@leanandmean/coding-agent 0.74.1-scramjet.34 → 0.74.1-scramjet.39

package/docs/extensions.md

@@ -288,8 +288,12 @@ user sends prompt ────────────────────
   │   ┌─── turn (repeats while LLM calls tools) ───┐       │
   │   │                                            │       │
   │   ├─► turn_start                               │       │
+  │   ├─► routing refresh                          │       │
   │   ├─► context (can modify messages)            │       │
+  │   ├─► before_provider_call (can replace request-local system prompt)
+  │   ├─► provider serialization                   │       │
   │   ├─► before_provider_request (can inspect or replace payload)
+  │   ├─► transport                                │       │
   │   ├─► after_provider_response (status + headers, before stream consume)
   │   │                                            │       │
   │   │   LLM responds, may call tools:            │       │
@@ -630,14 +634,29 @@ pi.on("context", async (event, ctx) => {
 });
 ```
 
+#### before_provider_call
+
+Fired after request routing and message-context transformation, immediately before provider serialization. `event.model` is an immutable, handler-isolated snapshot of the exact model routed for this call, and `event.systemPrompt` is its request-local provider-neutral prompt (`string` or `SystemPromptSection[]`). Return `{ systemPrompt }` to replace only this call's prompt. Replacements chain in extension load order and never accumulate in session state.
+
+```typescript
+pi.on("before_provider_call", (event) => {
+  return {
+    systemPrompt: typeof event.systemPrompt === "string"
+      ? `${event.systemPrompt}\n\nRequest routed to ${event.model.provider}/${event.model.id}`
+      : [...event.systemPrompt, { id: "routed-model", text: `\n\nRequest routed to ${event.model.provider}/${event.model.id}` }],
+  };
+});
+```
+
 #### before_provider_request
 
-Fired after the provider-specific payload is built, right before the request is sent. Handlers run in extension load order. Returning `undefined` keeps the payload unchanged. Returning any other value replaces the payload for later handlers and for the actual request.
+Fired after the provider-specific payload is built, right before transport. `event.model` is a fresh immutable snapshot of the same exact routed model exposed by `before_provider_call`; mutating one handler's snapshot cannot affect later handlers or transport routing. Handlers run in extension load order. Returning `undefined` keeps the payload unchanged. Returning any other value replaces the payload for later handlers and for the actual request.
 
-This hook can rewrite provider-level system instructions or remove them entirely. Those payload-level changes are not reflected by `ctx.getSystemPrompt()`, which reports Scramjet's system prompt string rather than the final serialized provider payload.
+This hook can rewrite provider-level system instructions or remove them entirely. Those payload-level changes are not reflected by `ctx.getSystemPrompt()`, which reports Scramjet's stored system prompt string rather than request-local `before_provider_call` changes or the final serialized provider payload.
 
 ```typescript
-pi.on("before_provider_request", (event, ctx) => {
+pi.on("before_provider_request", (event) => {
+  console.log(`${event.model.provider}/${event.model.id}`);
   console.log(JSON.stringify(event.payload, null, 2));
 
   // Optional: replace payload
@@ -645,7 +664,7 @@ pi.on("before_provider_request", (event, ctx) => {
 });
 ```
 
-This is mainly useful for debugging provider serialization and cache behavior.
+The complete request order is routing refresh → `context` transformation → `before_provider_call` → provider serialization → `before_provider_request` → transport. This is mainly useful for request-local prompt preparation and debugging provider serialization or cache behavior.
 
 #### after_provider_response
 
@@ -995,6 +1014,7 @@ Returns Scramjet's current system prompt string.
 
 - During `before_agent_start`, this reflects chained system-prompt changes made so far for the current turn.
 - It does not include later `context` message mutations.
+- It does not include request-local `before_provider_call` prompt replacements.
 - It does not include `before_provider_request` payload rewrites.
 - If later-loaded extensions run after yours, they can still change what is ultimately sent.
 

package/docs/models.md

@@ -91,6 +91,8 @@ Override defaults when you need specific values:
 
 The file reloads each time you open `/model`. Edit during session; no restart needed.
 
+When valid history exists, `/model` and `/scoped-models` append a recent median output-rate estimate to the requested provider/model row. The estimate uses normalized final output usage over first-to-last generated output, excluding time to first token and trailing completion latency; no placeholder is shown for models without history.
+
 ## Google AI Studio Example
 
 Use `google-generative-ai` with a `baseUrl` to add models from Google AI Studio, including custom Gemma 4 entries:

package/docs/session-format.md

@@ -81,6 +81,7 @@ interface UserMessage {
 interface AssistantMessage {
   role: "assistant";
   content: (TextContent | ThinkingContent | ToolCall)[];
+  origin?: "provider" | "harness";  // Explicit for new messages; absent in legacy sessions
   api: string;
   provider: string;
   model: string;
@@ -203,7 +204,7 @@ A message in the conversation. The `message` field contains an `AgentMessage`.
 
 ```json
 {"type":"message","id":"a1b2c3d4","parentId":"prev1234","timestamp":"2024-12-03T14:00:01.000Z","message":{"role":"user","content":"Hello"}}
-{"type":"message","id":"b2c3d4e5","parentId":"a1b2c3d4","timestamp":"2024-12-03T14:00:02.000Z","message":{"role":"assistant","content":[{"type":"text","text":"Hi!"}],"provider":"anthropic","model":"claude-sonnet-4-5","usage":{...},"stopReason":"stop"}}
+{"type":"message","id":"b2c3d4e5","parentId":"a1b2c3d4","timestamp":"2024-12-03T14:00:02.000Z","message":{"role":"assistant","content":[{"type":"text","text":"Hi!"}],"origin":"provider","provider":"anthropic","model":"claude-sonnet-4-5","usage":{...},"stopReason":"stop"}}
 {"type":"message","id":"c3d4e5f6","parentId":"b2c3d4e5","timestamp":"2024-12-03T14:00:03.000Z","message":{"role":"toolResult","toolCallId":"call_123","toolName":"bash","content":[{"type":"text","text":"output"}],"isError":false}}
 ```
 

package/docs/skills.md

@@ -141,7 +141,7 @@ Per the [Agent Skills specification](https://agentskills.io/specification#frontm
 | Field | Required | Description |
 |-------|----------|-------------|
 | `name` | Yes | Max 64 chars. Lowercase a-z, 0-9, hyphens. Unlike the standard, Scramjet does not require this to match the parent directory because that standard requirement is suboptimal for shared skill directories. |
-| `description` | Yes | Max 1024 chars. What the skill does and when to use it. |
+| `description` | Yes | The Agent Skills specification maximum is 1024 chars. Scramjet warns above this limit but retains the complete description in the generated model-visible skills list unless model invocation is disabled. |
 | `license` | No | License name or reference to bundled file. |
 | `compatibility` | No | Max 500 chars. Environment requirements. |
 | `metadata` | No | Arbitrary key-value mapping. |
@@ -179,7 +179,7 @@ Scramjet validates skills against the Agent Skills standard. Most issues produce
 
 - Name exceeds 64 characters or contains invalid characters
 - Name starts/ends with hyphen or has consecutive hyphens
-- Description exceeds 1024 characters
+- Description exceeds the Agent Skills specification maximum of 1024 characters. This warning is advisory: Scramjet retains the complete description in the generated model-visible skills list unless `disable-model-invocation` is `true`.
 
 Unknown frontmatter fields are ignored.
 

package/docs/usage.md

@@ -11,7 +11,9 @@ The interface has four main areas:
 - **Startup header** - shortcuts, loaded context files, prompt templates, skills, and extensions
 - **Messages** - user messages, assistant responses, tool calls, tool results, notifications, errors, and extension UI
 - **Editor** - where you type; border color indicates the current thinking level
-- **Footer** - working directory, session name, token/cache usage, cost, context usage, and current model
+- **Footer** - working directory, session name, token/cache usage, cost, context usage, current model, and output speed when valid data exists
+
+The footer shows the current model's recent median output-rate estimate beside a nonzero session output total when valid history exists. The `/model` and `/scoped-models` selectors annotate every model row that has valid history. Completed and historical estimates use normalized final output usage over the interval from the first to last generated output; they exclude time to first token and trailing completion latency.
 
 The editor can be replaced temporarily by built-in UI such as `/settings` or by custom extension UI.
 

package/package.json

@@ -1,11 +1,15 @@
 {
   "name": "@leanandmean/coding-agent",
-  "version": "0.74.1-scramjet.34",
+  "version": "0.74.1-scramjet.39",
   "publishConfig": {
     "access": "public"
   },
   "description": "Coding agent CLI with read, bash, edit, write tools and session management",
   "license": "Apache-2.0",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/LeanAndMean/scramjet.git"
+  },
   "type": "module",
   "piConfig": {
     "name": "scramjet",
@@ -33,9 +37,9 @@
     "test": "vitest --run --passWithNoTests"
   },
   "dependencies": {
-    "@leanandmean/agent": "0.74.1-scramjet.15",
-    "@leanandmean/ai": "0.74.1-scramjet.11",
-    "@leanandmean/tui": "0.74.1-scramjet.10",
+    "@leanandmean/agent": "0.74.1-scramjet.18",
+    "@leanandmean/ai": "0.74.1-scramjet.14",
+    "@leanandmean/tui": "0.74.1-scramjet.11",
     "@silvia-odwyer/photon-node": "^0.3.4",
     "chalk": "^5.5.0",
     "dictionary-en": "^4.0.0",