pi-namespace-patch 0.85.1 → 0.86.0-namespace.1

package/docs/session-format.md

@@ -5,10 +5,10 @@ Sessions are stored as JSONL (JSON Lines) files. Each line is a JSON object with
 ## File Location
 
 ```
-~/.pi/agent/sessions/--<path>--/<timestamp>_<uuid>.jsonl
+~/.pi/agent/sessions/--<path>--/<timestamp>_<session-id>.jsonl
 ```
 
-Where `<path>` is the working directory with `/` replaced by `-`.
+By default, `<session-id>` is a UUID. Callers can supply a custom ID through the SDK or `--session-id`. For `<path>`, Pi removes the leading path separator and replaces `/`, `\\`, and `:` with `-`.
 
 ## Deleting Sessions
 
@@ -28,11 +28,11 @@ Existing sessions are automatically migrated to the current version (v3) when lo
 
 ## Source Files
 
-Source on GitHub ([pi-mono](https://github.com/earendil-works/pi-mono)):
-- [`packages/coding-agent/src/core/session-manager.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/session-manager.ts) - Session entry types and SessionManager
-- [`packages/coding-agent/src/core/messages.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/messages.ts) - Extended message types (BashExecutionMessage, CustomMessage, etc.)
-- [`packages/ai/src/types.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/types.ts) - Base message types (UserMessage, AssistantMessage, ToolResultMessage)
-- [`packages/agent/src/types.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/agent/src/types.ts) - AgentMessage union type
+Source on GitHub ([pi](https://github.com/earendil-works/pi)):
+- [`packages/coding-agent/src/core/session-manager.ts`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/src/core/session-manager.ts) - Session entry types and SessionManager
+- [`packages/coding-agent/src/core/messages.ts`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/src/core/messages.ts) - Extended message types (BashExecutionMessage, CustomMessage, etc.)
+- [`packages/ai/src/types.ts`](https://github.com/earendil-works/pi/blob/main/packages/ai/src/types.ts) - Base message types (UserMessage, AssistantMessage, ToolResultMessage)
+- [`packages/agent/src/types.ts`](https://github.com/earendil-works/pi/blob/main/packages/agent/src/types.ts) - AgentMessage union type
 
 For TypeScript definitions in your project, inspect `node_modules/@earendil-works/pi-coding-agent/dist/` and `node_modules/@earendil-works/pi-ai/dist/`.
 
@@ -48,6 +48,7 @@ Messages contain arrays of typed content blocks:
 interface TextContent {
   type: "text";
   text: string;
+  textSignature?: string;
 }
 
 interface ImageContent {
@@ -59,6 +60,8 @@ interface ImageContent {
 interface ThinkingContent {
   type: "thinking";
   thinking: string;
+  thinkingSignature?: string;
+  redacted?: boolean;
 }
 
 interface ToolCall {
@@ -66,12 +69,22 @@ interface ToolCall {
   id: string;
   name: string;
   arguments: Record<string, any>;
+  thoughtSignature?: string;
+  namespace?: string;
 }
 ```
 
 ### Base Message Types (from pi-ai)
 
 ```typescript
+interface SystemMessage {
+  role: "system";
+  content: string | TextContent[];
+  toolsAdded?: Tool[];
+  toolsRemoved?: Array<{ name: string }>;
+  timestamp: number;  // Unix ms
+}
+
 interface UserMessage {
   role: "user";
   content: string | (TextContent | ImageContent)[];
@@ -84,9 +97,16 @@ interface AssistantMessage {
   api: string;
   provider: string;
   model: string;
+  responseModel?: string;
+  responseId?: string;
+  providerThinkingLevel?: string;
+  diagnostics?: AssistantMessageDiagnostic[];
   usage: Usage;
-  stopReason: "stop" | "length" | "toolUse" | "error" | "aborted";
+  stopReason: "pending" | "stop" | "length" | "toolUse" | "error" | "aborted" | "deferred";
+  deferred?: DeferredHandle;
   errorMessage?: string;
+  rawStopReason?: string;
+  endTurn?: boolean;
   timestamp: number;
 }
 
@@ -106,6 +126,8 @@ interface Usage {
   output: number;
   cacheRead: number;
   cacheWrite: number;
+  cacheWrite1h?: number;
+  reasoning?: number;
   totalTokens: number;
   cost: {
     input: number;
@@ -117,7 +139,7 @@ interface Usage {
 }
 ```
 
-The exported pi-ai `StopReason` type also includes `"pending"`, but that value is reserved for partial messages in streaming events. Terminal `done`/`error` messages replace it with a completion reason before pi persists the assistant message, so `"pending"` should never appear in session JSONL.
+`"pending"` is reserved for partial messages in streaming events. Terminal events replace it with a completion reason before Pi persists the assistant message, so `"pending"` should never appear in session JSONL. `"deferred"` is a terminal reason for a provider response that will complete later; its `deferred` handle contains the provider data needed to retrieve that response.
 
 ### Extended Message Types (from pi-coding-agent)
 
@@ -146,7 +168,7 @@ interface CustomMessage {
 interface BranchSummaryMessage {
   role: "branchSummary";
   summary: string;
-  fromId: string;                // Entry we branched from
+  fromId: string | null;         // Previous leaf whose abandoned path was summarized
   timestamp: number;
 }
 
@@ -162,6 +184,7 @@ interface CompactionSummaryMessage {
 
 ```typescript
 type AgentMessage =
+  | SystemMessage
   | UserMessage
   | AssistantMessage
   | ToolResultMessage
@@ -178,8 +201,8 @@ All entries (except `SessionHeader`) extend `SessionEntryBase`:
 ```typescript
 interface SessionEntryBase {
   type: string;
-  id: string;           // 8-char hex ID
-  parentId: string | null;  // Parent entry ID (null for first entry)
+  id: string;           // Usually an 8-char hex ID; may fall back to a full UUID
+  parentId: string | null;  // Parent entry ID (null for a root entry)
   timestamp: string;    // ISO timestamp
 }
 ```
@@ -202,12 +225,19 @@ For sessions with a parent (created via `/fork`, `/clone`, or `newSession({ pare
 
 ### SessionMessageEntry
 
-A message in the conversation. The `message` field contains an `AgentMessage`.
+A message in the conversation. The `message` field contains an `AgentMessage`. System messages carry the prompt and tool loadout: the first request of a session persists one with every prompt section and tool declaration, and later changes persist as system messages that patch `sections` by name (`null` removes one) and list `toolsAdded`/`toolsRemoved`. Replaying them in order yields the current prompt and tools; there is no separate prompt state entry.
+
+```json
+{"type":"message","id":"a0b1c2d3","parentId":null,"timestamp":"2024-12-03T14:00:00.000Z","message":{"role":"system","content":"","sections":{"preamble":"You are an expert coding assistant...","tools":"<tools>\n- read: ...\n</tools>","cwd":"/project"},"toolsAdded":[{"name":"read","description":"...","parameters":{}}],"timestamp":1733234400000}}
+{"type":"message","id":"d4e5f6g7","parentId":"c3d4e5f6","timestamp":"2024-12-03T14:04:00.000Z","message":{"role":"system","content":"","sections":{"skills":"<skills>...</skills>"},"toolsRemoved":[{"name":"write"}],"timestamp":1733234640000}}
+```
+
+Sessions created before system messages existed have no leading system message; the first request declares the current prompt as a later system message, which replays the same way.
 
 ```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":"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}}
+{"type":"message","id":"a1b2c3d4","parentId":"prev1234","timestamp":"2024-12-03T14:00:01.000Z","message":{"role":"user","content":"Hello","timestamp":1733234401000}}
+{"type":"message","id":"b2c3d4e5","parentId":"a1b2c3d4","timestamp":"2024-12-03T14:00:02.000Z","message":{"role":"assistant","content":[{"type":"text","text":"Hi!"}],"api":"anthropic-messages","provider":"anthropic","model":"claude-sonnet-4-5","usage":{...},"stopReason":"stop","timestamp":1733234402000}}
+{"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,"timestamp":1733234403000}}
 ```
 
 ### ModelChangeEntry
@@ -226,26 +256,31 @@ Emitted when the user changes the thinking/reasoning level.
 {"type":"thinking_level_change","id":"e5f6g7h8","parentId":"d4e5f6g7","timestamp":"2024-12-03T14:06:00.000Z","thinkingLevel":"high"}
 ```
 
-### CompactionEntry
+### UsageEntry
 
-Created when context is compacted. Stores a summary of earlier messages.
+Records model-attributed usage that is not an assistant message and does not participate in LLM context. `kind` is an arbitrary string identifying the operation; for example, cache warming uses `"cache_warm"`.
 
 ```json
-{"type":"compaction","id":"f6g7h8i9","parentId":"e5f6g7h8","timestamp":"2024-12-03T14:10:00.000Z","summary":"User discussed X, Y, Z...","firstKeptEntryId":"c3d4e5f6","tokensBefore":50000}
+{"type":"usage","id":"f6g7h8i9","parentId":"e5f6g7h8","timestamp":"2024-12-03T14:08:00.000Z","kind":"cache_warm","provider":"anthropic","model":"claude-sonnet-4-5","usage":{"input":0,"output":0,"cacheRead":50000,"cacheWrite":0,"totalTokens":50000,"cost":{"input":0,"output":0,"cacheRead":0.015,"cacheWrite":0,"total":0.015}}}
 ```
 
-Newer harness-generated compactions embed the retained post-compaction context directly on the entry, instead of `firstKeptEntryId`:
+Usage entries contribute to session token and cost totals. Pi hides them from the conversation tree. Consumers should treat unknown `kind` values as normal usage rather than rejecting them.
+
+### CompactionEntry
+
+Created when context is compacted. Stores a summary of earlier messages and a complete system prompt/tool checkpoint.
 
 ```json
-{"type":"compaction","id":"f6g7h8i9","parentId":"e5f6g7h8","timestamp":"2024-12-03T14:10:00.000Z","summary":"User discussed X, Y, Z...","tokensBefore":50000,"retainedTail":[{"role":"user","content":"latest request"},{"role":"assistant","content":[{"type":"text","text":"latest reply"}],"provider":"anthropic","model":"claude-sonnet-4-5","usage":{...},"stopReason":"stop"}]}
+{"type":"compaction","id":"f6g7h8i9","parentId":"e5f6g7h8","timestamp":"2024-12-03T14:10:00.000Z","summary":"User discussed X, Y, Z...","firstKeptEntryId":"c3d4e5f6","tokensBefore":50000,"systemMessage":{"role":"system","content":"You are a coding assistant.","toolsAdded":[],"timestamp":1733235000000}}
 ```
 
+`firstKeptEntryId` is required. It identifies the first entry retained from before the compaction entry. When rebuilding context, Pi replaces older summarized entries with the compaction summary and keeps the range beginning at this entry.
+
 Optional fields:
+- `systemMessage`: The replayed prompt sections and tool declarations at the compaction boundary; it becomes the leading system message of the compacted context, and system messages among the kept entries are dropped in its favor. It is absent on older session entries.
 - `usage`: LLM usage from generating the summary; included in session token and cost totals
-- `retainedTail`: Materialized `AgentMessage[]` kept after compaction. This is optional only for backward compatibility with older sessions. Newer harness-generated compactions include it so we can rebuild context from this checkpoint without walking older entries before the compaction entry.
 - `details`: Implementation-specific data (e.g., `{ readFiles: string[], modifiedFiles: string[] }` for default, or custom data for extensions)
 - `fromHook`: `true` if generated by an extension, `false`/`undefined` if pi-generated (legacy field name)
-- `firstKeptEntryId`: for compatibility with old entry format.
 
 ### BranchSummaryEntry
 
@@ -255,6 +290,8 @@ Created when switching branches via `/tree` with an LLM generated summary of the
 {"type":"branch_summary","id":"g7h8i9j0","parentId":"a1b2c3d4","timestamp":"2024-12-03T14:15:00.000Z","fromId":"f6g7h8i9","summary":"Branch explored approach A..."}
 ```
 
+`parentId` is the entry from which the new branch continues. `fromId` is the previous leaf whose abandoned path was summarized.
+
 Optional fields:
 - `usage`: LLM usage from generating the summary; included in session token and cost totals
 - `details`: File tracking data (`{ readFiles: string[], modifiedFiles: string[] }`) for default, or custom data for extensions
@@ -305,11 +342,12 @@ The session name is displayed in the session selector (`/resume`) instead of the
 
 ## Tree Structure
 
-Entries form a tree:
-- First entry has `parentId: null`
-- Each subsequent entry points to its parent via `parentId`
+Entries normally form one tree, but navigation APIs can create multiple roots:
+- A root entry has `parentId: null`; the first entry is initially the root
+- Each non-root entry points to its parent via `parentId`
 - Branching creates new children from an earlier entry
 - The "leaf" is the current position in the tree
+- Calling `resetLeaf()` or `branchWithSummary(null, ...)` allows a later entry to become another root
 
 ```
 [user msg] ─── [assistant] ─── [user msg] ─── [assistant] ─┬─ [user msg] ← current leaf
@@ -322,11 +360,10 @@ Entries form a tree:
 `buildContextEntries()` walks from the current leaf to the root, producing the active entry list while honoring compaction:
 
 1. Collects all entries on the path
-2. If a `CompactionEntry` is on the path:
+2. If one or more `CompactionEntry` values are on the path, uses the latest one:
    - Includes the compaction entry first
-   - If `retainedTail` is present, it acts as a self-contained checkpoint and entries after the compaction are included
-   - Otherwise entries from `firstKeptEntryId` to the compaction are included
-   - Then entries after compaction are included
+   - Includes non-system entries from `firstKeptEntryId` up to, but not including, the compaction entry
+   - Includes entries after the compaction entry
 3. Preserves non-message entries in the selected range so interactive mode can render them
 
 `buildSessionContext()` builds on that entry list to produce the message list for the LLM:
@@ -334,12 +371,12 @@ Entries form a tree:
 1. Extracts current model and thinking level settings from the full path
 2. Converts selected entries to messages:
    - `message` -> stored `AgentMessage`
-   - `compaction` -> `compactionSummary` plus `retainedTail` when present
+   - `compaction` -> complete system checkpoint followed by `compactionSummary`
    - `branch_summary` -> `branchSummary`
    - `custom_message` -> `CustomMessage`
-   - `custom` -> no context message
+   - `usage` and `custom` -> no context message
 
-This makes newer compactions act like self-contained checkpoints. `retainedTail` is optional only so older sessions that only store `firstKeptEntryId` continue to load correctly.
+The compaction summary replaces entries before `firstKeptEntryId`. Pre-compaction system messages are folded into the complete checkpoint rather than replayed from the retained range. Retained non-system entries and all entries after the compaction remain available to the LLM.
 
 ## Parsing Example
 
@@ -364,6 +401,9 @@ for (const line of lines) {
     case "branch_summary":
       console.log(`[${entry.id}] Branch from ${entry.fromId}`);
       break;
+    case "usage":
+      console.log(`[${entry.id}] Usage (${entry.kind}): ${entry.usage.totalTokens} tokens`);
+      break;
     case "custom":
       console.log(`[${entry.id}] Custom (${entry.customType}): ${JSON.stringify(entry.data)}`);
       break;
@@ -388,18 +428,19 @@ for (const line of lines) {
 Key methods for working with sessions programmatically.
 
 ### Static Creation Methods
-- `SessionManager.create(cwd, sessionDir?)` - New session
-- `SessionManager.open(path, sessionDir?)` - Open existing session file
+- `SessionManager.create(cwd, sessionDir?, options?)` - New session; `options` can set `id` and `parentSession`
+- `SessionManager.open(path, sessionDir?, cwdOverride?)` - Open existing session file
 - `SessionManager.continueRecent(cwd, sessionDir?)` - Continue most recent or create new
-- `SessionManager.inMemory(cwd?)` - No file persistence
-- `SessionManager.forkFrom(sourcePath, targetCwd, sessionDir?)` - Fork session from another project
+- `SessionManager.inMemory(cwd?, options?, entries?)` - No file persistence, optionally initialized from entries
+- `SessionManager.forkFrom(sourcePath, targetCwd, sessionDir?, options?)` - Fork session from another project
 
 ### Static Listing Methods
 - `SessionManager.list(cwd, sessionDir?, onProgress?)` - List sessions for a directory
 - `SessionManager.listAll(onProgress?)` - List all sessions across all projects
+- `SessionManager.listAll(sessionDir?, onProgress?)` - List sessions from a custom session root
 
 ### Instance Methods - Session Management
-- `newSession(options?)` - Start a new session (options: `{ parentSession?: string }`)
+- `newSession(options?)` - Start a new session (options: `{ id?: string, parentSession?: string }`)
 - `setSessionFile(path)` - Switch to a different session file
 - `createBranchedSession(leafId)` - Extract branch to new session file
 
@@ -407,7 +448,8 @@ Key methods for working with sessions programmatically.
 - `appendMessage(message)` - Add message
 - `appendThinkingLevelChange(level)` - Record thinking change
 - `appendModelChange(provider, modelId)` - Record model change
-- `appendCompaction(summary, firstKeptEntryId, tokensBefore, details?, fromHook?)` - Add compaction
+- `appendUsage(kind, provider, model, usage)` - Record model-attributed usage outside the conversation
+- `appendCompaction(summary, firstKeptEntryId, tokensBefore, details?, fromHook?, usage?)` - Add compaction
 - `appendCustomEntry(customType, data?)` - Extension state (not in context)
 - `appendSessionInfo(name)` - Set session display name
 - `appendCustomMessageEntry(customType, content, display, details?)` - Extension message (in context)
@@ -423,7 +465,7 @@ Key methods for working with sessions programmatically.
 - `getLabel(id)` - Get label for entry
 - `branch(entryId)` - Move leaf to earlier entry
 - `resetLeaf()` - Reset leaf to null (before any entries)
-- `branchWithSummary(entryId, summary, details?, fromHook?)` - Branch with context summary
+- `branchWithSummary(entryId, summary, details?, fromHook?, usage?)` - Branch with context summary; `entryId` may be `null` to branch from the root
 
 ### Instance Methods - Context & Info
 - `buildContextEntries()` - Get active branch entries with compaction applied

package/docs/sessions.md

@@ -33,6 +33,7 @@ For the JSONL file format and SessionManager API, see [Session Format](session-f
 | `/compact [prompt]` | Summarize older context; see [Compaction](compaction.md) |
 | `/export [file]` | Export session to HTML |
 | `/share` | Upload as private GitHub gist with shareable HTML link |
+| `/bug [description]` | Report a bug to the Pi developers; see [Reporting Bugs](#reporting-bugs) |
 
 ## Resuming and Deleting Sessions
 
@@ -138,6 +139,32 @@ When prompted, choose one of:
 
 See [Compaction](compaction.md) for branch summarization internals and extension hooks.
 
+## Reporting Bugs
+
+`/bug [description]` collects a bug report for the Pi developers. The report is not shared publicly. The dialog asks for an optional description and whether to include the session transcript. If you decline the transcript, pi offers to have the current model write a summary of what went wrong instead; the transcript is sent to your provider with your credentials, and only the summary is attached.
+
+The last step chooses where the report goes:
+
+- **Upload Report** sends it to the Pi developers through `radius.pi.dev`. No login is required; if you are logged into Radius, the report is attributed to your account so the developers can follow up. If the upload fails, pi offers to export the zip instead.
+- **Export as Zip** writes a zip archive to the current directory. Attach it to an issue or send it to the developers yourself.
+
+Both contain the same files:
+
+| File | Content |
+|------|---------|
+| `report.json` | pi version, runtime, OS, terminal, current model and provider configuration, loaded extensions, and settings. API keys, header values, URL credentials, and the analytics tracking id are never included. |
+| `diagnostics.json` | Provider and runtime error diagnostics attached to assistant messages across the whole session (failed or aborted turns, retries, error messages), plus any recorded crashes. Always included; message content is not. |
+| `session.jsonl` | The current branch of the session, only when you chose to include it. It contains file contents and command output read during the session. |
+| `summary.md` | The model-written summary, only when you chose to generate one. |
+
+Each report has a UUID. pi shows it after upload or export and records it in the session as a `pi.bug-report` entry so you can refer to it later.
+
+Set `PI_RADIUS_GATEWAY` to upload to a different Radius deployment.
+
+### Crashes
+
+When pi exits because of an uncaught exception or a fatal runtime error, it stores the error message and stack trace in `~/.pi/agent/crashes.json` (the newest five). The next interactive start shows a warning once; running `/bug` attaches the stored crashes to `diagnostics.json` and removes the file after the report is uploaded or exported. Resume the crashed session with `pi -r` first if you want the transcript in the report.
+
 ## Session Format
 
 Session files are JSONL and contain message entries, model changes, thinking-level changes, labels, compactions, branch summaries, and extension entries.

package/docs/settings.md

@@ -32,8 +32,31 @@ Use `/trust` in interactive mode to save a project trust decision for future ses
 | `defaultThinkingLevel` | string | - | Startup thinking level (saved with Ctrl+S in `/thinking`, or edited manually): `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"` |
 | `modelThinkingLevels` | object | - | Per-model startup thinking levels keyed by `"provider/modelId"`; configure from `/settings` → Default thinking level per model or edit manually |
 | `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output |
-| `showCacheMissNotices` | boolean | `false` | Show transcript notices for significant prompt-cache misses, compaction or branch-summary usage, and provider recovery diagnostics such as dropped Anthropic thinking blocks |
+| `showCacheMissNotices` | boolean | `false` | Show transcript notices for significant prompt-cache misses, successful cache-warming usage, compaction or branch-summary usage, and provider recovery diagnostics such as dropped Anthropic thinking blocks |
 | `thinkingBudgets` | object | - | Custom token budgets per thinking level. Anthropic, Google, and Bedrock use these natively. OpenAI-compatible models use them when `compat.thinkingTokenBudgetField` (or `supportsThinkingTokenBudget`) is set. |
+| `cacheWarming` | string | `"streaming"` | Prompt cache-warming mode: `"off"`, `"streaming"`, or `"idle"`. Global setting only. |
+
+#### Cache Warming
+
+Providers drop a prompt cache entry after a period of inactivity, so the first request after a pause pays full input price again. Cache warming re-sends the last request with a one-token output budget shortly before expiry:
+
+- `"off"` disables warming.
+- `"streaming"` protects expensive prefixes during long tool executions and stops as soon as the agent settles.
+- `"idle"` also considers refreshes while waiting for your next prompt, using a fixed 15% continuation probability measured from real usage.
+
+```json
+{
+  "cacheWarming": "idle"
+}
+```
+
+A refresh is sent only when the expected avoided cache-miss cost, minus the cost of the refresh, leaves at least $0.05 of expected savings. Active agent runs use 100% continuation probability. `/session` shows the next decision, continuation probability, expected savings, threshold, and estimated costs. When cache miss notices are enabled, each successful refresh appears in the transcript with its cost; notices identify extension overrides.
+
+Warming stops when the context changes (model switch, compaction, branch navigation). Idle warming stops no later than 30 minutes after the last real provider request; warming during an active agent run stops after 60 minutes. Extensions can override each decision through the [`cache_warming_decision`](extensions.md#cache_warming_decision) event.
+
+Each refresh is billed as a cache read of the full context plus one output token. Usage and cost show up in session totals but never enter model context. Pi schedules candidates at 90% of the cache lifetime while leaving at least ten seconds before expiry.
+
+Warming needs a known cache lifetime for the model and the retention tier the request used (`short`, or `long` with `PI_CACHE_RETENTION=long`). The built-in catalog carries lifetimes for direct Anthropic; custom models and other providers can declare theirs with `promptCache` in `models.json` (see [Prompt Cache Lifetimes](models.md#prompt-cache-lifetimes)). Claude models that use budget-based rather than adaptive thinking are skipped while thinking is on, because Anthropic derives the thinking budget from `max_tokens` and keys the message cache on it, so a one-token request cannot reproduce the entry.
 
 #### thinkingBudgets
 
@@ -118,6 +141,7 @@ Set `PI_SKIP_VERSION_CHECK=1` to disable the Pi version update check. Use `--off
 | `compaction.enabled` | boolean | `true` | Enable auto-compaction |
 | `compaction.reserveTokens` | number | `16384` | Tokens reserved for LLM response |
 | `compaction.keepRecentTokens` | number | `20000` | Recent tokens to keep (not summarized) |
+| `compaction.modelOverrides` | object | - | Per-model `reserveTokens` and `keepRecentTokens` overrides keyed by exact `"provider/modelId"` |
 
 ```json
 {
@@ -129,6 +153,37 @@ Set `PI_SKIP_VERSION_CHECK=1` to disable the Pi version update check. Use `--off
 }
 ```
 
+#### Per-model compaction overrides
+
+```json
+{
+  "compaction": {
+    "enabled": true,
+    "reserveTokens": 16384,
+    "keepRecentTokens": 20000,
+    "modelOverrides": {
+      "some-provider/big-model": {
+        "reserveTokens": 400000
+      },
+      "local/small-model": {
+        "reserveTokens": 2048,
+        "keepRecentTokens": 4096
+      }
+    }
+  }
+}
+```
+
+Keys match exact, case-sensitive `provider/modelId` values, not names or glob patterns. Model IDs may contain slashes (for example, `openrouter/anthropic/claude-sonnet-4`).
+
+Each token setting resolves independently: matching model override → ordinary `compaction` setting → built-in default. In the example, `some-provider/big-model` keeps the ordinary 20000 recent tokens. Token values must be non-negative safe integers. Invalid values in the matching model override produce an error when read; only omitted fields fall back to the ordinary setting. Model override entries must be objects. Invalid ordinary token settings produce an error when read, even if the active model has a valid override. Only omitted ordinary values use built-in defaults. Zero is accepted, but `reserveTokens: 0` leaves no response margin and also sets the summarization output budget to zero.
+
+Global and project settings merge recursively **before** model lookup. A project can override one field for a model without replacing its other fields or other models. A global model-specific value takes precedence over a project-wide fallback; override the same model entry in the project to change it.
+
+`enabled` is not model-specific. The active model's token settings apply to manual compaction, automatic threshold checks (including between assistant turns), and overflow recovery. Switching models takes effect on the next check or compaction. Configure overrides in JSON; `/settings` retains the ordinary auto-compaction toggle.
+
+See [compaction.md](compaction.md) for trigger and summarization behavior.
+
 ### Branch Summary
 
 | Setting | Type | Default | Description |
@@ -143,10 +198,13 @@ Set `PI_SKIP_VERSION_CHECK=1` to disable the Pi version update check. Use `--off
 | `retry.enabled` | boolean | `true` | Enable automatic agent-level retry on transient errors |
 | `retry.maxRetries` | number | `3` | Maximum agent-level retry attempts |
 | `retry.baseDelayMs` | number | `2000` | Base delay for agent-level exponential backoff (2s, 4s, 8s) |
+| `retry.maxAgentDelayMs` | number | `60000` | Max agent-level retry delay (60s) |
 | `retry.provider.timeoutMs` | number | SDK default | Provider/SDK request timeout in milliseconds |
 | `retry.provider.maxRetries` | number | `0` | Provider/SDK retry attempts |
 | `retry.provider.maxRetryDelayMs` | number | `60000` | Max server-requested delay before failing (60s) |
 
+Agent-level retries use exponential backoff capped by `retry.maxAgentDelayMs`, so long retry runs stay responsive after prolonged outages.
+
 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.
@@ -157,6 +215,7 @@ Keep `retry.provider.maxRetries` at `0` unless provider-level retries are explic
     "enabled": true,
     "maxRetries": 3,
     "baseDelayMs": 2000,
+    "maxAgentDelayMs": 60000,
     "provider": {
       "timeoutMs": 3600000,
       "maxRetries": 0,

package/docs/termux.md

@@ -96,7 +96,6 @@ termux-camera-photo out.jpg   # Take photo
 ## Limitations
 
 - **No image clipboard**: Termux clipboard API only supports text
-- **No native binaries**: Some optional native dependencies (like the clipboard module) are unavailable on Android ARM64 and are skipped during installation
 - **Storage access**: To access files in `/storage/emulated/0` (Downloads, etc.), run `termux-setup-storage` once to grant permissions
 
 ## Troubleshooting

package/docs/tui.md

@@ -4,7 +4,7 @@
 
 Extensions and custom tools can render custom TUI components for interactive user interfaces. This page covers the component system and available building blocks.
 
-**Source:** [`@earendil-works/pi-tui`](https://github.com/earendil-works/pi-mono/tree/main/packages/tui)
+**Source:** [`@earendil-works/pi-tui`](https://github.com/earendil-works/pi/tree/main/packages/tui)
 
 ## Component Interface
 
@@ -930,7 +930,7 @@ export default function (pi: ExtensionAPI) {
 
 - **Extend `CustomEditor`** (not base `Editor`) to get app keybindings (escape to abort, ctrl+d to exit, model switching, etc.)
 - **Call `super.handleInput(data)`** for keys you don't handle
-- **Working status**: custom editors keep the standalone working row by default. Pass `{ embedWorkingStatus: true }` as the fourth `CustomEditor` constructor argument to use the built-in editor-border spinner instead.
+- **Status spinners**: custom editors keep standalone status rows by default. Pass `{ embedWorkingStatus: true }` as the fourth `CustomEditor` constructor argument to embed working, compaction, branch summarization, and retry spinners in the editor border instead.
 - **Factory pattern**: `setEditorComponent` receives a factory function that gets `tui`, `theme`, and `keybindings`
 - **Pass `undefined`** to restore the default editor: `ctx.ui.setEditorComponent(undefined)`
 

package/docs/usage.md

@@ -55,6 +55,7 @@ Type `/` in the editor to open command completion. Extensions can register custo
 | `/export [file]` | Export session to HTML or JSONL |
 | `/import <file>` | Import and resume a session from a JSONL file |
 | `/share` | Upload as private GitHub gist with shareable HTML link |
+| `/bug [description]` | Report a bug to the Pi developers; see [Sessions](sessions.md#reporting-bugs) |
 | `/reload` | Reload keybindings, extensions, skills, prompts, themes, and context files |
 | `/hotkeys` | Show all keyboard shortcuts |
 | `/changelog` | Display version history |

package/examples/extensions/README.md

@@ -36,7 +36,6 @@ cp permission-gate.ts ~/.pi/agent/extensions/
 | `questionnaire.ts` | Multi-question input with tab bar navigation between questions |
 | `tool-override.ts` | Override built-in tools (e.g., add logging/access control to `read`) |
 | `dynamic-tools.ts` | Register tools after startup (`session_start`) and at runtime via command, with prompt snippets and tool-specific prompt guidelines |
-| `kimi-deferred-tools.ts` | Search for and progressively activate tools for Kimi's deferred-tool loading protocol |
 | `structured-output.ts` | Final structured-output tool that returns `terminate: true` so the agent can end on the tool call |
 | `built-in-tool-renderer.ts` | Custom compact rendering for built-in tools (read, bash, edit, write) while keeping original behavior |
 | `minimal-mode.ts` | Override built-in tool rendering for minimal display (only tool calls, no output in collapsed mode) |

package/examples/extensions/custom-provider-anthropic/index.ts

@@ -27,9 +27,11 @@ import {
 	type Api,
 	type AssistantMessage,
 	type AssistantMessageEventStream,
-	type Context,
 	calculateCost,
+	collapseSystemMessages,
 	createAssistantMessageEventStream,
+	getCurrentSystemPrompt,
+	getCurrentTools,
 	type ImageContent,
 	type Message,
 	type Model,
@@ -42,6 +44,7 @@ import {
 	type Tool,
 	type ToolCall,
 	type ToolResultMessage,
+	type TranscriptContext,
 } from "@earendil-works/pi-ai";
 import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
 
@@ -334,10 +337,15 @@ function mapStopReason(reason: string): StopReason {
 
 function streamCustomAnthropic(
 	model: Model<Api>,
-	context: Context,
+	context: TranscriptContext,
 	options?: SimpleStreamOptions,
 ): AssistantMessageEventStream {
 	const stream = createAssistantMessageEventStream();
+	// The transcript carries the prompt and tools in its system messages. This provider sends
+	// one top-level system prompt, so fold later system messages into the leading one first.
+	const transcript = collapseSystemMessages(context);
+	const systemPrompt = getCurrentSystemPrompt(transcript.messages);
+	const tools = getCurrentTools(transcript.messages);
 
 	(async () => {
 		const output: AssistantMessage = {
@@ -393,7 +401,7 @@ function streamCustomAnthropic(
 			// Build request params
 			const params: MessageCreateParamsStreaming = {
 				model: model.id,
-				messages: convertMessages(context.messages, isOAuth, context.tools),
+				messages: convertMessages(transcript.messages, isOAuth, tools),
 				max_tokens: options?.maxTokens || Math.floor(model.maxTokens / 3),
 				stream: true,
 			};
@@ -407,25 +415,25 @@ function streamCustomAnthropic(
 						cache_control: { type: "ephemeral" },
 					},
 				];
-				if (context.systemPrompt) {
+				if (systemPrompt) {
 					params.system.push({
 						type: "text",
-						text: sanitizeSurrogates(context.systemPrompt),
+						text: sanitizeSurrogates(systemPrompt),
 						cache_control: { type: "ephemeral" },
 					});
 				}
-			} else if (context.systemPrompt) {
+			} else if (systemPrompt) {
 				params.system = [
 					{
 						type: "text",
-						text: sanitizeSurrogates(context.systemPrompt),
+						text: sanitizeSurrogates(systemPrompt),
 						cache_control: { type: "ephemeral" },
 					},
 				];
 			}
 
-			if (context.tools) {
-				params.tools = convertTools(context.tools, isOAuth);
+			if (tools.length > 0) {
+				params.tools = convertTools(tools, isOAuth);
 			}
 
 			// Handle thinking/reasoning
@@ -474,9 +482,7 @@ function streamCustomAnthropic(
 						output.content.push({
 							type: "toolCall",
 							id: event.content_block.id,
-							name: isOAuth
-								? fromClaudeCodeName(event.content_block.name, context.tools)
-								: event.content_block.name,
+							name: isOAuth ? fromClaudeCodeName(event.content_block.name, tools) : event.content_block.name,
 							arguments: {},
 							partialJson: "",
 							index: event.index,

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

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-custom-provider",
-  "version": "0.85.1",
+  "version": "0.86.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-custom-provider",
-      "version": "0.85.1",
+      "version": "0.86.0",
       "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": "0.85.1",
+  "version": "0.86.0",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/extensions/custom-provider-gitlab-duo/index.ts

@@ -13,7 +13,6 @@ import {
 	type Api,
 	type AssistantMessageEventStream,
 	anthropicMessagesApi,
-	type Context,
 	createAssistantMessageEventStream,
 	type Model,
 	type OAuthCredentials,
@@ -21,6 +20,7 @@ import {
 	openAIResponsesApi,
 	type SimpleStreamOptions,
 	type ThinkingLevelMap,
+	type TranscriptContext,
 } from "@earendil-works/pi-ai/compat";
 import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
 
@@ -306,7 +306,7 @@ async function refreshGitLabToken(credentials: OAuthCredentials, signal: AbortSi
 
 export function streamGitLabDuo(
 	model: Model<Api>,
-	context: Context,
+	context: TranscriptContext,
 	options?: SimpleStreamOptions,
 ): AssistantMessageEventStream {
 	const stream = createAssistantMessageEventStream();