tinker-agent 2.9.0 → 2.11.0

package/CHANGELOG.md

@@ -5,6 +5,72 @@ All notable user-facing changes to Tinker are documented here. The project follo
 
 ## [Unreleased]
 
+## [2.11.0] - 2026-09-08
+
+### Added
+
+- Offer directories in the TUI `@` file-mention popup. Ancestor directories of
+  workspace files now appear alongside files, ranked after matching files, and
+  selecting a directory inserts its path directly instead of attempting an
+  image import.
+- Offer a retry selection in the TUI after provider retries are exhausted, so a
+  failed model request can be retried without re-entering the prompt.
+
+### Changed
+
+- Cache ESLint results for `check:fast` and split the fast test tier into
+  twelve independent shards, shortening local iteration while keeping the
+  serial full test run as the final gate.
+
+### Fixed
+
+- Align `Grep` context-line precedence and remove an unsupported regex hint
+  from its documentation.
+- Warm up the fake ripgrep binary in tests to absorb the macOS first-execution
+  validation delay.
+- Cancel pending image file opens without leaking file handles.
+- Emphasize TUI timeline labels and add spacing between messages.
+- Finalize scoped SQLite queries before closing the session database.
+
+## [2.10.0] - 2026-09-06
+
+### Added
+
+- Add remote access for paired clients. `tinker serve --config <path>` runs the
+  local daemon that paired remote clients connect to, and
+  `tinker connect --config <path>` attaches a terminal client to a running
+  service; exiting the client detaches without stopping the service. See
+  `docs/remote-access.md`. A native iOS client under `client/Tinker` is included
+  for acceptance.
+- Add `offset` and `head_limit` pagination to `Glob` results. Long result sets
+  now report whether more matches remain instead of being silently capped.
+- Add `cols` and `rows` options to `Bash` for custom initial PTY dimensions when
+  `tty=true`, so terminal applications that require a specific size can run in
+  an appropriately sized pseudo-terminal.
+
+### Changed
+
+- Run `Grep` directory searches with ripgrep's working directory set to the search
+  directory and `.` as the path argument. Directory globs such as `sub/**` now
+  match from that directory; globs that relied on absolute search paths may need
+  updating. Explicit file searches keep their existing invocation.
+- Increase the default `Bash` foreground wait before a command continues in the
+  background, and clarify how `TaskOutput` and `TaskInput` poll PTY sessions.
+- Omit internal file hashes from tool observations; the model sees the same
+  content without opaque bookkeeping tokens.
+
+### Fixed
+
+- Stop `TaskStop` from hanging when a shell's child processes survive after the
+  shell itself exits; stopping a task now reliably reports its final state.
+- Preserve `Grep` match context across paginated results, keep long-line matches
+  instead of dropping them, and report counts and paginated records
+  consistently, including a `count-matches` mode with explicit counting units.
+- Resolve symbolic-link search roots in `Glob` while preserving result paths,
+  and exclude directory and broken symbolic links from results.
+- Accept pagination arguments in `Read` when reading empty files instead of
+  rejecting the call.
+
 ## [2.9.0] - 2026-09-05
 
 ### Added
@@ -398,7 +464,9 @@ All notable user-facing changes to Tinker are documented here. The project follo
 - First formal npm release under the `tinker-agent` package name with the `tinker`
   executable.
 
-[Unreleased]: https://github.com/ishowshao/tinker/compare/v2.9.0...HEAD
+[Unreleased]: https://github.com/ishowshao/tinker/compare/v2.11.0...HEAD
+[2.11.0]: https://github.com/ishowshao/tinker/releases/tag/v2.11.0
+[2.10.0]: https://github.com/ishowshao/tinker/releases/tag/v2.10.0
 [2.9.0]: https://github.com/ishowshao/tinker/releases/tag/v2.9.0
 [2.8.0]: https://github.com/ishowshao/tinker/releases/tag/v2.8.0
 [2.7.0]: https://github.com/ishowshao/tinker/releases/tag/v2.7.0

package/README.md

@@ -34,6 +34,33 @@ This does not pretend that any model has infinite tokens or guarantee that it wi
   explicit model and context limits. Actual provider support must be established
   by a qualification matrix; transport compatibility alone is not a guarantee.
 
+### Provider retry selection
+
+When automatic retries for a provider request are exhausted, the TUI offers
+**Retry again** or **End this turn**. Retrying reuses the same request within the
+same turn and iteration, with a fresh automatic retry allowance. Ending the turn
+(or pressing Esc in the selection) records the original failure. The selection
+adds no conversation message and applies only to the current running process.
+Retryable failures include HTTP 429/500/502/503/504, structured `server_error`
+and `rate_limit_exceeded` errors inside provider streams or failed Responses,
+and transient connection failures, including socket resets during streaming.
+Tool failures and non-retryable errors keep their existing behavior. One-shot
+and remote service runs do not wait for this TUI selection.
+
+### PTY screen size
+
+`Bash` accepts optional `cols` and `rows` for the initial PTY screen size:
+
+```json
+{"command":"python3 -q","tty":true,"cols":160,"rows":48}
+```
+
+Each omitted dimension keeps its default: 80 columns and 24 rows. Columns accept
+integers from 2 to 1000; rows accept integers from 1 to 1000. When `tty` is omitted
+or `false`, dimensions are ignored and execution continues through ordinary pipes.
+`TaskOutput` and `TaskInput` report the actual screen size. Dimensions are set at
+creation; running tasks cannot be resized through these tools.
+
 ### Reading another session's history
 
 Both Recall tools accept an optional `sessionId` (a canonical session UUID).
@@ -158,6 +185,8 @@ The installed package exposes this public CLI:
 | `tinker run [--profile <profile-name>] [--yolo] --stdin` | Read the prompt from standard input until EOF. |
 | `tinker run [--profile <profile-name>] [--yolo] --file <path>` | Read the prompt from a UTF-8 text file. |
 | `tinker update` | Update the global npm installation from the official npm registry. |
+| `tinker serve --config <path>` | Run the local daemon for paired remote clients. |
+| `tinker connect --config <path>` | Attach a terminal client to a service; exiting detaches only. |
 | `tinker --help` | Show top-level CLI help. |
 | `tinker help run` | Show one-shot command help. |
 | `tinker help update` | Show update command help. |
@@ -229,7 +258,7 @@ are required. Boolean environment values accept case-insensitive `true/false`,
 | `EXA_API_KEY` | Tooling | All modes | No | Non-empty string | — | Yes | Enables WebSearch and the Exa WebFetch backend when set. |
 | `TINKER_MCP_TIMEOUT_MS` | Tooling | All modes | No | Positive integer | `60000` | No | MCP tool-call timeout in milliseconds. |
 | `TINKER_MCP_MAX_OBSERVATION_CHARS` | Tooling | All modes | No | Positive integer | `40000` | No | Maximum model-visible characters in one MCP result. |
-| `TINKER_BASH_DEFAULT_TIMEOUT_MS` | Tooling | All modes | No | Positive integer | `5000` | No | Default Bash foreground timeout in milliseconds. |
+| `TINKER_BASH_DEFAULT_TIMEOUT_MS` | Tooling | All modes | No | Positive integer | `60000` | No | Default Bash foreground timeout in milliseconds. |
 | `TINKER_BASH_MAX_TIMEOUT_MS` | Tooling | All modes | No | Positive integer | `600000` | No | Maximum Bash foreground timeout in milliseconds. |
 | `TINKER_YOLO` | Tooling | All modes | No | Boolean | `false` | No | Allow high-confidence destructive Bash commands without confirmation. |
 | `TINKER_GREP_TIMEOUT_MS` | Tooling | All modes | No | Positive integer | `20000` | No | Bundled ripgrep invocation timeout in milliseconds. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "tinker-agent",
-  "version": "2.9.0",
+  "version": "2.11.0",
   "description": "A personal coding agent with an interactive TUI and one-shot CLI.",
   "license": "Apache-2.0",
   "type": "module",
@@ -23,6 +23,7 @@
     "src/memory",
     "src/model",
     "src/observation",
+    "src/remote",
     "src/session",
     "src/skills",
     "src/tools",
@@ -65,14 +66,15 @@
     "docs:check": "bun scripts/render-public-contract-docs.ts --check",
     "tinker": "bun src/cli/index.ts",
     "check": "bun run check:source-lines && bun run typecheck && bun run format:check && bun run lint && bun run docs:check && bun run test && bun run bench:smoke",
-    "check:fast": "bun run check:source-lines && bun run typecheck && bun run format:check && bun run lint && bun run test:fast",
+    "check:fast": "bun run check:source-lines && bun run typecheck && bun run format:check && bun run lint:fast && bun run test:fast",
     "check:source-lines": "bun scripts/check-source-lines.ts",
     "format": "biome format --write .",
     "format:check": "biome format .",
     "lint": "eslint \"bin/**/*.js\" \"src/**/*.{ts,tsx}\" \"scripts/**/*.ts\" \"packages/**/*.ts\" --max-warnings=0",
+    "lint:fast": "bun run lint --cache --cache-strategy content --cache-location .cache/eslint-fast/",
     "lint:fix": "eslint \"bin/**/*.js\" \"src/**/*.{ts,tsx}\" \"scripts/**/*.ts\" \"packages/**/*.ts\" --fix",
     "test": "FORCE_COLOR=0 bun test",
-    "test:fast": "FORCE_COLOR=0 bun test --path-ignore-patterns='**/*pty*.test.ts' --path-ignore-patterns='**/native-host-integration.test.ts'",
+    "test:fast": "bun scripts/run-test-shards.ts --path-ignore-patterns='**/*pty*.test.ts' --path-ignore-patterns='**/native-host-integration.test.ts'",
     "test:e2e": "FORCE_COLOR=0 bun test src/__tests__/cli-pty src/__tests__/pty-tui-harness packages/tinker-chrome/__tests__/native-host-integration",
     "typecheck": "tsc --noEmit"
   },

package/src/agent/loop.ts

@@ -1,3 +1,5 @@
+import type { ModelRequestFailedData } from "../events/types";
+import type { ProviderRetryDecision } from "./runtime-provider-retry";
 import {
   materializeModelRequest,
   type MaterializedModelRequest,
@@ -74,6 +76,11 @@ export type RunAgentInput = {
     usage: ContextUsageSnapshot;
   };
   transientRetryDelaysMs?: readonly number[];
+  requestProviderRetry?: (
+    iteration: IterationIdentity,
+    failure: ModelRequestFailedData,
+    signal: AbortSignal,
+  ) => Promise<ProviderRetryDecision>;
 };
 
 export class FatalAgentTurnError extends Error {
@@ -196,12 +203,13 @@ export async function runAgent(input: RunAgentInput): Promise<RunAgentResult> {
       return failedResult(error, iteration);
     }
 
+    let maxAttempts = MODEL_REQUEST_MAX_ATTEMPTS;
     await input.runtimeSession.append({
       type: "model.request.started",
       ...iteration,
       data: {
         attemptNumber: 1,
-        maxAttempts: MODEL_REQUEST_MAX_ATTEMPTS,
+        maxAttempts,
       },
     });
 
@@ -240,7 +248,7 @@ export async function runAgent(input: RunAgentInput): Promise<RunAgentResult> {
           ...iteration,
           data: {
             attemptNumber,
-            maxAttempts: MODEL_REQUEST_MAX_ATTEMPTS,
+            maxAttempts,
           },
         });
       }
@@ -289,19 +297,47 @@ export async function runAgent(input: RunAgentInput): Promise<RunAgentResult> {
           transientRetries,
           transientRetryDelaysMs,
         });
+        const failure = modelRequestFailureData({
+          error,
+          request,
+          attemptNumber,
+          maxAttempts,
+          retryDisposition: decision.disposition,
+          ...(decision.disposition === "scheduled" && decision.delayMs > 0
+            ? { retryDelayMs: decision.delayMs }
+            : {}),
+        });
         await input.runtimeSession.append({
           type: "model.request.failed",
           ...iteration,
-          data: modelRequestFailureData({
-            error,
-            request,
-            attemptNumber,
-            retryDisposition: decision.disposition,
-            ...(decision.disposition === "scheduled" && decision.delayMs > 0
-              ? { retryDelayMs: decision.delayMs }
-              : {}),
-          }),
+          data: failure,
         });
+        if (decision.disposition === "exhausted" && input.requestProviderRetry) {
+          let retry: ProviderRetryDecision;
+          try {
+            retry = await input.requestProviderRetry(iteration, failure, input.signal);
+          } catch (retryError) {
+            if (input.signal.aborted) {
+              return cancelledResult(
+                cancellation(input.signal, iteration, "model_request"),
+                iteration,
+              );
+            }
+            throw retryError;
+          }
+          if (input.signal.aborted) {
+            return cancelledResult(
+              cancellation(input.signal, iteration, "model_request"),
+              iteration,
+            );
+          }
+          if (retry === "retry") {
+            reasoningOnlyRetries = 0;
+            transientRetries = 0;
+            maxAttempts = attemptNumber + MODEL_REQUEST_MAX_ATTEMPTS;
+            continue;
+          }
+        }
 
         if (decision.disposition === "scheduled") {
           if (decision.kind === "reasoning_only") {
@@ -349,7 +385,7 @@ export async function runAgent(input: RunAgentInput): Promise<RunAgentResult> {
       ...iteration,
       data: {
         attemptNumber: successfulAttempt,
-        maxAttempts: MODEL_REQUEST_MAX_ATTEMPTS,
+        maxAttempts,
         output: modelOutput,
       },
     });
@@ -823,6 +859,7 @@ function modelRequestFailureData(input: {
   error: unknown;
   request: PreparedModelRequest;
   attemptNumber: number;
+  maxAttempts: number;
   retryDisposition: "scheduled" | "not_retryable" | "exhausted";
   retryDelayMs?: number;
 }) {
@@ -830,7 +867,7 @@ function modelRequestFailureData(input: {
     input.error instanceof ProviderResponseError ? input.error : undefined;
   return {
     attemptNumber: input.attemptNumber,
-    maxAttempts: MODEL_REQUEST_MAX_ATTEMPTS,
+    maxAttempts: input.maxAttempts,
     code: providerError?.code ?? ("provider_request_error" as const),
     retryDisposition: input.retryDisposition,
     ...(input.retryDelayMs === undefined ? {} : { retryDelayMs: input.retryDelayMs }),