@lazyingart/agintiflow 0.20.81 → 0.20.83

package/README.md

@@ -35,13 +35,7 @@ The short version: run `aginti` inside a project, give it a task, inspect what i
 | Product positioning | [references/agintiflow-product-positioning.md](references/agintiflow-product-positioning.md) |
 | Full archived README reference | [references/notes/readme-full-reference-2026-05-05.md](references/notes/readme-full-reference-2026-05-05.md) |
 
-<p align="center">
-  <img src="./demos/agintiflow-cli-launch.jpg" alt="AgInTiFlow interactive CLI launch screen with colorful terminal banner, Docker workspace status, and chat input panel" width="960" />
-</p>
-
-<p align="center">
-  <img src="./demos/agintiflow-web-console-run-output.jpg" alt="AgInTiFlow web console showing conversation history and structured run output" width="960" />
-</p>
+Screenshots are kept out of the README body so the start guide stays readable. View them on the website carousel or in [demos/](demos/) and [website/assets/screenshots/](website/assets/screenshots/).
 
 ## Why This Exists
 
@@ -186,25 +180,17 @@ aginti --resume <session-id> \
   "continue with trusted host access"
 ```
 
-## Real Screenshots
+## Screenshots
 
-| CLI launch | Web console run output |
-| --- | --- |
-| <img src="./demos/agintiflow-cli-launch.jpg" alt="AgInTiFlow CLI launch" width="480" /> | <img src="./demos/agintiflow-web-console-run-output.jpg" alt="AgInTiFlow web console conversation and run output" width="480" /> |
-
-| Web app overview | Task controls |
-| --- | --- |
-| <img src="./website/assets/screenshots/app-overview.jpg" alt="AgInTiFlow web app overview" width="480" /> | <img src="./website/assets/screenshots/task-controls.jpg" alt="AgInTiFlow task controls" width="480" /> |
+The website keeps the visual walkthrough in a carousel so this README can stay focused on setup and usage:
 
-| Conversation history | Sandbox status |
+| View | Link |
 | --- | --- |
-| <img src="./website/assets/screenshots/conversation-history.jpg" alt="AgInTiFlow conversation history" width="480" /> | <img src="./website/assets/screenshots/sandbox-status.jpg" alt="AgInTiFlow sandbox status" width="480" /> |
-
-| Mobile overview |
-| --- |
-| <img src="./website/assets/screenshots/mobile-overview.jpg" alt="AgInTiFlow mobile overview" width="480" /> |
-
-Older launch screenshots are kept in the source repository under [demos/archive/](https://github.com/lazyingart/AgInTiFlow/tree/main/demos/archive).
+| Website carousel | [https://flow.lazying.art/#screenshots](https://flow.lazying.art/#screenshots) |
+| CLI launch | [demos/agintiflow-cli-launch.jpg](demos/agintiflow-cli-launch.jpg) |
+| Web console run output | [demos/agintiflow-web-console-run-output.jpg](demos/agintiflow-web-console-run-output.jpg) |
+| Web app screenshots | [website/assets/screenshots/](website/assets/screenshots/) |
+| Older launch screenshots | [demos/archive/](https://github.com/lazyingart/AgInTiFlow/tree/main/demos/archive) |
 
 ## Core Capabilities
 
@@ -270,7 +256,7 @@ Inside chat:
 /aaps dry-run workflows/main.aaps
 ```
 
-Use AAPS when the task is bigger than a single chat: app development with stages, paper/book workflows, validation gates, recovery steps, artifact production, or top-down agentic scripts. See [docs/aaps.md](docs/aaps.md) and the package [https://www.npmjs.com/package/@lazyingart/aaps](https://www.npmjs.com/package/@lazyingart/aaps).
+Use AAPS when the task is bigger than a single chat: app development with stages, paper/book workflows, validation gates, recovery steps, artifact production, or top-down agentic scripts. The current adapter is intentionally lightweight: prompt-only AAPS tasks are reported as handoffs and do not automatically execute an LLM/backend agent yet, so AgInTiFlow warns when a run has no executable steps or misses a declared output. See [docs/aaps.md](docs/aaps.md) and the package [https://www.npmjs.com/package/@lazyingart/aaps](https://www.npmjs.com/package/@lazyingart/aaps).
 
 ## Local API Quick Reference
 

package/docs/aaps.md

@@ -42,6 +42,8 @@ The adapter keeps paths project-relative and uses `execFile`, not shell interpol
 
 `compile check` and `validate` are the recommended first checks. `run` can execute commands declared by the `.aaps` workflow, so treat it like any other project execution step and run only workflows you intend to execute.
 
+Current lightweight adapter boundary: prompt-only AAPS tasks are recorded as handoffs. They do not automatically call an LLM/backend agent yet. When a workflow has prompt-only steps, `aginti aaps run` and `aginti aaps dry-run` print `promptOnly=<n>` plus warnings if no executable steps ran or a declared output was not produced.
+
 `aginti aaps install` installs `@lazyingart/aaps` as a project dev dependency only when the current project has `package.json`. Use `aginti aaps install global` only when you intentionally want a global npm install.
 
 ## Project Shape
@@ -56,7 +58,7 @@ runs/
 artifacts/
 ```
 
-The starter workflow is deliberately simple: it defines a planner agent and a `draft_plan` task that writes `reports/aaps-plan.md`. Use it as a safe scaffold, then expand the workflow with blocks, validations, recovery steps, and review gates.
+The starter workflow is deliberately simple: it defines a planner agent and a `draft_plan` task whose declared output is `reports/aaps-plan.md`. With the current lightweight adapter this task is prompt-only, so `run` produces durable run metadata and a handoff warning rather than writing the plan itself. Use AgInTiFlow to act on that handoff, or expand the workflow with executable actions, validations, recovery steps, and review gates.
 
 ## When To Use AAPS
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lazyingart/agintiflow",
-  "version": "0.20.81",
+  "version": "0.20.83",
   "type": "module",
   "description": "Low-cost, project-aware Web and CLI agents with DeepSeek/Venice/OpenAI routing, visible tool calls, durable sessions, scouts, AAPS, SCS, and guarded local execution.",
   "license": "Apache-2.0",