agim-cli 1.2.147 → 1.2.148

package/dist/core/skills/builtin/tinystruct-patterns/references/database.md

@@ -0,0 +1,99 @@
+# tinystruct Database Persistence
+
+## When to Use
+
+Use the built-in ORM-like data layer for database operations. It provides a lightweight alternative to JPA/Hibernate using POJOs extending `AbstractData` and XML mapping files.
+
+## How It Works
+
+### Architecture
+
+Each table is represented by:
+1. **Java POJO**: Extends `AbstractData`, provides getters/setters and `setData(Row)`.
+2. **Mapping XML**: `ClassName.map.xml` in resources, binding Java fields to DB columns.
+
+#### Key Base Class: `AbstractData`
+Provides CRUD methods:
+- `append()` / `appendAndGetId()`
+- `update()`
+- `delete()`
+- `findAll()` / `findOneById()` / `findOneByKey(key, value)`
+- `findWith(where, params)`
+- `find(SQL, params)`
+
+### POJO Generation (CLI)
+
+Introspect a live database table to produce the POJO and mapping file.
+
+#### Configuration
+`application.properties`:
+```properties
+driver=com.mysql.cj.jdbc.Driver
+database.url=jdbc:mysql://localhost:3306/mydb
+database.user=root
+database.password=secret
+```
+
+#### Command
+```bash
+# Interactive mode
+bin/dispatcher generate
+
+# Specify table
+bin/dispatcher generate --tables users
+```
+
+## Examples
+
+### CRUD Operations
+```java
+// CREATE
+User user = new User();
+user.setUsername("james");
+user.append();
+
+// READ
+User user = new User();
+user.setId(42);
+user.findOneById();
+
+// UPDATE
+user.setEmail("new@example.com");
+user.update();
+
+// DELETE
+user.delete();
+```
+
+### Querying with Conditions
+```java
+User user = new User();
+Table results = user.findWith("username LIKE ?", new Object[]{"%jam%"});
+
+// Fluent Condition Builder
+Condition condition = new Condition();
+condition.setRequestFields("id,username");
+Table filtered = user.find(
+    condition.select("`users`").and("email LIKE ?").orderBy("id DESC"),
+    new Object[]{"%@example.com"}
+);
+```
+
+### Mapping XML Structure
+`User.map.xml`:
+```xml
+<mapping>
+  <class name="User" table="users">
+    <id name="Id" column="id" increment="true" generate="false" length="11" type="int"/>
+    <property name="username" column="username" length="50" type="varchar"/>
+    <property name="email" column="email" length="100" type="varchar"/>
+  </class>
+</mapping>
+```
+
+## Important Rules
+
+1. **File Placement**: The mapping XML **must** mirror the POJO's package path under `src/main/resources/`.
+2. **Naming**: Table names are singularized for class names (`users` → `User`). Underscored columns become camelCase fields (`created_at` → `createdAt`).
+3. **Setters**: Use `setFieldAsXxx` methods (e.g., `setFieldAsString`) in setters to sync state with the internal field map.
+4. **Id Field**: The primary key field in Java is always named `Id` (inherited from `AbstractData`).

package/dist/core/skills/builtin/tinystruct-patterns/references/routing.md

@@ -0,0 +1,64 @@
+# tinystruct @Action Routing Reference
+
+## When to Use
+
+Use the `@Action` annotation in your applications to define routes for both CLI commands and HTTP endpoints. It is appropriate whenever you need to map logic to a specific path, handle parameterized requests, or restrict execution to specific HTTP methods while maintaining a consistent command structure across environments.
+
+## How It Works
+
+The `ActionRegistry` parses `@Action` annotations to build a routing table. For parameterized methods, the framework automatically maps Java parameter types to corresponding regex segments.
+
+### Regex Generation Rules
+- `getUser(int id)` → pattern: `^/?user/(-?\d+)$`
+- `search(String query)` → pattern: `^/?search/([^/]+)$`
+
+Supported parameter types: `String`, `int/Integer`, `long/Long`, `float/Float`, `double/Double`, `boolean/Boolean`, `char/Character`, `short/Short`, `byte/Byte`, `Date` (parsed as `yyyy-MM-dd HH:mm:ss`).
+
+### Mode Values
+
+| Mode | When it triggers |
+|---|---|
+| `DEFAULT` | Both CLI and HTTP (GET, POST, etc.) |
+| `CLI` | CLI dispatcher only |
+| `HTTP_GET` | HTTP GET only |
+| `HTTP_POST` | HTTP POST only |
+| `HTTP_PUT` | HTTP PUT only |
+| `HTTP_DELETE` | HTTP DELETE only |
+| `HTTP_PATCH` | HTTP PATCH only |
+
+> **Note:** You can map HTTP method names to `Mode` using `Action.Mode.fromName(String methodName)`. Unknown or null values return `Mode.DEFAULT`.
+
+## Examples
+
+### Basic Action Declaration
+```java
+@Action(
+    value = "path/subpath",          // required: URI segment or CLI command
+    description = "What it does",    // shown in --help output
+    mode = Mode.DEFAULT,             // default: Mode.DEFAULT
+    example = "bin/dispatcher path/subpath/42"
+)
+public String myAction(int id) { ... }
+```
+
+### Parameterized Paths
+```java
+@Action("user/{id}")
+public String getUser(int id) { ... }
+// → CLI: bin/dispatcher user/42
+// → HTTP: /?q=user/42
+```
+
+### Dependency Injection
+`ActionRegistry` automatically injects `Request` and/or `Response` from `Context` if they are parameters:
+
+```java
+@Action(value = "upload", mode = Mode.HTTP_POST)
+public String upload(Request<?, ?> req, Response<?, ?> res) throws ApplicationException {
+    // Access raw request/response if needed
+    return "ok";
+}
+```
+
+### Path Matching Priority
+If two methods share the same path, the framework uses the first match in the `ActionRegistry`. Use explicit `Mode` values to disambiguate (e.g., separating a GET for a form and a POST for submission).

package/dist/core/skills/builtin/tinystruct-patterns/references/system-usage.md

@@ -0,0 +1,97 @@
+# tinystruct System and Usage Reference
+
+## When to Use
+
+Use these patterns to handle request state, manage web sessions, implement Server-Sent Events (SSE), handle file uploads, or perform outbound HTTP networking.
+
+## How It Works
+
+### Context and CLI Arguments
+`Context` is the primary data store for request-specific state. CLI flags passed as `--key value` are stored in `Context` as `"--key"`.
+
+### Session Management
+Pluggable architecture. Default is `MemorySessionRepository`. Configure Redis in `application.properties`:
+```properties
+default.session.repository=org.tinystruct.http.RedisSessionRepository
+redis.host=127.0.0.1
+redis.port=6379
+```
+
+### Server-Sent Events (SSE)
+Built-in support for real-time push. The `HttpServer` automatically handles the SSE lifecycle when it detects the `Accept: text/event-stream` header. Connections are tracked by session ID in `SSEPushManager`.
+
+### Outbound Networking
+Use `URLRequest` and `HTTPHandler` for making HTTP requests to external services.
+
+## Examples
+
+### Context and CLI Arguments
+```java
+@Action("echo")
+public String echo() {
+    // CLI: bin/dispatcher echo --words "Hello World"
+    Object words = getContext().getAttribute("--words");
+    if (words != null) return words.toString();
+    return "No words provided";
+}
+```
+
+### Session Management
+```java
+@Action(value = "login", mode = Mode.HTTP_POST)
+public String login(Request<?, ?> request) {
+    request.getSession().setAttribute("userId", "42");
+    return "Logged in";
+}
+```
+
+### Server-Sent Events (SSE)
+```java
+@Action("sse/connect")
+public String connect() {
+    return "{\"type\":\"connect\",\"message\":\"Connected\"}";
+}
+
+// In another method or event handler:
+String sessionId = getContext().getId();
+SSEPushManager.getInstance().push(sessionId, new Builder().put("msg", "hello"));
+```
+
+### File Uploads
+```java
+import org.tinystruct.data.FileEntity;
+
+@Action(value = "upload", mode = Mode.HTTP_POST)
+public String upload(Request<?, ?> request) throws ApplicationException {
+    List<FileEntity> files = request.getAttachments();
+    if (files != null) {
+        for (FileEntity file : files) {
+            // file.getFilename(), file.getContent()
+        }
+    }
+    return "Uploaded";
+}
+```
+
+### Outbound HTTP
+```java
+import org.tinystruct.net.URLRequest;
+import org.tinystruct.net.handlers.HTTPHandler;
+
+URLRequest request = new URLRequest(new URL("https://api.example.com"));
+request.setMethod("POST").setBody("{\"data\":\"val\"}");
+
+HTTPHandler handler = new HTTPHandler();
+var response = handler.handleRequest(request);
+if (response.getStatusCode() == 200) {
+    String body = response.getBody();
+}
+```
+
+### Event System
+Register handlers in `init()` for asynchronous task execution.
+```java
+EventDispatcher.getInstance().registerHandler(MyEvent.class, event -> {
+    CompletableFuture.runAsync(() -> doHeavyWork(event.getPayload()));
+});
+```

package/dist/core/skills/builtin/tinystruct-patterns/references/testing.md

@@ -0,0 +1,72 @@
+# tinystruct Testing Patterns
+
+## When to Use
+
+Use these patterns when writing unit tests for your applications with **JUnit 5**. Essential for verifying action logic, routing registration, and HTTP mode behavior.
+
+## How It Works
+
+### Unit Testing Applications
+ActionRegistry is a singleton. To test an application:
+1. Instantiate the application.
+2. Provide a `Settings` object (triggers `init()` and annotation processing).
+3. Use `app.invoke(path, args)` to test logic directly.
+
+### HTTP Integration Testing
+For tests involving the built-in HTTP server:
+1. Start `HttpServer` in a background thread.
+2. Use `ApplicationManager.call("start", context, Action.Mode.CLI)` to boot.
+3. Wait for the port to be open using a `Socket`.
+4. Use `URLRequest` and `HTTPHandler` to perform actual requests.
+
+## Examples
+
+### Unit Test
+```java
+import org.junit.jupiter.api.*;
+import org.tinystruct.system.Settings;
+
+class MyAppTest {
+    private MyApp app;
+
+    @BeforeEach
+    void setUp() {
+        app = new MyApp();
+        app.setConfiguration(new Settings());
+        app.init(); // triggers @Action annotation processing and registers all actions
+    }
+
+    @Test
+    void testHello() throws Exception {
+        Object result = app.invoke("hello");
+        Assertions.assertEquals("Hello!", result);
+    }
+
+    @Test
+    void testGreet() throws Exception {
+        Object result = app.invoke("greet", new Object[]{"James"});
+        Assertions.assertEquals("Hello, James!", result);
+    }
+}
+```
+
+### ActionRegistry Match Testing
+```java
+@Test
+void testRouting() {
+    ActionRegistry registry = ActionRegistry.getInstance();
+    Action action = registry.getAction("greet/James");
+    Assertions.assertNotNull(action);
+}
+```
+
+### HTTP Integration Pattern
+Reference: `src/test/java/org/tinystruct/system/HttpServerHttpModeTest.java`
+
+```java
+// Pattern:
+// 1. Start server in thread
+// 2. Poll for port availability
+// 3. Send HTTP request via HTTPHandler
+// 4. Assert response body/status
+```

package/dist/core/skills/builtin/token-budget-advisor/SKILL.md

@@ -0,0 +1,133 @@
+---
+name: token-budget-advisor
+description: [ECC] >-
+  Offers the user an informed choice about how much response depth to
+  consume before answering. Use this skill when the user explicitly
+  wants to control response length, depth, or token budget.
+  TRIGGER when: "token budget", "token count", "token usage", "token limit",
+  "response length", "answer depth", "short version", "brief answer",
+  "detailed answer", "exhaustive answer", "respuesta corta vs larga",
+  "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión
+  corta", "quiero controlar cuánto usas", or clear variants where the
+  user is explicitly asking to control answer size or depth.
+  DO NOT TRIGGER when: user has already specified a level in the current
+  session (maintain it), the request is clearly a one-word answer, or
+  "token" refers to auth/session/payment tokens rather than response size.
+origin: community
+---
+
+# Token Budget Advisor (TBA)
+
+Intercept the response flow to offer the user a choice about response depth **before** Claude answers.
+
+## When to Use
+
+- User wants to control how long or detailed a response is
+- User mentions tokens, budget, depth, or response length
+- User says "short version", "tldr", "brief", "al 25%", "exhaustive", etc.
+- Any time the user wants to choose depth/detail level upfront
+
+**Do not trigger** when: user already set a level this session (maintain it silently), or the answer is trivially one line.
+
+## How It Works
+
+### Step 1 — Estimate input tokens
+
+Use the repository's canonical context-budget heuristics to estimate the prompt's token count mentally.
+
+Use the same calibration guidance as [context-budget](../context-budget/SKILL.md):
+
+- prose: `words × 1.3`
+- code-heavy or mixed/code blocks: `chars / 4`
+
+For mixed content, use the dominant content type and keep the estimate heuristic.
+
+### Step 2 — Estimate response size by complexity
+
+Classify the prompt, then apply the multiplier range to get the full response window:
+
+| Complexity   | Multiplier range | Example prompts                                      |
+|--------------|------------------|------------------------------------------------------|
+| Simple       | 3× – 8×          | "What is X?", yes/no, single fact                   |
+| Medium       | 8× – 20×         | "How does X work?"                                  |
+| Medium-High  | 10× – 25×        | Code request with context                           |
+| Complex      | 15× – 40×        | Multi-part analysis, comparisons, architecture      |
+| Creative     | 10× – 30×        | Stories, essays, narrative writing                  |
+
+Response window = `input_tokens × mult_min` to `input_tokens × mult_max` (but don’t exceed your model’s configured output-token limit).
+
+### Step 3 — Present depth options
+
+Present this block **before** answering, using the actual estimated numbers:
+
+```
+Analyzing your prompt...
+
+Input: ~[N] tokens  |  Type: [type]  |  Complexity: [level]  |  Language: [lang]
+
+Choose your depth level:
+
+[1] Essential   (25%)  ->  ~[tokens]   Direct answer only, no preamble
+[2] Moderate    (50%)  ->  ~[tokens]   Answer + context + 1 example
+[3] Detailed    (75%)  ->  ~[tokens]   Full answer with alternatives
+[4] Exhaustive (100%)  ->  ~[tokens]   Everything, no limits
+
+Which level? (1-4 or say "25% depth", "50% depth", "75% depth", "100% depth")
+
+Precision: heuristic estimate ~85-90% accuracy (±15%).
+```
+
+Level token estimates (within the response window):
+- 25%  → `min + (max - min) × 0.25`
+- 50%  → `min + (max - min) × 0.50`
+- 75%  → `min + (max - min) × 0.75`
+- 100% → `max`
+
+### Step 4 — Respond at the chosen level
+
+| Level            | Target length       | Include                                             | Omit                                              |
+|------------------|---------------------|-----------------------------------------------------|---------------------------------------------------|
+| 25% Essential    | 2-4 sentences max   | Direct answer, key conclusion                       | Context, examples, nuance, alternatives           |
+| 50% Moderate     | 1-3 paragraphs      | Answer + necessary context + 1 example              | Deep analysis, edge cases, references             |
+| 75% Detailed     | Structured response | Multiple examples, pros/cons, alternatives          | Extreme edge cases, exhaustive references         |
+| 100% Exhaustive  | No restriction      | Everything — full analysis, all code, all perspectives | Nothing                                        |
+
+## Shortcuts — skip the question
+
+If the user already signals a level, respond at that level immediately without asking:
+
+| What they say                                      | Level |
+|----------------------------------------------------|-------|
+| "1" / "25% depth" / "short version" / "brief answer" / "tldr"  | 25%   |
+| "2" / "50% depth" / "moderate depth" / "balanced answer"        | 50%   |
+| "3" / "75% depth" / "detailed answer" / "thorough answer"       | 75%   |
+| "4" / "100% depth" / "exhaustive answer" / "full deep dive"     | 100%  |
+
+If the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it.
+
+## Precision note
+
+This skill uses heuristic estimation — no real tokenizer. Accuracy ~85-90%, variance ±15%. Always show the disclaimer.
+
+## Examples
+
+### Triggers
+
+- "Give me the short version first."
+- "How many tokens will your answer use?"
+- "Respond at 50% depth."
+- "I want the exhaustive answer, not the summary."
+- "Dame la version corta y luego la detallada."
+
+### Does Not Trigger
+
+- "What is a JWT token?"
+- "The checkout flow uses a payment token."
+- "Is this normal?"
+- "Complete the refactor."
+- Follow-up questions after the user already chose a depth for the session
+
+## Source
+
+Standalone skill from [TBA — Token Budget Advisor for Claude Code](https://github.com/Xabilimon1/Token-Budget-Advisor-Claude-Code-).
+Original project also ships a Python estimator script, but this repository keeps the skill self-contained and heuristic-only.