchain/node-vfs`. |
||
|
open-swe[bot]
|
b7a5f26fd9 |
fix(quickjs): scope REPL prompt sandbox bullet to the runtime (#546)
Ports langchain-ai/deepagents#3528 to deepagentsjs. The base `CodeInterpreterMiddleware` REPL prompt asserted "no filesystem, no stdlib, no network, no real clock, no `fetch`, no `require`". When `ptc` is configured, the same system prompt also exposes a `tools.*` namespace whose members can include things like web fetch, file I/O, or shell access — directly contradicting the sandbox bullet. A model reading both sections sees "no network" *and* `await tools.webFetch({...})` in the same prompt. With PTC disabled it's even worse: exposed tools are still reachable through the normal tool-calling path *outside* `eval`, and the model could interpret the bullet as a statement about the agent's capabilities rather than the REPL's. This rewords the bullet to scope it to the QuickJS runtime, and notes that external side effects from inside the REPL flow through `tools.*` when it's exposed (otherwise the REPL is pure computation). `@langchain/quickjs` middleware unit tests, lint, and format all pass locally. _Opened collaboratively by Mason Daugherty and open-swe._ Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Mason Daugherty <61371264+mdrxy@users.noreply.github.com> |
||
|
Hunter Lovell
|
84f3c0c2f1 |
fix(deepagents): add browser and node entrypoints (#574)
## Summary Fixes #292, #543 This updates `deepagents` packaging to split environment-specific exports and avoid browser build failures caused by Node-only imports in the default bundle. Browser consumers now have an explicit `deepagents/browser` entrypoint, while Node consumers can keep using `deepagents` (or optionally `deepagents/node`) for the full runtime API. ## Changes ### `deepagents` package exports and entrypoints - Added `src/browser.ts` as a browser-safe public barrel that excludes Node-only APIs. - Added `src/node.ts` as an explicit Node entrypoint that re-exports the full API. - Updated `package.json` exports to: - route the root `browser` condition to `./dist/browser.js` - expose `./browser` and `./node` subpath exports (ESM + CJS + types). - Updated `tsdown` config to build `index`, `browser`, and `node` outputs. ### Runtime import graph hardening - Updated `createDeepAgent` to import `StateBackend` directly from `backends/state` so it no longer pulls in the full Node-oriented backends barrel. - Updated `types.ts` to import `AnyBackendProtocol` from `backends/protocol` instead of `backends/index`. - Removed named Node builtin path imports from `backends/utils.ts` by replacing `path.basename`/`path.extname` with local helpers. ### Documentation and release notes - Added a README section documenting import guidance: browser apps should use `deepagents/browser`, and Node apps can continue to use `deepagents`. - Added a patch changeset for `deepagents` describing the entrypoint and packaging fix. |
||
|
Hunter Lovell
|
03df237385 |
fix(deepagents): scope composite route search fanout by path (#572)
## Summary Fixes #241. This updates `CompositeBackend` search routing so scoped `grep`/`glob` requests only fan out to routed backends mounted under the requested path. Previously, non-route paths (for example `/workspace`) still queried all routes, which could trigger unrelated backend errors. ## Changes ### `libs/deepagents/src/backends/composite.ts` - Added route/path helper predicates to distinguish: - when a search path is inside a route, - when a route is a descendant of the requested search path. - Updated `grep` fallback behavior to query the default backend plus only descendant routes (instead of unconditional all-route fanout). - Updated `glob` fallback behavior to use the same descendant-route filtering. - Normalized `grep` path handling to accept `null` and treat it as root (`/`). - Reused the same route-matching helper in `ls` for consistent prefix matching semantics. ### `libs/deepagents/src/backends/composite.test.ts` - Added regression test to ensure `grep("...", "/workspace")` does not call unrelated routes (for example `/skills/`) while still searching relevant descendant routes. - Added regression test for equivalent `glob` behavior. Co-authored-by: Christian Bromann <731337+christian-bromann@users.noreply.github.com> |