fimo 2.3.0 → 2.3.1-staging.2

package/assets/skills/fimo-cli/references/agents.md

@@ -38,7 +38,7 @@ fimo agents secrets remove <name> <KEY> [-C <dir>]
 ```
 
 - **`list-templates`** — list the bundled starter templates with the first line of each template's `GOAL.md` as a summary. Ships with the CLI binary; no API call. The five bundled templates are `_default`, `seo-audit`, `content-translator`, `broken-link-sweeper`, `post-deploy-check`.
-- **`create <name>`** — scaffold `.fimo/agents/<name>/` from a template (default `_default`, a minimal valid bundle with a manual trigger). `--description <text>` writes a one-line tagline into the scaffolded `config.yaml` (surfaces in the dashboard's agents list). When run **without** `-C`, it requires the cwd to be inside a real Fimo project (walks up for `.fimo/project.json` or legacy `.fimo.settings.json`) and errors out cleanly otherwise, so it never leaks an agent bundle into a stray cwd. If the template declares capabilities, an install-consent flow runs after the copy (`--quiet` skips it; critical caps still abort).
+- **`create <name>`** — scaffold `.fimo/agents/<name>/` from a template (default `_default`, a minimal valid bundle with a manual trigger). `--description <text>` writes a one-line tagline into the scaffolded `config.yaml` (surfaces in the dashboard's agents list). When run **without** `-C`, it requires the cwd to be inside a real Fimo project (walks up for `.fimo/project.json` or legacy `.fimo.settings.json`) and errors out cleanly otherwise, so it never leaks an agent bundle into a stray cwd. If the template declares capabilities, an install-consent flow runs after the copy (`--quiet` skips it; critical caps still abort). Keep the scaffolded `runtime` block as is unless the author asks for a different credit limit; see the `runtime` reference below before adding any limit key.
 - Every generated `config.yaml` includes `model: openai/gpt-5.6-luna`. Change that top-level value to another supported Fimo text model when needed; bundles without `model` keep the Luna fallback. Deploy after changing it because cloud runs use the deployed bundle.
 - **`list`** — list the agents declared under `<project>/.fimo/agents/` (or legacy root `agents/`), with each one's trigger types and capability count. Local — the bundle list is the source of truth even if the project isn't linked yet.
 - **`validate [name]`** — run the full validation pipeline: parse → capability vocabulary → composition (cycle / missing sub-agents / invalid grants) → semantic + Fimo project config policy checks. Omit `name` to validate every bundle. `--json` emits a structured `ValidationReport` for CI; exit code is non-zero on any failure.
@@ -64,19 +64,20 @@ runtime:
   dev: false
   long_running: false
   max_credits: 5000
-  max_steps: 40
 ```
 
 - `cloud` / `dev` — declared boolean environment flags for where the bundle may run.
 - `long_running` — same capability as the `runtime:long_running` token: lets the run exceed the default time limit.
-- `max_credits` — the run's own credit ceiling (integer, credits ≥ 1). The default scaffold template ships
-  `max_credits: 5000` as a visible starter limit. Unset: the run may spend up to the organization's available
-  credits at admission.
-- `max_steps` — cap on model-loop steps for one run (integer ≥ 1). Unset: no step cap; only `max_credits` (or the
-  organization's balance) and the plan's agent-hours bound the run.
+- `max_credits` — the run's own credit ceiling (integer, credits ≥ 1) and the one limit to tune. The default scaffold
+  template ships `max_credits: 5000` as a visible starter limit; raise, lower, or remove it to fit the agent's work.
+  Unset: the run may spend up to the organization's available credits at admission.
+- `max_steps` — advanced cost-management knob, extremely rare: a cap on model-loop steps for one run (integer ≥ 1).
+  Leave it unset unless the author explicitly wants a step-based bound on top of credits. Do not add it when
+  scaffolding a bundle, and do not reach for it to control spend — tune `max_credits` instead. Unset: no step cap;
+  `max_credits` (or the organization's balance) and the plan's agent-hours bound the run.
 
 All five keys are optional; an absent `runtime` block behaves as if every key were unset. There is no platform step cap
-and no legacy per-session cost ceiling — the only stops are these author-owned limits, the organization running out of
+and no platform per-run cost ceiling — the only stops are these author-owned limits, the organization running out of
 credits (`insufficient_credits`), and the agent-hours allowance. A limit that fires records a truthful terminal reason
 (`max_steps`, `budget_exceeded`, `insufficient_credits`, or `finish_run_missing` when a run ends without calling
 `finish_run`), readable via `fimo agents report` and the Studio run page.

package/assets/skills/fimo-cli/references/content.md

@@ -13,7 +13,7 @@ Never remove `isSingleton: true` merely because `fimo entries create` rejects th
 
 ## Flow
 
-1. Write `src/schemas/{Uid}.json` — PascalCase filename (e.g. `BlogPost.json`). Run `fimo skills get fimo-code --ref content/schema` for the JSON contract.
+1. Write `src/schemas/{Uid}.json` — PascalCase filename (e.g. `BlogPost.json`). Run `fimo skills get fimo-code --ref content/schema` to decide what becomes editor-managed content (Single, collection, blocks, references, labels, or `json`) and for the JSON contract.
 2. Run `fimo schemas push {Uid}`. It registers the schema and generates the framework-specific public modules. It does not run whole-project validation.
 3. App code imports generated public modules, never `.types.ts` directly. Load the detected framework reference before choosing server modules, client modules, hooks, or a registry.
 4. Seed collections via `fimo entries create`, or update one-off content via `fimo singles update`. Generate cover images first with `fimo image generate` if needed (see `media.md` / `assets.md`).

package/assets/skills/fimo-cli/references/integrations.md

@@ -55,8 +55,7 @@ fimo integrations enable firecrawl --connection client-a
 
 Bare enable uses the integration's default auth path. For Firecrawl, that is "Use Fimo credits".
 
-If an integration has no safe default auth path, bare enable should stop with a repair command instead of guessing. OAuth
-integrations point to `fimo integrations connect <integration>`. API-key integrations point to
+If an integration has no safe default auth path, bare enable should stop with a repair command instead of guessing. API-key integrations point to
 `fimo integrations connect <integration> --name <name> --token-stdin`, then
 `fimo integrations enable <integration> --connection <name>`.
 
@@ -76,13 +75,14 @@ There is no silent fallback. If a project is enabled with a named API-key connec
 ## Connections
 
 ```bash
-fimo integrations connect slack
 fimo integrations connect firecrawl --name client-a --token-stdin
 fimo integrations enable firecrawl --connection client-a
 ```
 
 Use `connect` for provider accounts, workspaces, OAuth installs, and API-key accounts. Connections live at the organization level and are shared as capabilities, not as visible credentials. A project chooses one by enabling the integration with `--connection <alias>`.
 
+Set up Slack from **Project Settings > Connections** in Fimo Studio. Slack app creation and workspace approval require an explicit organization app choice, so the CLI does not guess one.
+
 ## Run
 
 ```bash

package/assets/skills/fimo-code/references/content/schema.md

@@ -23,6 +23,18 @@ Write one schema per `src/schemas/<Uid>.json`. The PascalCase filename must matc
 
 Required root keys: `uid`, `name`, and `fields`.
 
+## Model what editors manage
+
+Design schemas around what content editors need to see and change in Fimo Studio.
+
+- Use clear, editor-facing names for Singles, collections, fields, blocks, and groups. For example, use `heroHeading` instead of `H1`, and `Testimonial` with the name `Testimonials`. Order and group fields the way editors work through the form.
+- Use labels for small standalone interface copy. Use schemas when content has structure, media, or repeated records.
+- Use a Single for one shared document such as site settings or navigation. Set `isSingleton` at the schema root: `{ "uid": "HomePage", "name": "Homepage", "isSingleton": true, "fields": {} }`. Use a collection for independent records such as posts, products, or team members.
+- Prefer structured fields: `richtext` for formatted prose, `blocks` for repeatable sections, `reference` for shared records, and `media` for assets.
+- Avoid `json` for editor-managed content. Use it only for opaque data that editors do not need to understand or edit.
+
+Keep routing, layout, computed values, and external system data in code. Load `fimo-cli/references/content.md` for the Single and collection write workflows.
+
 ## Group fields in Studio
 
 Use optional top-level `groups` when an entry has meaningful editing areas, such as Overview, Tickets, SEO, or Scheduling. They work best for longer forms where editors regularly work on one area at a time. Usually skip groups for short forms, one-field groups, or vague buckets such as General and Other. Prefer two to five groups organized around editor tasks. This is guidance, not a schema limit.
@@ -46,19 +58,6 @@ Assign each top-level field with `group`; one field may appear in more than one
 
 Group IDs must be unique, at most one group may be the default, and memberships must reference a declared group. Only top-level fields can be grouped; fields inside blocks cannot declare `group`.
 
-Use `"isSingleton": true` whenever the site has exactly one logical document: a homepage, site settings, an About page, or one campaign landing page. Do not turn it into a one-entry collection just to seed content; keep the Single and load `fimo-cli/references/content.md` for the `fimo singles update` workflow.
-
-```json
-{
-  "uid": "HomePage",
-  "name": "Homepage",
-  "isSingleton": true,
-  "fields": {
-    "title": { "type": "string", "required": true }
-  }
-}
-```
-
 ## Locale policy
 
 - Omit `i18n` or use `{ "enabled": true }` for localized variants.

package/dist/cli/bundle.json

@@ -1,7 +1,7 @@
 {
   "bundled": true,
   "bundler": "esbuild",
-  "bundledAt": "2026-09-02T12:32:52.515Z",
+  "bundledAt": "2026-09-03T14:36:18.960Z",
   "cliVersion": "2.3.0",
   "external": [
     "oxc-parser",