@earendil-works/pi-coding-agent 0.81.0 → 0.82.0

package/docs/custom-provider.md

@@ -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.
 
@@ -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/docs/environment-variables.md

@@ -0,0 +1,88 @@
+# Environment Variables
+
+Pi uses environment variables in three ways:
+
+- Variables such as `PI_OFFLINE` configure the Pi process.
+- Pi sets `PI_CODING_AGENT` so child processes can detect that they run inside Pi.
+- Commands run by the LLM-callable bash tool receive `PI_*` variables describing the current session.
+
+Provider API-key variables are documented separately in [Providers](providers.md#environment-variables-or-auth-file).
+
+## Process Marker
+
+The CLI and RPC entry points set `PI_CODING_AGENT=true`. Child processes inherit it and can use it to detect that they run inside Pi. It is not session-specific and is not set automatically when Pi is embedded through the SDK.
+
+## Bash Tool Session Environment
+
+Commands run by the bash tool receive the current Pi session state:
+
+| Variable | Description |
+|----------|-------------|
+| `PI_SESSION_ID` | Current session ID |
+| `PI_SESSION_FILE` | Absolute path to the current session JSONL file; unset for ephemeral sessions |
+| `PI_PROVIDER` | Currently selected model provider |
+| `PI_MODEL` | Currently selected model ID |
+| `PI_REASONING_LEVEL` | Current effective reasoning level: `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max` |
+
+The values are resolved when each command starts. Switching models or changing the reasoning level therefore affects the next bash command without restarting Pi. `PI_PROVIDER` and `PI_MODEL` identify the selected Pi model, not a different upstream model that a router may choose internally.
+
+When asked which model or provider is running, inspect these variables instead of inferring the answer from the system prompt:
+
+```bash
+printf '%s/%s\n' "$PI_PROVIDER" "$PI_MODEL"
+printf 'reasoning=%s session=%s\n' "$PI_REASONING_LEVEL" "$PI_SESSION_ID"
+```
+
+The session file can be inspected directly when the session is persistent:
+
+```bash
+if [ -n "$PI_SESSION_FILE" ]; then
+  tail -n 1 "$PI_SESSION_FILE"
+fi
+```
+
+These variables are injected into the LLM-callable bash tool. They are not injected into user-entered `!` or `!!` commands.
+
+### Custom Bash Tools
+
+Bash tools created with `createBashTool()` expose the session environment by default when registered with Pi. Injection happens before `spawnHook`, so a hook receives the variables in `ctx.env`:
+
+```typescript
+const bashTool = createBashTool(cwd, {
+  spawnHook: (ctx) => ({
+    ...ctx,
+    env: { ...ctx.env, CI: "1" },
+  }),
+});
+```
+
+Disable session metadata independently of the spawn hook:
+
+```typescript
+const bashTool = createBashTool(cwd, {
+  exposeSessionEnvironment: false,
+  spawnHook: (ctx) => ctx,
+});
+```
+
+When disabled, Pi removes inherited values for these variables so nested Pi processes do not expose stale parent-session metadata.
+
+## Pi Process Configuration
+
+These variables are read by Pi itself:
+
+| Variable | Description |
+|----------|-------------|
+| `PI_CODING_AGENT_DIR` | Override the config directory; default is `~/.pi/agent` |
+| `PI_CODING_AGENT_SESSION_DIR` | Override session storage; overridden by `--session-dir` |
+| `PI_PACKAGE_DIR` | Override the package directory, useful for Nix/Guix store paths |
+| `PI_OFFLINE` | Disable startup network operations, including update checks, package updates, and install/update telemetry |
+| `PI_SKIP_VERSION_CHECK` | Disable the `pi.dev` latest-version request |
+| `PI_TELEMETRY` | Override install/update telemetry and provider attribution headers: `1`/`true`/`yes` or `0`/`false`/`no` |
+| `PI_CACHE_RETENTION` | Set to `long` for extended provider prompt caching where supported |
+| `PI_SHARE_VIEWER_URL` | Override the base URL used by `/share` |
+| `PI_HARDWARE_CURSOR` | Set to `1` to show the hardware cursor; see [Terminal setup](terminal-setup.md) |
+| `VISUAL`, `EDITOR` | External editor fallback when `externalEditor` is unset |
+| `HTTP_PROXY`, `HTTPS_PROXY` | Proxy outbound HTTP requests |
+
+Provider credentials such as `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, and cloud-provider configuration are listed in [Providers](providers.md#environment-variables-or-auth-file).

package/docs/extensions.md

@@ -982,9 +982,9 @@ ctx.sessionManager.buildContextEntries()    // Active branch entries with compac
 ctx.sessionManager.getLeafId()              // Current leaf entry ID
 ```
 
-### ctx.modelRegistry / ctx.model
+### ctx.modelRegistry / ctx.model / ctx.thinkingLevel
 
-Access to models, providers, and resolved authentication. `ctx.modelRegistry.getProvider(id)` returns the effective pi-ai provider, while `getProviderAuth(id)` resolves its current API key, headers, base URL, and provider-scoped environment without requiring a loaded model. `ctx.model` is the active model.
+Access to models, providers, and resolved authentication. `ctx.modelRegistry.getProvider(id)` returns the effective pi-ai provider, while `getProviderAuth(id)` resolves its current API key, headers, base URL, and provider-scoped environment without requiring a loaded model. `ctx.model` is the active model, and `ctx.thinkingLevel` is its current effective thinking level.
 
 ### ctx.signal
 
@@ -2096,7 +2096,15 @@ const bashTool = createBashTool(cwd, {
 });
 ```
 
-See [examples/extensions/ssh.ts](../examples/extensions/ssh.ts) for a complete SSH example with `--ssh` flag.
+`createBashTool()` exposes the current session to commands through `PI_SESSION_ID`, `PI_SESSION_FILE`, `PI_PROVIDER`, `PI_MODEL`, and `PI_REASONING_LEVEL`. Injection happens before `spawnHook`, so hooks receive these values in `env` and preserve them when they spread the existing environment as above. Set `exposeSessionEnvironment: false` to disable them:
+
+```typescript
+const bashTool = createBashTool(cwd, {
+  exposeSessionEnvironment: false,
+});
+```
+
+See [Bash tool session environment](environment-variables.md#bash-tool-session-environment) for variable semantics. See [examples/extensions/ssh.ts](../examples/extensions/ssh.ts) for a complete SSH example with `--ssh` flag.
 
 ### Output Truncation
 

package/docs/index.md

@@ -68,6 +68,7 @@ For the full first-run flow, see [Quickstart](quickstart.md).
 
 ## Reference
 
+- [Environment variables](environment-variables.md) - Pi process configuration and session metadata available to bash tools.
 - [Session format](session-format.md) - JSONL session file format, entry types, and SessionManager API.
 
 ## Platform setup

package/docs/json.md

@@ -17,7 +17,11 @@ type AgentSessionEvent =
   | { type: "compaction_start"; reason: "manual" | "threshold" | "overflow" }
   | { type: "compaction_end"; reason: "manual" | "threshold" | "overflow"; result: CompactionResult | undefined; aborted: boolean; willRetry: boolean; errorMessage?: string }
   | { type: "auto_retry_start"; attempt: number; maxAttempts: number; delayMs: number; errorMessage: string }
-  | { type: "auto_retry_end"; success: boolean; attempt: number; finalError?: string };
+  | { type: "auto_retry_end"; success: boolean; attempt: number; finalError?: string }
+  | { type: "summarization_retry_scheduled"; attempt: number; maxAttempts: number; delayMs: number; errorMessage: string }
+  | { type: "summarization_retry_attempt_start"; source: "branchSummary" }
+  | { type: "summarization_retry_attempt_start"; source: "compaction"; reason: "manual" | "threshold" | "overflow" }
+  | { type: "summarization_retry_finished" };
 ```
 
 `queue_update` emits the full pending steering and follow-up queues whenever they change. `compaction_start` and `compaction_end` cover both manual and automatic compaction.

package/docs/models.md

@@ -375,6 +375,8 @@ Some Anthropic models require adaptive thinking (`thinking.type: "adaptive"` plu
 
 Some Anthropic-compatible providers emit thinking blocks with empty signatures and still expect them on replay. Set `allowEmptySignature` to `true` only for those providers; real Anthropic rejects empty thinking signatures.
 
+Built-in Anthropic models enable `supportsStrictTools` in their model metadata. Custom Anthropic-compatible models must set it to `true` when their endpoint accepts strict JSON-schema tool definitions.
+
 ```json
 {
   "providers": {
@@ -408,6 +410,7 @@ Some Anthropic-compatible providers emit thinking blocks with empty signatures a
 | `supportsCacheControlOnTools` | Whether the provider accepts Anthropic-style `cache_control` markers on tool definitions. Default: `true`. |
 | `forceAdaptiveThinking` | Whether to send adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`) for this model. Built-in adaptive models set this automatically. Default: `false`. |
 | `allowEmptySignature` | Whether to replay empty thinking signatures as `signature: ""` instead of converting thinking to text. Default: `false`. |
+| `supportsStrictTools` | Whether the provider accepts strict JSON-schema tool definitions. Default: `false`; built-in Anthropic models enable it in generated metadata. |
 
 ## OpenAI Compatibility
 
@@ -445,10 +448,11 @@ For providers with partial OpenAI compatibility, use the `compat` field.
 | `requiresReasoningContentOnAssistantMessages` | Include empty `reasoning_content` on all replayed assistant messages when reasoning is enabled |
 | `thinkingFormat` | Use `reasoning_effort`, `openrouter`, `deepseek`, `together`, `zai`, `qwen`, `chat-template`, or `qwen-chat-template` thinking parameters |
 | `chatTemplateKwargs` | `chat_template_kwargs` values for `thinkingFormat: "chat-template"`; use `{ "$var": "thinking.enabled" }` or `{ "$var": "thinking.effort" }` for pi-controlled thinking values |
-| `cacheControlFormat` | Use Anthropic-style `cache_control` markers on the system prompt, last tool definition, and last user/assistant text content. Currently only `anthropic` is supported. |
+| `cacheControlFormat` | Use Anthropic-style `cache_control` markers on the system prompt, last tool definition, and last user, assistant, or tool-result text content. Currently only `anthropic` is supported. |
 | `sendSessionAffinityHeaders` | For `openai-completions`, send session-affinity headers from the session id when caching is enabled. Default: `false`. |
 | `sessionAffinityFormat` | For `openai-completions` and `openai-responses`, the session-affinity header format: `openai` sends `session_id`/`x-client-request-id` (completions also `x-session-affinity`), `openai-nosession` omits the underscore-containing `session_id` header, `openrouter` sends `x-session-id`. Does not affect the `prompt_cache_key` body param. Default: auto-detected. |
-| `supportsStrictMode` | Include the `strict` field in tool definitions |
+| `supportsStrictMode` | Whether the provider accepts strict JSON-schema function tool definitions. Defaults depend on the API; built-in OpenAI models carry explicit capability metadata. |
+| `supportsOpenAIGrammarTools` | Whether OpenAI-compatible APIs emit custom Lark/regex grammar tools. When `false`, grammar-constrained tools fall back to normal function tools. Default: `false`; the built-in model catalog enables it for GPT-5+ models on OpenAI, OpenAI Codex, Azure OpenAI, GitHub Copilot, opencode, and Cloudflare AI Gateway. |
 | `deferredToolsMode` | Use provider-specific deferred tool serialization. Currently only `"kimi"` is supported for Kimi's OpenAI-compatible Chat Completions format. |
 | `supportsLongCacheRetention` | Whether the provider accepts long cache retention when cache retention is `long`: `prompt_cache_retention: "24h"` for OpenAI prompt caching, or `cache_control.ttl: "1h"` when `cacheControlFormat` is `anthropic`. Default: `true`. |
 | `openRouterRouting` | OpenRouter provider routing preferences. This object is sent as-is in the `provider` field of the [OpenRouter API request](https://openrouter.ai/docs/guides/routing/provider-selection). |

package/docs/providers.md

@@ -20,9 +20,10 @@ Use `/login` in interactive mode, then select a provider:
 - Claude Pro/Max
 - GitHub Copilot
 - xAI (Grok/X subscription)
+- OpenRouter (OAuth-minted API key billed from OpenRouter credits)
 - Radius
 
-Use `/logout` to clear credentials. Tokens are stored in `~/.pi/agent/auth.json` and auto-refresh when expired.
+Use `/logout` to clear credentials. Tokens are stored in `~/.pi/agent/auth.json` and auto-refresh when expired. OpenRouter instead mints a user-controlled API key that does not expire automatically.
 
 ### OpenAI Codex
 
@@ -43,6 +44,12 @@ Anthropic subscription auth is active for Claude Pro/Max accounts. Third-party h
 - Run `/login xai`, then select **Use a subscription**
 - `XAI_API_KEY` remains available through **Use an API key**
 
+### OpenRouter
+
+- Run `/login openrouter`, then select **Sign in with OpenRouter** to open the OpenRouter PKCE authorization flow
+- The authorization creates a user-controlled OpenRouter API key billed from your OpenRouter credits
+- `OPENROUTER_API_KEY` remains available through **Use an API key**
+
 ### Radius
 
 Radius is a dynamic `pi-messages` gateway. `/login radius` stores OAuth tokens in `auth.json`; the gateway catalog is refreshed independently and cached in `models-store.json`. Custom Radius gateways can be declared in `models.json` with `"oauth": "radius"` and a gateway `baseUrl`.

package/docs/rpc.md

@@ -23,7 +23,7 @@ Common options:
 - **Responses**: JSON objects with `type: "response"` indicating command success/failure
 - **Events**: Agent events streamed to stdout as JSON lines
 
-All commands support an optional `id` field for request/response correlation. If provided, the corresponding response will include the same `id`.
+All commands support an optional `id` field for request/response correlation. If provided, the corresponding response will include the same `id`. `bash_execution_update` events also include the `id` of their originating `bash` command.
 
 ### Framing
 
@@ -455,15 +455,18 @@ Response:
 
 #### bash
 
-Execute a shell command and add output to conversation context.
+Execute a shell command and add output to conversation context. Output streams as `bash_execution_update` events while the command runs; the response contains the final result.
 
 ```json
-{"type": "bash", "command": "ls -la"}
+{"id": "req-1", "type": "bash", "command": "ls -la"}
 ```
 
+Include an `id` to associate streamed `bash_execution_update` events with this command.
+
 Response:
 ```json
 {
+  "id": "req-1",
   "type": "response",
   "command": "bash",
   "success": true,
@@ -494,7 +497,7 @@ If output was truncated, includes `fullOutputPath`:
 
 **How bash results reach the LLM:**
 
-The `bash` command executes immediately and returns a `BashResult`. Internally, a `BashExecutionMessage` is created and stored in the agent's message state. This message does NOT emit an event.
+The `bash` command executes immediately and returns a `BashResult`. Internally, a `BashExecutionMessage` is created and stored in the agent's message state.
 
 When the next `prompt` command is sent, all messages (including `BashExecutionMessage`) are transformed before being sent to the LLM. The `BashExecutionMessage` is converted to a `UserMessage` with this format:
 
@@ -509,7 +512,6 @@ drwxr-xr-x ...
 This means:
 1. Bash output is included in the LLM context on the **next prompt**, not immediately
 2. Multiple bash commands can be executed before a prompt; all outputs will be included
-3. No event is emitted for the `BashExecutionMessage` itself
 
 #### abort_bash
 
@@ -829,7 +831,7 @@ Each command has:
 
 ## Events
 
-Events are streamed to stdout as JSON lines during agent operation. Events do NOT include an `id` field (only responses do).
+Events are streamed to stdout as JSON lines during agent operation. Events do not generally include an `id` field; `bash_execution_update` includes the `id` of its originating `bash` command when one was provided.
 
 ### Event Types
 
@@ -843,6 +845,7 @@ Events are streamed to stdout as JSON lines during agent operation. Events do NO
 | `message_start` | Message begins |
 | `message_update` | Streaming update (text/thinking/toolcall deltas) |
 | `message_end` | Message completes |
+| `bash_execution_update` | Direct RPC bash command output chunk |
 | `tool_execution_start` | Tool begins execution |
 | `tool_execution_update` | Tool execution progress (streaming output) |
 | `tool_execution_end` | Tool completes |
@@ -851,6 +854,9 @@ Events are streamed to stdout as JSON lines during agent operation. Events do NO
 | `compaction_end` | Compaction completes |
 | `auto_retry_start` | Auto-retry begins (after transient error) |
 | `auto_retry_end` | Auto-retry completes (success or final failure) |
+| `summarization_retry_scheduled` | Retry scheduled for a transient compaction or branch-summary summarization error |
+| `summarization_retry_attempt_start` | Retried summarization request starts |
+| `summarization_retry_finished` | Summarization retry loop completes |
 | `extension_error` | Extension threw an error |
 
 ### agent_start
@@ -948,6 +954,20 @@ Example streaming a text response:
 {"type":"message_update","message":{...},"assistantMessageEvent":{"type":"text_end","contentIndex":0,"content":"Hello world","partial":{...}}}
 ```
 
+### bash_execution_update
+
+Emitted once for each output chunk from a direct `bash` command. `id` matches the command's `id`, allowing clients to associate output with the correct command.
+
+Events stream all output while the command runs, even if the final `bash` response's `output` is truncated.
+
+```json
+{
+  "type": "bash_execution_update",
+  "id": "req-1",
+  "delta": "total 48\n"
+}
+```
+
 ### tool_execution_start / tool_execution_update / tool_execution_end
 
 Emitted when a tool begins, streams progress, and completes execution.
@@ -1077,6 +1097,36 @@ On final failure (max retries exceeded):
 }
 ```
 
+### summarization_retry_scheduled / summarization_retry_attempt_start / summarization_retry_finished
+
+Emitted when compaction or branch-summary summarization retries after a transient provider error. These events use the same retry settings as automatic assistant-turn retries.
+
+```json
+{
+  "type": "summarization_retry_scheduled",
+  "attempt": 1,
+  "maxAttempts": 3,
+  "delayMs": 2000,
+  "errorMessage": "terminated"
+}
+```
+
+```json
+{
+  "type": "summarization_retry_attempt_start",
+  "source": "compaction",
+  "reason": "threshold"
+}
+```
+
+For branch summaries, `source` is `"branchSummary"` and no `reason` is present.
+
+```json
+{
+  "type": "summarization_retry_finished"
+}
+```
+
 ### extension_error
 
 Emitted when an extension throws an error.

package/docs/sdk.md

@@ -319,6 +319,9 @@ session.subscribe((event) => {
     case "compaction_end":
     case "auto_retry_start":
     case "auto_retry_end":
+    case "summarization_retry_scheduled":
+    case "summarization_retry_attempt_start":
+    case "summarization_retry_finished":
       break;
   }
 });

package/docs/settings.md

@@ -142,7 +142,7 @@ Set `PI_SKIP_VERSION_CHECK=1` to disable the Pi version update check. Use `--off
 | `retry.provider.maxRetries` | number | `0` | Provider/SDK retry attempts |
 | `retry.provider.maxRetryDelayMs` | number | `60000` | Max server-requested delay before failing (60s) |
 
-When a provider requests a retry delay longer than `retry.provider.maxRetryDelayMs` (e.g., Google's "quota will reset after 5h"), the request fails immediately with an informative error instead of waiting silently. Set to `0` to disable the cap.
+When a provider requests a retry delay longer than `retry.provider.maxRetryDelayMs`, the request fails immediately with an informative error instead of waiting silently. Set it to `0` to disable the limit.
 
 Keep `retry.provider.maxRetries` at `0` unless provider-level retries are explicitly needed. Setting it above `0` can make SDK/provider retries handle out-of-usage-limit errors before Pi sees them, which may block the agent until the provider quota resets in some circumstances.
 

package/docs/usage.md

@@ -289,19 +289,6 @@ pi --tools read,grep,find,ls -p "Review the code"
 pi --exclude-tools ask_question
 ```
 
-### Environment Variables
-
-| Variable | Description |
-|----------|-------------|
-| `PI_CODING_AGENT_DIR` | Override config directory; default is `~/.pi/agent` |
-| `PI_CODING_AGENT_SESSION_DIR` | Override session storage directory; overridden by `--session-dir` |
-| `PI_PACKAGE_DIR` | Override package directory, useful for Nix/Guix store paths |
-| `PI_OFFLINE` | Disable startup network operations, including update checks, package update checks, and install/update telemetry |
-| `PI_SKIP_VERSION_CHECK` | Skip the Pi version update check at startup. This prevents the `pi.dev` latest-version request |
-| `PI_TELEMETRY` | Override install/update telemetry and provider attribution headers: `1`/`true`/`yes` or `0`/`false`/`no`. This does not disable update checks |
-| `PI_CACHE_RETENTION` | Set to `long` for extended prompt cache where supported |
-| `VISUAL`, `EDITOR` | Fallback external editor for Ctrl+G when `externalEditor` is unset; defaults to Notepad on Windows and `nano` elsewhere |
-
 ## Design Principles
 
 Pi keeps the core small and pushes workflow-specific behavior into extensions, skills, prompt templates, and packages.

package/examples/extensions/custom-compaction.ts

@@ -13,6 +13,7 @@
  *   pi --extension examples/extensions/custom-compaction.ts
  */
 
+import { uuidv7 } from "@earendil-works/pi-ai";
 import { complete } from "@earendil-works/pi-ai/compat";
 import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
 import { convertToLlm, serializeConversation } from "@earendil-works/pi-coding-agent";
@@ -96,6 +97,8 @@ ${conversationText}
 					env: auth.env,
 					maxTokens: 8192,
 					signal,
+					cacheRetention: "none",
+					sessionId: uuidv7(),
 				},
 			);
 

package/examples/extensions/custom-provider-anthropic/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-custom-provider",
-  "version": "0.81.0",
+  "version": "0.82.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-custom-provider",
-      "version": "0.81.0",
+      "version": "0.82.0",
       "dependencies": {
         "@anthropic-ai/sdk": "^0.52.0"
       }

package/examples/extensions/custom-provider-anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-anthropic",
   "private": true,
-  "version": "0.81.0",
+  "version": "0.82.0",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/extensions/custom-provider-gitlab-duo/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-gitlab-duo",
   "private": true,
-  "version": "0.81.0",
+  "version": "0.82.0",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/extensions/gondolin/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-gondolin",
-	"version": "0.81.0",
+	"version": "0.82.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-gondolin",
-			"version": "0.81.0",
+			"version": "0.82.0",
 			"dependencies": {
 				"@earendil-works/gondolin": "0.12.0"
 			}

package/examples/extensions/gondolin/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-gondolin",
 	"private": true,
-	"version": "0.81.0",
+	"version": "0.82.0",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/handoff.ts

@@ -13,6 +13,7 @@
  */
 
 import type { AgentMessage } from "@earendil-works/pi-agent-core";
+import { uuidv7 } from "@earendil-works/pi-ai";
 import { complete, type Message } from "@earendil-works/pi-ai/compat";
 import type { ExtensionAPI, SessionEntry } from "@earendil-works/pi-coding-agent";
 import { BorderedLoader, convertToLlm, serializeConversation } from "@earendil-works/pi-coding-agent";
@@ -136,7 +137,14 @@ export default function (pi: ExtensionAPI) {
 					const response = await complete(
 						ctx.model!,
 						{ systemPrompt: SYSTEM_PROMPT, messages: [userMessage] },
-						{ apiKey: auth.apiKey, headers: auth.headers, env: auth.env, signal: loader.signal },
+						{
+							apiKey: auth.apiKey,
+							headers: auth.headers,
+							env: auth.env,
+							signal: loader.signal,
+							cacheRetention: "none",
+							sessionId: uuidv7(),
+						},
 					);
 
 					if (response.stopReason === "aborted") {

package/examples/extensions/sandbox/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-sandbox",
-	"version": "1.11.0",
+	"version": "1.12.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-sandbox",
-			"version": "1.11.0",
+			"version": "1.12.0",
 			"dependencies": {
 				"@anthropic-ai/sandbox-runtime": "^0.0.26"
 			}

package/examples/extensions/sandbox/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-sandbox",
 	"private": true,
-	"version": "1.11.0",
+	"version": "1.12.0",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/summarize.ts

@@ -1,3 +1,4 @@
+import { uuidv7 } from "@earendil-works/pi-ai";
 import { complete, getModel } from "@earendil-works/pi-ai/compat";
 import type { ExtensionAPI, ExtensionCommandContext } from "@earendil-works/pi-coding-agent";
 import { DynamicBorder, getMarkdownTheme } from "@earendil-works/pi-coding-agent";
@@ -193,6 +194,8 @@ export default function (pi: ExtensionAPI) {
 					headers: auth.headers,
 					env: auth.env,
 					reasoningEffort: "high",
+					cacheRetention: "none",
+					sessionId: uuidv7(),
 				},
 			);
 

package/examples/extensions/with-deps/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-with-deps",
-  "version": "0.81.0",
+  "version": "0.82.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-with-deps",
-      "version": "0.81.0",
+      "version": "0.82.0",
       "dependencies": {
         "ms": "^2.1.3"
       },

package/examples/extensions/with-deps/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-with-deps",
   "private": true,
-  "version": "0.81.0",
+  "version": "0.82.0",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",