zidane 5.14.4 → 6.0.0

package/docs/CHAT.md

@@ -133,7 +133,7 @@ The table below indexes every named export; sections further down dive into the
 | `enabled-toggle-set` | `useEnabledToggleSet({ catalog, keyOf, settingKey })` — generic state machine for `enabledSkills` / `enabledMcps` (undefined = all enabled, `[]` = off, `[names]` = allowlist). |
 | `files-discovery` | `listProjectFiles({ cwd, signal? })` → `FileEntry[]`, gitignored paths excluded. |
 | `format` | `fmtTokens`, `ageString`, `shortId`, `compactPath` — display-only helpers. |
-| `generate-title` | `generateSessionTitle({ session, provider, model, signal? })` + `cleanTitle`. |
+| `generate-title` | `generateSessionTitle({ session, provider, model, signal? })` + `cleanTitle` + `shouldAutoGenerateTitle(turns, metadata?)` (true once a session has ≥2 turns and no explicit `metadata.title` — the TUI's automatic-titling gate). |
 | `hints` | Footer + prompt-hint plumbing — `Hint`, `hintsLength`, `clipHintsToWidth`, `truncateTrailing`. Plain-text math; rendering is the consumer's job. |
 | `interactions` | Plan + Q&A protocol (`present_plan`, `ask_user`). See **Interactions** and `docs/INTERACTIONS.md`. |
 | `keybindings` | Action catalog + JSONC overrides — `KEYBINDING_DEFS`, `KEYBINDING_DEF_BY_ACTION`, `DEFAULT_KEYBINDINGS`, `parseBindingSpec`, `matchesBinding`, `mergeKeybindings`, `formatBindingForDisplay`, `groupBindings`, `KEYBINDING_KEY_COL_WIDTH`, `readKeybindings`, `ensureKeybindingsFile`, `keybindingsPath`, `stripJsonComments`. See **Keybindings**. |
@@ -483,11 +483,12 @@ type ToolCallDisplay = 'hidden' | 'formatted' | 'full'
 
 `useSettings()` returns `{ settings, toggle, setSetting }`. `toggle` is restricted at the type level to `BooleanSettingKey` (`[K in keyof Settings]-?: Settings[K] extends boolean ? K : never`); `setSetting` is the general writer.
 
-Three tables drive any settings UI (TUI tabs today, GUI panels tomorrow) — they're the source of truth so new settings land automatically:
+Four tables drive any settings UI (TUI tabs today, GUI panels tomorrow) — they're the source of truth so new settings land automatically:
 
-- `SETTINGS_CATEGORIES: SettingsCategoryDescriptor[]` — display order + labels for the high-level buckets (`agent`, `ui`). Each toggle / choice declares which bucket it belongs to via its `category` field.
+- `SETTINGS_CATEGORIES: SettingsCategoryDescriptor[]` — display order + labels for the high-level buckets (`agent`, `ui`). Each toggle / choice / input declares which bucket it belongs to via its `category` field.
 - `SETTINGS_TOGGLES: SettingsToggle[]` — boolean rows. `key` is the narrowed `BooleanSettingKey`; `category: SettingsCategory` routes the row to the right tab.
-- `SETTINGS_CHOICES: SettingsChoice[]` — value-from-options rows. `category` field on every entry. Currently spans both buckets: `autoCompactThreshold`, `userInstructionsScope` (agent); `toolCallDisplay`, `editDiffDisplay`, `theme`, `uiMode`, `targetFps` (ui).
+- `SETTINGS_CHOICES: SettingsChoice[]` — value-from-options rows. `category` field on every entry. Currently spans both buckets: `autoCompactThreshold`, `userInstructionsScope` (agent); `toolCallDisplay`, `editDiffDisplay`, `theme`, `uiMode`, `targetFps`, `ctrlCBehavior`, `terminalTitle` (ui). `terminalTitle: 'icon-session'` pairs with the `sessionIcon` input to render the tab title as `{icon} · {session}`.
+- `SETTINGS_INPUTS: SettingsInput[]` — free-text rows edited via a single-line input (`key` is the narrowed `StringSettingKey`). Currently `sessionIcon` (ui), shown only while `terminalTitle` is `'icon-session'`. The modal renders the value (or `placeholder` when empty) and opens a footer editor on `enter`.
 
 ## Theme
 
@@ -765,7 +766,7 @@ agent.hooks.hook('compact:end', (ctx) => {
 
 ## Context-usage breakdown
 
-A categorized view of what's consuming the context window — system prompt, rules (AGENTS.md/CLAUDE.md), skills catalog, MCP instructions, subagent definitions, tool definitions, MCP tools, conversation, plus deferred (lazy) tools, the autocompact buffer, and free space. Surfaced as the TUI `ctrl+g` panel and the GUI context popover; both consume the same data.
+A categorized view of what's consuming the context window — system prompt, rules (AGENTS.md/CLAUDE.md), skills catalog, MCP instructions, subagent definitions, tool definitions, MCP tools, conversation, plus deferred (lazy) tools, the autocompact buffer, and free space. Surfaced as the TUI `ctrl+shift+g` panel and the GUI context popover; both consume the same data.
 
 - **`agent.getContextBreakdown(opts?)`** (on the core `Agent`, see `docs/ARCHITECTURE.md`) returns a `ContextBreakdown | null`. It snapshots the assembled prompt sections at run time (and a skills-only **pre-run** assembly before the first turn, so the panel works the moment the chat screen opens), then shapes them via `buildContextBreakdown`. The snapshot is cleared on `reset()` / `destroy()`, so it never leaks stale data across sessions.
 - **`buildContextBreakdown(snapshot)`** (`zidane/chat` + `zidane/chat/pure`, node-free) is the pure shaper. Live categories always reconcile to the real last-turn total (`conversation = used − Σ(other live)`), so the bar can never contradict the footer's `ctx` gauge. Free space and the autocompact buffer are exact; per-section counts are heuristic (`estimateTokens`) unless the provider supplies exact counts.
@@ -1097,7 +1098,7 @@ Render path expectations on the `'tool'` `StreamEvent`:
 
 `listSessionMeta(store, filter?)` uses `Promise.allSettled` so a single corrupt row doesn't take down the picker. `filter.projectRoot` scopes the list to one project (current TUI default); pass `null` to ask for untagged legacy sessions specifically.
 
-`deriveSessionTitle(turns, metadata)` prefers `metadata.title` (set by `generateSessionTitle`), then `titleFromTurns(turns)` (one-line first user message), then the literal `'untitled'`.
+`deriveSessionTitle(turns, metadata)` prefers `metadata.title` (set by `generateSessionTitle`), then `titleFromTurns(turns)` (one-line first user message), then the literal `'New session'` (`DEFAULT_SESSION_TITLE`).
 
 ### Transcript view rules
 

package/docs/EXECUTION_CONTEXT.md

@@ -251,6 +251,22 @@ Because there's no isolation, the agent's commands can read and modify anything
 your own shell can. Prefer `docker` or `e2b` when you don't fully trust what the
 agent might run.
 
+The process context also implements the optional `fileSize` capability — a
+containment-aware size probe that lets whole-file tools (`read_file`, `edit`,
+`multi_edit`, grep's no-ripgrep fallback) refuse multi-GB targets (256MB
+ceiling) instead of materializing them into host memory. The docker context
+implements the same probe via `wc -c` through its exec (its `readFile` also
+gets transport headroom above the tool ceiling, so tool policy — not the
+docker transport — decides read limits). Remote sandbox contexts (e2b,
+daytona, custom providers) probe identically through the sandbox's shell —
+one extra round-trip per whole-read tool call, paid so a multi-GB file is
+refused before the SDK transfers it into host memory. The experience is
+uniform across contexts: the same 256MB ceiling, the same refusal message.
+One residual remains in the remote SDK contexts: `exec` output is buffered
+inside the provider SDKs and can't be capped from our side, so a command that
+streams GBs to stdout within its timeout can still balloon the host — bounded
+in time by the command timeout, but not in bytes.
+
 ---
 
 ## Programmatic use