@psnext/slingcli 2.5.20260727-1 → 2.5.20260731-1

package/node_modules/@aws-sdk/credential-provider-process/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/credential-provider-process",
-  "version": "3.972.61",
+  "version": "3.972.65",
   "description": "AWS credential provider that sources credential_process from ~/.aws/credentials and ~/.aws/config",
   "keywords": [
     "aws",
@@ -43,9 +43,9 @@
     "test:watch": "yarn g:vitest watch"
   },
   "dependencies": {
-    "@aws-sdk/core": "^3.977.0",
+    "@aws-sdk/core": "^3.977.4",
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
+    "@smithy/core": "^3.31.1",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/credential-provider-sso/node_modules/@aws-sdk/token-providers/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/token-providers",
-  "version": "3.1095.0",
+  "version": "3.1100.0",
   "description": "A collection of token providers",
   "keywords": [
     "aws",
@@ -48,10 +48,10 @@
     "test:integration:watch": "yarn g:vitest watch -c vitest.config.integ.mts"
   },
   "dependencies": {
-    "@aws-sdk/core": "^3.977.0",
-    "@aws-sdk/nested-clients": "^3.997.35",
+    "@aws-sdk/core": "^3.977.4",
+    "@aws-sdk/nested-clients": "^3.997.39",
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
+    "@smithy/core": "^3.31.1",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/credential-provider-sso/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/credential-provider-sso",
-  "version": "3.973.5",
+  "version": "3.973.9",
   "description": "AWS credential provider that exchanges a resolved SSO login token file for temporary AWS credentials",
   "keywords": [
     "aws",
@@ -45,11 +45,11 @@
     "test:integration:watch": "yarn g:vitest watch -c vitest.config.integ.mts"
   },
   "dependencies": {
-    "@aws-sdk/core": "^3.977.0",
-    "@aws-sdk/nested-clients": "^3.997.35",
-    "@aws-sdk/token-providers": "3.1095.0",
+    "@aws-sdk/core": "^3.977.4",
+    "@aws-sdk/nested-clients": "^3.997.39",
+    "@aws-sdk/token-providers": "3.1100.0",
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
+    "@smithy/core": "^3.31.1",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/credential-provider-web-identity/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/credential-provider-web-identity",
-  "version": "3.972.67",
+  "version": "3.972.71",
   "description": "AWS credential provider that calls STS assumeRole for temporary AWS credentials",
   "keywords": [
     "aws",
@@ -50,10 +50,10 @@
     "test:watch": "yarn g:vitest watch"
   },
   "dependencies": {
-    "@aws-sdk/core": "^3.977.0",
-    "@aws-sdk/nested-clients": "^3.997.35",
+    "@aws-sdk/core": "^3.977.4",
+    "@aws-sdk/nested-clients": "^3.997.39",
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
+    "@smithy/core": "^3.31.1",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/eventstream-handler-node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/eventstream-handler-node",
-  "version": "3.972.30",
+  "version": "3.972.31",
   "homepage": "https://github.com/aws/aws-sdk-js-v3/tree/main/packages-internal/eventstream-handler-node",
   "license": "Apache-2.0",
   "author": {
@@ -39,7 +39,7 @@
   },
   "dependencies": {
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
+    "@smithy/core": "^3.31.1",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/middleware-eventstream/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/middleware-eventstream",
-  "version": "3.972.25",
+  "version": "3.972.26",
   "homepage": "https://github.com/aws/aws-sdk-js-v3/tree/main/packages-internal/middleware-eventstream",
   "license": "Apache-2.0",
   "author": {
@@ -40,7 +40,7 @@
   },
   "dependencies": {
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
+    "@smithy/core": "^3.31.1",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/middleware-websocket/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/middleware-websocket",
-  "version": "3.972.43",
+  "version": "3.972.47",
   "homepage": "https://github.com/aws/aws-sdk-js-v3/tree/main/packages-internal/middleware-websocket",
   "license": "Apache-2.0",
   "author": {
@@ -40,11 +40,11 @@
     "test:integration:watch": "yarn g:vitest watch -c vitest.config.integ.mts"
   },
   "dependencies": {
-    "@aws-sdk/core": "^3.977.0",
+    "@aws-sdk/core": "^3.977.4",
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
-    "@smithy/fetch-http-handler": "^5.6.10",
-    "@smithy/signature-v4": "^5.6.9",
+    "@smithy/core": "^3.31.1",
+    "@smithy/fetch-http-handler": "^5.6.13",
+    "@smithy/signature-v4": "^5.6.12",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/nested-clients/dist-cjs/submodules/cognito-identity/index.js

@@ -83,7 +83,7 @@ const commonParams = {
     UseDualStack: { type: "builtInParams", name: "useDualstackEndpoint" },
 };
 
-var version = "3.997.34";
+var version = "3.997.38";
 var packageInfo = {
 	version: version};
 

package/node_modules/@aws-sdk/nested-clients/dist-cjs/submodules/signin/index.js

@@ -78,7 +78,7 @@ const commonParams = {
     UseDualStack: { type: "builtInParams", name: "useDualstackEndpoint" },
 };
 
-var version = "3.997.34";
+var version = "3.997.38";
 var packageInfo = {
 	version: version};
 

package/node_modules/@aws-sdk/nested-clients/dist-cjs/submodules/sso/index.js

@@ -78,7 +78,7 @@ const commonParams = {
     UseDualStack: { type: "builtInParams", name: "useDualstackEndpoint" },
 };
 
-var version = "3.997.34";
+var version = "3.997.38";
 var packageInfo = {
 	version: version};
 

package/node_modules/@aws-sdk/nested-clients/dist-cjs/submodules/sso-oidc/index.js

@@ -78,7 +78,7 @@ const commonParams = {
     UseDualStack: { type: "builtInParams", name: "useDualstackEndpoint" },
 };
 
-var version = "3.997.34";
+var version = "3.997.38";
 var packageInfo = {
 	version: version};
 

package/node_modules/@aws-sdk/nested-clients/dist-cjs/submodules/sts/index.js

@@ -258,7 +258,7 @@ const commonParams = {
     UseDualStack: { type: "builtInParams", name: "useDualstackEndpoint" },
 };
 
-var version = "3.997.34";
+var version = "3.997.38";
 var packageInfo = {
 	version: version};
 

package/node_modules/@aws-sdk/nested-clients/node_modules/@smithy/node-http-handler/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@smithy/node-http-handler",
-  "version": "4.9.11",
+  "version": "4.9.13",
   "description": "Provides a way to make requests",
   "homepage": "https://github.com/smithy-lang/smithy-typescript/tree/main/packages/node-http-handler",
   "license": "Apache-2.0",
@@ -43,7 +43,7 @@
     "test:watch": "yarn g:vitest watch"
   },
   "dependencies": {
-    "@smithy/core": "^3.30.0",
+    "@smithy/core": "^3.31.1",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/nested-clients/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/nested-clients",
-  "version": "3.997.35",
+  "version": "3.997.39",
   "description": "Nested clients for AWS SDK packages.",
   "homepage": "https://github.com/aws/aws-sdk-js-v3/tree/main/packages/nested-clients",
   "license": "Apache-2.0",
@@ -100,12 +100,12 @@
     "test:watch": "yarn g:vitest watch"
   },
   "dependencies": {
-    "@aws-sdk/core": "^3.977.0",
-    "@aws-sdk/signature-v4-multi-region": "^3.996.42",
+    "@aws-sdk/core": "^3.977.4",
+    "@aws-sdk/signature-v4-multi-region": "^3.996.43",
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/core": "^3.29.8",
-    "@smithy/fetch-http-handler": "^5.6.10",
-    "@smithy/node-http-handler": "^4.9.10",
+    "@smithy/core": "^3.31.1",
+    "@smithy/fetch-http-handler": "^5.6.13",
+    "@smithy/node-http-handler": "^4.9.13",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@aws-sdk/signature-v4-multi-region/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aws-sdk/signature-v4-multi-region",
-  "version": "3.996.42",
+  "version": "3.996.43",
   "homepage": "https://github.com/aws/aws-sdk-js-v3/tree/main/packages/signature-v4-multi-region",
   "license": "Apache-2.0",
   "author": {
@@ -43,7 +43,7 @@
   },
   "dependencies": {
     "@aws-sdk/types": "^3.974.2",
-    "@smithy/signature-v4": "^5.6.9",
+    "@smithy/signature-v4": "^5.6.12",
     "@smithy/types": "^4.16.1",
     "tslib": "^2.6.2"
   },

package/node_modules/@earendil-works/pi-coding-agent/docs/compaction.md

@@ -13,14 +13,14 @@ For TypeScript definitions in your project, inspect `node_modules/@earendil-work
 
 ## Overview
 
-Pi has two summarization mechanisms:
+Sling has two summarization mechanisms:
 
 | Mechanism | Trigger | Purpose |
 |-----------|---------|---------|
 | Compaction | Context exceeds threshold, or `/compact` | Summarize old messages to free up context |
 | Branch summarization | `/tree` navigation | Preserve context when switching branches |
 
-Both use the same structured summary format and track file operations cumulatively.
+Both use the same structured summary format and track file operations cumulatively. Compaction and branch-summary requests use fresh routing session IDs and, where supported by the provider, disable prompt-cache writes because these one-off prompts are unlikely to be reused.
 
 ## Compaction
 
@@ -76,7 +76,7 @@ What the LLM sees:
     prompt   from cmp          messages from firstKeptEntryId
 ```
 
-On repeated compactions, the summarized span starts at the previous compaction's kept boundary (`firstKeptEntryId`), not at the compaction entry itself, falling back to the entry after the previous compaction if that kept entry cannot be found in the path. This preserves messages that survived the earlier compaction by including them in the next summarization pass as well. Pi also recalculates `tokensBefore` from the rebuilt session context before writing the new `CompactionEntry`, so the token count reflects the actual pre-compaction context being replaced.
+On repeated compactions, the summarized span starts at the previous compaction's kept boundary (`firstKeptEntryId`), not at the compaction entry itself, falling back to the entry after the previous compaction if that kept entry cannot be found in the path. This preserves messages that survived the earlier compaction by including them in the next summarization pass as well. Sling also recalculates `tokensBefore` from the rebuilt session context before writing the new `CompactionEntry`, so the token count reflects the actual pre-compaction context being replaced.
 
 ### Split Turns
 
@@ -102,7 +102,7 @@ Split turn (one huge turn exceeds budget):
   turnPrefixMessages = [usr, ass, tool, ass, tool, tool]
 ```
 
-For split turns, pi generates two summaries and merges them:
+For split turns, sling generates two summaries and merges them:
 1. **History summary**: Previous context (if any)
 2. **Turn prefix summary**: The early part of the split turn
 
@@ -129,6 +129,7 @@ interface CompactionEntry<T = unknown> {
   summary: string;
   firstKeptEntryId: string;
   tokensBefore: number;
+  usage?: Usage;       // LLM usage that generated the summary
   fromHook?: boolean;  // true if provided by extension (legacy field name)
   details?: T;         // implementation-specific data
 }
@@ -140,15 +141,15 @@ interface CompactionDetails {
 }
 ```
 
-Extensions can store any JSON-serializable data in `details`. The default compaction tracks file operations, but custom extension implementations can use their own structure.
+Extensions can store any JSON-serializable data in `details`. The default compaction tracks file operations, but custom extension implementations can use their own structure. Generated and extension-provided summaries store their LLM `usage` when available so session totals include summarization work.
 
-See [`prepareCompaction()`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/compaction/compaction.ts) and [`compact()`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/compaction/compaction.ts) for the implementation.
+See [`prepareCompaction()`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/compaction/compaction.ts) and [`compact()`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/compaction/compaction.ts) for the implementation. For direct programmatic summarization, `generateSummary()` returns the summary text and `generateSummaryWithUsage()` returns `{ text, usage }`.
 
 ## Branch Summarization
 
 ### When It Triggers
 
-When you use `/tree` to navigate to a different branch, pi offers to summarize the work you're leaving. This injects context from the left branch into the new branch.
+When you use `/tree` to navigate to a different branch, sling offers to summarize the work you're leaving. This injects context from the left branch into the new branch.
 
 ### How It Works
 
@@ -177,7 +178,7 @@ After navigation with summary:
 
 ### Cumulative File Tracking
 
-Both compaction and branch summarization track files cumulatively. When generating a summary, pi extracts file operations from:
+Both compaction and branch summarization track files cumulatively. When generating a summary, sling extracts file operations from:
 - Tool calls in the messages being summarized
 - Previous compaction or branch summary `details` (if any)
 
@@ -195,6 +196,7 @@ interface BranchSummaryEntry<T = unknown> {
   timestamp: number;
   summary: string;
   fromId: string;      // Entry we navigated from
+  usage?: Usage;       // LLM usage that generated the summary
   fromHook?: boolean;  // true if provided by extension (legacy field name)
   details?: T;         // implementation-specific data
 }
@@ -300,6 +302,7 @@ pi.on("session_before_compact", async (event, ctx) => {
       summary: "Your summary...",
       firstKeptEntryId: preparation.firstKeptEntryId,
       tokensBefore: preparation.tokensBefore,
+      // usage: summaryResponse.usage, // Optional; included in session totals
       details: { /* custom data */ },
     }
   };
@@ -328,13 +331,14 @@ pi.on("session_before_compact", async (event, ctx) => {
   // [Tool result]: output text
 
   // Now send to your model for summarization
-  const summary = await myModel.summarize(conversationText);
+  const { summary, usage } = await myModel.summarize(conversationText);
   
   return {
     compaction: {
       summary,
       firstKeptEntryId: preparation.firstKeptEntryId,
       tokensBefore: preparation.tokensBefore,
+      usage,
     }
   };
 });
@@ -364,6 +368,7 @@ pi.on("session_before_tree", async (event, ctx) => {
     return {
       summary: {
         summary: "Your summary...",
+        // usage: summaryResponse.usage, // Optional; included in session totals
         details: { /* custom data */ },
       }
     };

package/node_modules/@earendil-works/pi-coding-agent/docs/containerization.md

@@ -3,23 +3,23 @@
 Pi runs with all permissions by default, but in some cases, you will want to have more control over what directories Pi can write to and which accesses it has.
 
 There are two general options. You can either
-1. run the whole `pi` process inside an isolated environment, or
-2. run `pi` on the host and route tool execution into an isolated environment.
+1. run the whole `sling` process inside an isolated environment, or
+2. run `sling` on the host and route tool execution into an isolated environment.
 
 ## Choose a pattern
 
 | Pattern | What is isolated | Best for | Notes |
 | --- | --- | --- | --- |
 | Gondolin extension | Built-in tools and `!` commands | Local micro-VM isolation while keeping auth on host | See [`examples/extensions/gondolin/`](../examples/extensions/gondolin/). |
-| Plain Docker | Whole `pi` process in a local container | Simple local isolation | Provider API keys enter the container. |
-| OpenShell | Whole `pi` process in a policy-controlled sandbox | Local or remote managed sandbox | Requires an OpenShell gateway |
+| Plain Docker | Whole `sling` process in a local container | Simple local isolation | Provider API keys enter the container. |
+| OpenShell | Whole `sling` process in a policy-controlled sandbox | Local or remote managed sandbox | Requires an OpenShell gateway |
 
-Extensions run wherever the `pi` process runs. If you run host `pi` with a tool-routing extension, other custom extension tools still run on the host unless they also delegate their operations.
+Extensions run wherever the `sling` process runs. If you run host `sling` with a tool-routing extension, other custom extension tools still run on the host unless they also delegate their operations.
 
 ## Gondolin
 
 [Gondolin](https://github.com/earendil-works/gondolin) is a local Linux micro-VM.
-Use the [example extension](../examples/extensions/gondolin) when you want `pi` on the host but all built-in tools routed into the VM.
+Use the [example extension](../examples/extensions/gondolin) when you want `sling` on the host but all built-in tools routed into the VM.
 
 Setup:
 
@@ -33,7 +33,7 @@ Run from the project you want mounted:
 
 ```bash
 cd /path/to/project
-pi -e ~/.sling/agent/extensions/gondolin
+sling -e ~/.sling/agent/extensions/gondolin
 ```
 
 The extension mounts the host cwd at `/workspace` in the VM and overrides `read`, `write`, `edit`, `bash`, `grep`, `find`, and `ls`.
@@ -54,7 +54,7 @@ FROM node:24-bookworm-slim
 RUN apt-get update \
   && apt-get install -y --no-install-recommends bash ca-certificates git ripgrep \
   && rm -rf /var/lib/apt/lists/*
-RUN npm install -g --ignore-scripts @earendil-works/pi-coding-agent
+RUN npm install -g --ignore-scripts @psnext/slingcli
 
 WORKDIR /workspace
 ENTRYPOINT ["sling"]
@@ -63,13 +63,13 @@ ENTRYPOINT ["sling"]
 Build and run:
 
 ```bash
-docker build -t pi-sandbox -f Dockerfile.sling .
+docker build -t sling-sandbox -f Dockerfile.sling .
 
 docker run --rm -it \
   -e ANTHROPIC_API_KEY \
   -v "$PWD:/workspace" \
-  -v pi-agent-home:/root/.sling/agent \
-  pi-sandbox
+  -v sling-agent-home:/root/.sling/agent \
+  sling-sandbox
 ```
 
 The `-v "$PWD:/workspace"` mounts your current directory into the container at /workspace such that reads and writes in `/workspace` inside Docker directly affect your host files, like in the Gondolin example.
@@ -89,21 +89,21 @@ openshell gateway add <gateway-url> --name <name>
 openshell gateway select <name>
 ```
 
-Launch `pi` inside an OpenShell sandbox:
+Launch `sling` inside an OpenShell sandbox:
 
 ```bash
-openshell sandbox create --name pi-sandbox --from pi -- pi
+openshell sandbox create --name sling-sandbox --from sling -- sling
 ```
 
-In this pattern, the whole `pi` process runs inside the sandbox.
+In this pattern, the whole `sling` process runs inside the sandbox.
 Built-in tools, `!` commands, and extension tools execute inside the OpenShell boundary.
 
 If the gateway is remote, project files are not bind-mounted from the host, meaning writes in the sandbox are not reflected on your machine.
 Clone the repository inside the sandbox or use OpenShell file transfer commands:
 
 ```bash
-openshell sandbox upload pi-sandbox ./repo /workspace
-openshell sandbox download pi-sandbox /workspace/repo ./repo-out
+openshell sandbox upload sling-sandbox ./repo /workspace
+openshell sandbox download sling-sandbox /workspace/repo ./repo-out
 ```
 
 OpenShell providers can keep raw model API keys outside the sandbox.

package/node_modules/@earendil-works/pi-coding-agent/docs/custom-provider.md

@@ -88,7 +88,7 @@ export default function (pi: ExtensionAPI) {
 }
 ```
 
-The extension factory can also be `async`. For dynamic model discovery, fetch and register models in the factory instead of `session_start`. pi waits for the factory before startup continues, so the provider is available during interactive startup and to `pi --list-models`.
+The extension factory can also be `async`. For dynamic model discovery, fetch and register models in the factory instead of `session_start`. sling waits for the factory before startup continues, so the provider is available during interactive startup and to `sling --list-models`.
 
 ## Override Existing Provider
 
@@ -259,7 +259,7 @@ models: [{
 ```
 
 Use `openrouter` for OpenRouter-style `reasoning: { effort }` controls. Use `together` for Together-style `reasoning: { enabled }` controls; with `supportsReasoningEffort`, it also sends `reasoning_effort`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking` and need `preserve_thinking`.
-Use `cacheControlFormat: "anthropic"` for OpenAI-compatible providers that expose Anthropic-style prompt caching via `cache_control` on the system prompt, last tool definition, and last user/assistant text content.
+Use `cacheControlFormat: "anthropic"` for OpenAI-compatible providers that expose Anthropic-style prompt caching via `cache_control` on the system prompt, last tool definition, and last user, assistant, or tool-result text content.
 
 For Anthropic-compatible providers using `api: "anthropic-messages"`, set `compat.forceAdaptiveThinking: true` on models or providers whose upstream model requires adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`). Built-in adaptive Claude models set this automatically. Set `compat.allowEmptySignature: true` only for providers that emit empty thinking signatures and expect `signature: ""` on replay.
 
@@ -560,14 +560,14 @@ calculateCost(model, output.usage);
 
 ### Context Overflow Errors
 
-When a request exceeds the model's context window, pi can recover automatically by compacting the conversation and retrying. This recovery only kicks in if pi recognizes the failure as an overflow.
+When a request exceeds the model's context window, sling can recover automatically by compacting the conversation and retrying. This recovery only kicks in if sling recognizes the failure as an overflow.
 
 Detection runs on the finalized assistant message:
 
 - `stopReason === "error"`
-- `errorMessage` matches one of pi's known overflow patterns (see [`packages/ai/src/utils/overflow.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/utils/overflow.ts))
+- `errorMessage` matches one of sling's known overflow patterns (see [`packages/ai/src/utils/overflow.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/utils/overflow.ts))
 
-If your provider returns overflow errors with a message pi does not recognize, normalize the error from the same extension that registers the provider. Use a `message_end` handler to rewrite the assistant message so its `errorMessage` starts with a phrase pi recognizes. The generic fallback `context_length_exceeded` is the safest choice.
+If your provider returns overflow errors with a message sling does not recognize, normalize the error from the same extension that registers the provider. Use a `message_end` handler to rewrite the assistant message so its `errorMessage` starts with a phrase sling recognizes. The generic fallback `context_length_exceeded` is the safest choice.
 
 ```typescript
 const MY_PROVIDER_OVERFLOW_PATTERN = /your provider's overflow phrase/i;
@@ -599,7 +599,7 @@ export default function (pi: ExtensionAPI) {
 }
 ```
 
-`message_end` runs before pi tracks the assistant message for auto-compaction, so the rewritten `errorMessage` is what pi checks. With this in place, pi will:
+`message_end` runs before sling tracks the assistant message for auto-compaction, so the rewritten `errorMessage` is what sling checks. With this in place, sling will:
 
 1. Detect the overflow from `errorMessage`.
 2. Drop the failed assistant message from live context.
@@ -609,7 +609,7 @@ export default function (pi: ExtensionAPI) {
 Guard the rewrite carefully:
 
 - Scope it to your provider (`message.provider` and `ctx.model?.provider`) so unrelated errors from other providers are untouched.
-- Match a provider-specific pattern, not pi's generic overflow patterns. Rewriting rate-limit or throttling errors (`rate limit`, `too many requests`) would falsely trigger compaction instead of pi's normal retry-with-backoff path.
+- Match a provider-specific pattern, not sling's generic overflow patterns. Rewriting rate-limit or throttling errors (`rate limit`, `too many requests`) would falsely trigger compaction instead of sling's normal retry-with-backoff path.
 - Skip when `errorMessage` already includes `context_length_exceeded` so the handler is idempotent.
 
 ### Registration
@@ -617,7 +617,7 @@ Guard the rewrite carefully:
 Register your stream function:
 
 ```typescript
-pi.registerProvider("my-provider", {
+sling.registerProvider("my-provider", {
   baseUrl: "https://api.example.com",
   apiKey: "$MY_API_KEY",
   api: "my-custom-api",
@@ -737,6 +737,8 @@ interface ProviderModelConfig {
     supportsDeveloperRole?: boolean;
     supportsReasoningEffort?: boolean;
     supportsUsageInStreaming?: boolean;
+    supportsStrictMode?: boolean;
+    supportsOpenAIGrammarTools?: boolean; // openai-completions/openai-responses; false falls back to normal function tools
     maxTokensField?: "max_completion_tokens" | "max_tokens";
     requiresToolResultName?: boolean;
     requiresAssistantAfterToolResult?: boolean;
@@ -755,9 +757,10 @@ interface ProviderModelConfig {
     supportsCacheControlOnTools?: boolean;
     forceAdaptiveThinking?: boolean;
     allowEmptySignature?: boolean;
+    supportsStrictTools?: boolean;
   };
 }
 ```
 
 `openrouter` sends `reasoning: { effort }`. `deepseek` sends `thinking: { type: "enabled" | "disabled" }` and `reasoning_effort` when enabled. `together` sends `reasoning: { enabled }` and also `reasoning_effort` when `supportsReasoningEffort` is enabled. `qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking` and need `preserve_thinking`. Use `chat-template` for configurable `chat_template_kwargs`, for example DeepSeek V3.x behind vLLM with `chatTemplateKwargs: { "thinking": { "$var": "thinking.enabled" } }`.
-`cacheControlFormat: "anthropic"` applies Anthropic-style `cache_control` markers to the system prompt, last tool definition, and last user/assistant text content.
+`cacheControlFormat: "anthropic"` applies Anthropic-style `cache_control` markers to the system prompt, last tool definition, and last user, assistant, or tool-result text content.

package/node_modules/@earendil-works/pi-coding-agent/docs/docs.json

@@ -12,7 +12,7 @@
           "path": "quickstart.md"
         },
         {
-          "title": "Using sling",
+          "title": "Using Sling",
           "path": "usage.md"
         },
         {
@@ -68,10 +68,6 @@
           "title": "Pi Packages",
           "path": "packages.md"
         },
-        {
-          "title": "MCP Servers",
-          "path": "mcp.md"
-        },
         {
           "title": "Custom Models",
           "path": "models.md"