gravity-cli 0.5.0__tar.gz → 0.5.3__tar.gz

{gravity_cli-0.5.0 → gravity_cli-0.5.3}/AGENT_STANDARD.md

@@ -191,6 +191,37 @@ model = ChatOpenAI(model="openai/gpt-6-luna",
                    api_key=os.environ["GRAVITY_RUN_TOKEN"])
 ```
 
+**Embeddings** use the same URL and token (`<GRAVITY_LLM_URL>/embeddings`), metered
+and budgeted like chat calls:
+
+```python
+emb = OpenAIEmbeddings(model="voyageai/voyage-4-lite",   # or google/gemini-embedding-2
+                       base_url=os.environ["GRAVITY_LLM_URL"],
+                       api_key=os.environ["GRAVITY_RUN_TOKEN"],
+                       check_embedding_ctx_length=False)  # send text, not OpenAI token ids
+vectors = await emb.aembed_documents(["first text", "second text"])
+```
+
+**Images** come from an image model through the same URL and token: no tool to
+declare. Ask for image output; the picture comes back as a data URL, which is
+exactly what the corpus takes (§8):
+
+```python
+async with httpx.AsyncClient(timeout=120) as http:
+    resp = await http.post(f"{os.environ['GRAVITY_LLM_URL']}/chat/completions",
+        headers={"Authorization": f"Bearer {os.environ['GRAVITY_RUN_TOKEN']}"},
+        json={"model": "google/gemini-2.5-flash-image",   # or openai/gpt-5-image-mini
+              "modalities": ["image", "text"],
+              "messages": [{"role": "user", "content": "A flat illustration of ..., no text"}]})
+    resp.raise_for_status()
+    src = resp.json()["choices"][0]["message"]["images"][0]["image_url"]["url"]   # data:image/png;base64,...
+```
+
+An image is a few MB and the whole state is checkpointed after every step, so
+make pictures in the **last** node (or the one that builds the corpus) and keep
+them out of state until then. Each one is metered and counts toward the run's
+budget like any model call.
+
 Those three env vars — `GRAVITY_GATEWAY_URL`, `GRAVITY_LLM_URL`,
 `GRAVITY_RUN_TOKEN` — are the entire Gravity surface, plus the `gravity`
 package for tools on the platform (§8). No `OPENAI_API_KEY`: locally and in
@@ -217,6 +248,11 @@ undeclared tool is refused locally exactly as it will be when hosted. Your
 agent only ever sees the run token. `GRAVITY_GATEWAY_URL` defaults to
 `http://127.0.0.1:8000/mcp` and `GRAVITY_LLM_URL` to the same host's `/v1`.
 
+`gravity dev` opens a local dashboard over the same runs: a form from your
+manifest, a live timeline, approvals, the result and a history. A run from
+`gravity run` in the same folder shows up in it, and the other way round (both
+leave their record in `.gravity/runs/`; one run is live per folder).
+
 ## 7. What's checked where
 
 | Stage | Catches |
@@ -271,7 +307,10 @@ start**: everything before the call happens twice.
 replaced. State is kept per thread. A key the next run doesn't send keeps its
 value (a monitor's `seen`, a draft). For memory shared by one consumer's
 threads, use `langgraph.config.get_store()` (`aget` / `aput` / `asearch` by
-namespace and filter; no semantic search).
+namespace and filter; no semantic search). It is kept per consumer and agent,
+across runs and versions, until the agent deletes an item (`aput(ns, key, None)`);
+store one item per record, not one large blob. `gravity run` gives you the same
+store locally, saved in `.gravity/store.json` (delete it to start over).
 
 **Conversation.** `messages` must use the `add_messages` reducer:
 `messages: Annotated[list, add_messages]`. Each turn the platform sends only
@@ -314,6 +353,7 @@ corpus = gravity.Corpus(
         facts=[gravity.Fact(label="TAM", value="$18B", source="s1")],   # value: text or a number
         table=gravity.Table(columns=["Segment", "Teams"], rows=[["Founders", "1.2M"]]),
         notes="speaker notes / read-out text",
+        images=[gravity.Image(src=src, alt="server rack", caption="Option A")],   # data URL, see §4
         sections=[gravity.Section(heading="one level of nesting, same shape")],
     )],
     sources=[gravity.Source(id="s1", title="Report", url="https://example.com")],
@@ -322,7 +362,10 @@ return {**corpus.to_state(), "result": {"title": corpus.title}}
 ```
 
 A plain dict of the same shape works too. The models catch a typo when the
-corpus is built rather than when it's rendered. Set `result` as well: it's
+corpus is built rather than when it's rendered. Images (`png`, `jpeg`, `webp`
+or `gif` data URLs, at most 8 MB each and 12 per corpus) are embedded in the
+Word, PowerPoint and Markdown downloads and shown on `/app` and in `gravity
+dev`; an emailed output names each one as `[image: alt — caption]` instead. Set `result` as well: it's
 what the run returns.
 
 ## 9. Checklist

gravity_cli-0.5.0/README.md → gravity_cli-0.5.3/PKG-INFO

@@ -1,3 +1,20 @@
+Metadata-Version: 2.5
+Name: gravity-cli
+Version: 0.5.3
+Summary: gravity cli — init, run, and push python agents to the Gravity marketplace
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Requires-Python: >=3.12
+Requires-Dist: gravity-schema==0.5.3
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: keyring>=25.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: rich>=13.9.0
+Requires-Dist: typer>=0.15.0
+Requires-Dist: uv>=0.8.0
+Description-Content-Type: text/markdown
+
 <h1 align="center">Gravity CLI</h1>
 
 <p align="center">
@@ -179,6 +196,7 @@ Run `gravity help` for this list in the terminal, and add `-h` to any command fo
 | **Build an agent** | [`gravity init`](#gravity-init) | Create a new agent from a template |
 | | [`gravity validate`](#gravity-validate) | Check your agent for mistakes before it runs |
 | | [`gravity run`](#gravity-run) | Run your agent locally against real tools |
+| | [`gravity dev`](#gravity-dev) | Open a local dashboard to run and watch your agent |
 | | [`gravity schedule`](#gravity-schedule) | Run your agent on its schedule, locally |
 | | [`gravity adapt`](#gravity-adapt) | Write a new slot adapter with AI, kept only if its tests pass |
 | **Publish** | [`gravity build`](#gravity-build) | Package your agent into `build/agent.zip` |
@@ -274,6 +292,29 @@ gravity run --reply "make it shorter"
 - Requires a gateway token: the one `gravity login` stores, or `GRAVITY_DEV_TOKEN`.
 - A call to a tool in `approvals.required_for` pauses, shows what it would do, and waits for `y` or `n`. With no terminal to ask in, it is rejected.
 - Exits with code 0 when the run finishes and 1 when it fails.
+- Leaves a record in `.gravity/runs/<id>/` (`run.json` and `events.jsonl`), which is what `gravity dev` reads. One run is live per folder at a time, because runs share the folder's memory, store and thread files.
+
+### `gravity dev`
+
+Open a local dashboard for the agent in this folder: a form built from the manifest's inputs, a live timeline of each step, model call and tool call, approval buttons for held calls, the result, and a history of runs.
+
+```
+gravity dev [path] [--port 4747] [--no-open] [--llm-url URL]
+```
+
+| Option | Description |
+|---|---|
+| `--port N` | Port to listen on (default 4747). If it is taken, a free one is used and printed. |
+| `--no-open` | Print the address without opening a browser (SSH, WSL, CI) |
+| `--llm-url URL` | Model endpoint to use instead of `GRAVITY_LLM_URL` |
+
+- A run from `gravity run` in the same folder shows up in the dashboard live, and a run started in the dashboard is the same run (same engine, same memory, store and thread files), so `gravity run --reply` continues it.
+- It listens on `127.0.0.1` only, behind a random token in the printed address, for as long as the command runs. Ctrl+C stops it and any run it started. Nothing keeps running in the background.
+- Connected accounts: it shows the accounts your tools need and a Connect button for each one that is missing.
+- Approvals: a call held for approval can be decided in the terminal or in the dashboard; whichever answers first wins.
+- Cancel a run from the dashboard only if the dashboard started it; stop a terminal run with Ctrl+C in that terminal.
+- Results show as text. Word, PowerPoint and CSV files are produced by Gravity after you push. A file input is read as text here.
+- Same requirements as `gravity run`: a gateway token from `gravity login`, or `GRAVITY_DEV_TOKEN`.
 
 ### `gravity schedule`
 
@@ -738,6 +779,8 @@ Real tools act on a connected account. Connect one with `gravity-gateway connect
 
 ## What's new
 
+- **0.5.3** `gravity dev` opens a local dashboard for your agent: a form from your manifest, a live timeline, approvals, the result and run history; runs from `gravity run` in the same folder show up in it live, and the other way round. WhatsApp joins the catalog (51 tools; 1,374 across 12 apps). Agents can return generated images: put them in a corpus section's `images` and they land in the Word, PowerPoint and Markdown outputs. The agent standard now shows how to generate images and embeddings through the gateway. `NEEDS_RECONNECT` on the shared test account tells you to ask Gravity, not to connect your own account.
+- **0.5.2** Jira, Confluence and Notion join the catalog: 1,351 tools across 11 apps. `get_store()` works in local runs, kept in `.gravity/store.json`. Renewing an expired sign-in keeps your gateway token, so `gravity run` keeps working after an hour. Commands start faster: the catalog loads in a quarter of the time.
 - **0.5.0** `gravity connect` links your own accounts. `web.search` and `web.fetch` join the catalog. `gravity validate` now refuses a tool that isn't in the catalog, an imported write tool without an approval, and code that names a write tool the manifest doesn't grant. `gravity tools` reads the gateway's list and needs no sign-in. On Windows the session stays in the keychain instead of a file.
 - **0.4.4** Same code as 0.4.3, released from this repository so the GitHub release, the tag and PyPI line up again. Adds `RELEASING.md`.
 - **0.4.3** Documents the `secret` input type and the `supadata.get_transcript` tool.

gravity_cli-0.5.0/PKG-INFO → gravity_cli-0.5.3/README.md

@@ -1,20 +1,3 @@
-Metadata-Version: 2.5
-Name: gravity-cli
-Version: 0.5.0
-Summary: gravity cli — init, run, and push python agents to the Gravity marketplace
-License-Expression: Apache-2.0
-License-File: LICENSE
-License-File: NOTICE
-Requires-Python: >=3.12
-Requires-Dist: gravity-schema==0.5.0
-Requires-Dist: httpx>=0.27.0
-Requires-Dist: keyring>=25.0.0
-Requires-Dist: python-dotenv>=1.0.0
-Requires-Dist: rich>=13.9.0
-Requires-Dist: typer>=0.15.0
-Requires-Dist: uv>=0.8.0
-Description-Content-Type: text/markdown
-
 <h1 align="center">Gravity CLI</h1>
 
 <p align="center">
@@ -196,6 +179,7 @@ Run `gravity help` for this list in the terminal, and add `-h` to any command fo
 | **Build an agent** | [`gravity init`](#gravity-init) | Create a new agent from a template |
 | | [`gravity validate`](#gravity-validate) | Check your agent for mistakes before it runs |
 | | [`gravity run`](#gravity-run) | Run your agent locally against real tools |
+| | [`gravity dev`](#gravity-dev) | Open a local dashboard to run and watch your agent |
 | | [`gravity schedule`](#gravity-schedule) | Run your agent on its schedule, locally |
 | | [`gravity adapt`](#gravity-adapt) | Write a new slot adapter with AI, kept only if its tests pass |
 | **Publish** | [`gravity build`](#gravity-build) | Package your agent into `build/agent.zip` |
@@ -291,6 +275,29 @@ gravity run --reply "make it shorter"
 - Requires a gateway token: the one `gravity login` stores, or `GRAVITY_DEV_TOKEN`.
 - A call to a tool in `approvals.required_for` pauses, shows what it would do, and waits for `y` or `n`. With no terminal to ask in, it is rejected.
 - Exits with code 0 when the run finishes and 1 when it fails.
+- Leaves a record in `.gravity/runs/<id>/` (`run.json` and `events.jsonl`), which is what `gravity dev` reads. One run is live per folder at a time, because runs share the folder's memory, store and thread files.
+
+### `gravity dev`
+
+Open a local dashboard for the agent in this folder: a form built from the manifest's inputs, a live timeline of each step, model call and tool call, approval buttons for held calls, the result, and a history of runs.
+
+```
+gravity dev [path] [--port 4747] [--no-open] [--llm-url URL]
+```
+
+| Option | Description |
+|---|---|
+| `--port N` | Port to listen on (default 4747). If it is taken, a free one is used and printed. |
+| `--no-open` | Print the address without opening a browser (SSH, WSL, CI) |
+| `--llm-url URL` | Model endpoint to use instead of `GRAVITY_LLM_URL` |
+
+- A run from `gravity run` in the same folder shows up in the dashboard live, and a run started in the dashboard is the same run (same engine, same memory, store and thread files), so `gravity run --reply` continues it.
+- It listens on `127.0.0.1` only, behind a random token in the printed address, for as long as the command runs. Ctrl+C stops it and any run it started. Nothing keeps running in the background.
+- Connected accounts: it shows the accounts your tools need and a Connect button for each one that is missing.
+- Approvals: a call held for approval can be decided in the terminal or in the dashboard; whichever answers first wins.
+- Cancel a run from the dashboard only if the dashboard started it; stop a terminal run with Ctrl+C in that terminal.
+- Results show as text. Word, PowerPoint and CSV files are produced by Gravity after you push. A file input is read as text here.
+- Same requirements as `gravity run`: a gateway token from `gravity login`, or `GRAVITY_DEV_TOKEN`.
 
 ### `gravity schedule`
 
@@ -755,6 +762,8 @@ Real tools act on a connected account. Connect one with `gravity-gateway connect
 
 ## What's new
 
+- **0.5.3** `gravity dev` opens a local dashboard for your agent: a form from your manifest, a live timeline, approvals, the result and run history; runs from `gravity run` in the same folder show up in it live, and the other way round. WhatsApp joins the catalog (51 tools; 1,374 across 12 apps). Agents can return generated images: put them in a corpus section's `images` and they land in the Word, PowerPoint and Markdown outputs. The agent standard now shows how to generate images and embeddings through the gateway. `NEEDS_RECONNECT` on the shared test account tells you to ask Gravity, not to connect your own account.
+- **0.5.2** Jira, Confluence and Notion join the catalog: 1,351 tools across 11 apps. `get_store()` works in local runs, kept in `.gravity/store.json`. Renewing an expired sign-in keeps your gateway token, so `gravity run` keeps working after an hour. Commands start faster: the catalog loads in a quarter of the time.
 - **0.5.0** `gravity connect` links your own accounts. `web.search` and `web.fetch` join the catalog. `gravity validate` now refuses a tool that isn't in the catalog, an imported write tool without an approval, and code that names a write tool the manifest doesn't grant. `gravity tools` reads the gateway's list and needs no sign-in. On Windows the session stays in the keychain instead of a file.
 - **0.4.4** Same code as 0.4.3, released from this repository so the GitHub release, the tag and PyPI line up again. Adds `RELEASING.md`.
 - **0.4.3** Documents the `secret` input type and the `supadata.get_transcript` tool.

{gravity_cli-0.5.0 → gravity_cli-0.5.3}/packages/gravity-schema/gravity_schema/catalog.py

@@ -10,6 +10,13 @@ from typing import Protocol
 
 import yaml
 
+# libyaml's parser, about 8x faster: every CLI command loads the whole catalog at import.
+_LOADER = getattr(yaml, "CSafeLoader", yaml.SafeLoader)
+
+
+def _load(text: str):
+    return yaml.load(text, Loader=_LOADER)
+
 
 class ToolCatalog(Protocol):
     def exists(self, tool_name: str) -> bool: ...
@@ -39,6 +46,7 @@ class ToolEntry:
     breadth: str  # generic | niche
     guarantee: str  # certified | community | experimental
     side_effect: str  # read | write
+    toolkit: str | None = None  # the account a user connects for it; None when none is needed
 
 
 _BREADTH = {"generic", "niche"}
@@ -48,12 +56,12 @@ _SIDE_EFFECT = {"read", "write"}
 
 def load_catalog(path: Path | None = None) -> tuple[ToolEntry, ...]:
     """Parse and check catalog.yaml; a malformed entry fails at import."""
-    raw = yaml.safe_load((path or Path(__file__).with_name("catalog.yaml")).read_text(encoding="utf-8"))
+    raw = _load((path or Path(__file__).with_name("catalog.yaml")).read_text(encoding="utf-8"))
     # catalog_imported.yaml (`gravity-gateway sync-tools`): the same apps' other tools,
     # experimental. Absent until the first sync; never read for an explicit path.
     imported = Path(__file__).with_name("catalog_imported.yaml")
     if path is None and imported.is_file():
-        raw = [*raw, *(yaml.safe_load(imported.read_text(encoding="utf-8")) or [])]
+        raw = [*raw, *(_load(imported.read_text(encoding="utf-8")) or [])]
     entries: list[ToolEntry] = []
     for item in raw:
         entry = ToolEntry(
@@ -64,6 +72,7 @@ def load_catalog(path: Path | None = None) -> tuple[ToolEntry, ...]:
             breadth=item["breadth"],
             guarantee=item["guarantee"],
             side_effect=item["side_effect"],
+            toolkit=item.get("toolkit"),
         )
         problems = []
         if entry.breadth not in _BREADTH:

{gravity_cli-0.5.0 → gravity_cli-0.5.3}/packages/gravity-schema/gravity_schema/catalog.yaml

@@ -10,6 +10,7 @@
 # Fields
 #   name         the Gravity name builders write in permissions.tools
 #   slug         the vendor action it routes to; null for a gateway built-in
+#   toolkit      the account a user connects for it (gravity connect); null when none is needed
 #   description  what a builder or a model reads to choose it
 #   scopes       the consent a consumer grants when connecting
 #   breadth      generic: ordinary plumbing any agent might use
@@ -21,6 +22,7 @@
 
 - name: example.echo
   slug: null
+  toolkit: null
   description: echoes back its input, for templates and plumbing tests
   scopes: []
   breadth: generic
@@ -29,6 +31,7 @@
 
 - name: web.search
   slug: COMPOSIO_SEARCH_WEB
+  toolkit: composio_search
   description: search the web; returns results with titles, links and snippets. No account needed
   scopes: []
   breadth: generic
@@ -37,6 +40,7 @@
 
 - name: web.fetch
   slug: COMPOSIO_SEARCH_FETCH_URL_CONTENT
+  toolkit: composio_search
   description: read the text content of a web page by its URL. No account needed
   scopes: []
   breadth: generic
@@ -45,6 +49,7 @@
 
 - name: supadata.get_transcript
   slug: null
+  toolkit: null
   description: fetch the transcript of a YouTube video with the caller's own Supadata API key (api_key argument)
   scopes: []
   breadth: niche
@@ -53,6 +58,7 @@
 
 - name: gmail.read
   slug: GMAIL_FETCH_EMAILS
+  toolkit: gmail
   description: read the connected Gmail inbox
   scopes: [gmail.readonly]
   breadth: generic
@@ -61,6 +67,7 @@
 
 - name: gmail.draft
   slug: GMAIL_CREATE_EMAIL_DRAFT
+  toolkit: gmail
   description: create a Gmail draft
   scopes: [gmail.compose]
   breadth: generic
@@ -69,6 +76,7 @@
 
 - name: gmail.send
   slug: GMAIL_SEND_EMAIL
+  toolkit: gmail
   description: send an email from the connected Gmail
   scopes: [gmail.send]
   breadth: generic
@@ -77,6 +85,7 @@
 
 - name: sheets.read
   slug: GOOGLESHEETS_BATCH_GET
+  toolkit: googlesheets
   description: read values from a connected Google Sheet
   scopes: [sheets]
   breadth: generic
@@ -85,6 +94,7 @@
 
 - name: sheets.append
   slug: GOOGLESHEETS_BATCH_UPDATE
+  toolkit: googlesheets
   description: append a row to a connected Google Sheet
   scopes: [sheets]
   breadth: generic
@@ -93,6 +103,7 @@
 
 - name: slack.send
   slug: SLACK_SEND_MESSAGE
+  toolkit: slack
   description: post a message to a connected Slack channel
   scopes: [slack.chat:write]
   breadth: generic
@@ -101,6 +112,7 @@
 
 - name: slack.list_channels
   slug: SLACK_LIST_ALL_CHANNELS
+  toolkit: slack
   description: list channels in the connected Slack workspace
   scopes: [slack.channels:read]
   breadth: generic
@@ -109,6 +121,7 @@
 
 - name: slack.read_history
   slug: SLACK_FETCH_CONVERSATION_HISTORY
+  toolkit: slack
   description: read message history of a Slack channel
   scopes: [slack.channels:history]
   breadth: generic
@@ -117,6 +130,7 @@
 
 - name: slack.find_user
   slug: SLACK_FIND_USERS
+  toolkit: slack
   description: find a Slack user by name, handle or email, for mentions
   scopes: [slack.users:read]
   breadth: generic
@@ -125,6 +139,7 @@
 
 - name: calendar.read
   slug: GOOGLECALENDAR_EVENTS_LIST
+  toolkit: googlecalendar
   description: list events on the connected Google Calendar
   scopes: [calendar.readonly]
   breadth: generic
@@ -133,6 +148,7 @@
 
 - name: drive.read
   slug: GOOGLEDRIVE_DOWNLOAD_FILE
+  toolkit: googledrive
   description: download a file from the connected Google Drive
   scopes: [drive.readonly]
   breadth: generic
@@ -141,6 +157,7 @@
 
 - name: linear.create_issue
   slug: LINEAR_CREATE_LINEAR_ISSUE
+  toolkit: linear
   description: create an issue in a connected Linear team
   scopes: [linear.write]
   breadth: generic
@@ -149,6 +166,7 @@
 
 - name: linear.list_teams
   slug: LINEAR_LIST_LINEAR_TEAMS
+  toolkit: linear
   description: list the connected Linear workspace teams
   scopes: [linear.read]
   breadth: generic
@@ -157,6 +175,7 @@
 
 - name: linear.list_issues
   slug: LINEAR_LIST_LINEAR_ISSUES
+  toolkit: linear
   description: list open issues in the connected Linear workspace
   scopes: [linear.read]
   breadth: generic
@@ -165,6 +184,7 @@
 
 - name: linear.get_issue
   slug: LINEAR_GET_LINEAR_ISSUE
+  toolkit: linear
   description: read one Linear issue by id
   scopes: [linear.read]
   breadth: generic
@@ -174,6 +194,7 @@
 # GitHub: read-only, for change summaries and contribution profiles.
 - name: github.list_commits
   slug: GITHUB_LIST_COMMITS
+  toolkit: github
   description: list commits on a repository branch, filterable by date range, author or path
   scopes: [repo]
   breadth: generic
@@ -182,6 +203,7 @@
 
 - name: github.get_commit
   slug: GITHUB_GET_A_COMMIT
+  toolkit: github
   description: read one commit with its changed files, line counts and patches
   scopes: [repo]
   breadth: generic
@@ -190,6 +212,7 @@
 
 - name: github.compare
   slug: GITHUB_COMPARE_TWO_COMMITS
+  toolkit: github
   description: compare two refs (base...head) with the commits and changed files between them
   scopes: [repo]
   breadth: generic
@@ -198,6 +221,7 @@
 
 - name: github.list_pull_requests
   slug: GITHUB_LIST_PULL_REQUESTS
+  toolkit: github
   description: list pull requests on a repository, filterable by state and branch
   scopes: [repo]
   breadth: generic
@@ -206,6 +230,7 @@
 
 - name: github.list_pr_files
   slug: GITHUB_LIST_PULL_REQUESTS_FILES
+  toolkit: github
   description: list the files a pull request changes, with line counts and patches
   scopes: [repo]
   breadth: generic
@@ -214,6 +239,7 @@
 
 - name: github.list_pr_reviews
   slug: GITHUB_LIST_REVIEWS_FOR_A_PULL_REQUEST
+  toolkit: github
   description: list the reviews submitted on a pull request
   scopes: [repo]
   breadth: generic
@@ -222,6 +248,7 @@
 
 - name: github.search_issues
   slug: GITHUB_SEARCH_ISSUES_AND_PULL_REQUESTS
+  toolkit: github
   description: search issues and pull requests with GitHub qualifiers (repo:, author:, reviewed-by:, is:pr, created:)
   scopes: [repo]
   breadth: generic
@@ -230,6 +257,7 @@
 
 - name: linkedin.whoami
   slug: LINKEDIN_GET_MY_INFO
+  toolkit: linkedin
   description: read the connected LinkedIn member's id, name and headline (the author of their posts)
   scopes: [linkedin.profile]
   breadth: generic
@@ -238,6 +266,7 @@
 
 - name: linkedin.create_post
   slug: LINKEDIN_CREATE_LINKED_IN_POST
+  toolkit: linkedin
   description: publish a post on LinkedIn as the connected member or an organisation they manage
   scopes: [linkedin.w_member_social]
   breadth: generic