You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+4Lines changed: 4 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,6 +15,8 @@ GitHub Releases page; `0.8.0` is the new starting line.
15
15
16
16
## Unreleased
17
17
18
+
## 0.42.0 (2026-06-12)
19
+
18
20
-**Adversarial branch review hardening.** A multi-agent review pass confirmed and fixed: committed-but-clean isolation worktrees are now retained (commits ahead of the creation base count as changes — they were previously orphaned on cleanup); foreground shell commands and relative-path file edits now resolve against the agent's work dir, so worktree isolation actually binds them (host exec gained a `cwd` argument); safe mode now also disables the read-only-command prompt elision; locally parallel-safe MCP/tools run in parallel in the same-step gate; worktree add/remove serializes per repo. Behavior notes: same-step tool calls without `supports_parallel` now serialize deterministically (previously fully concurrent), and text-mode error diagnostics moved to stderr — capture `2>&1` or use `--output-format stream-json` if you scraped stdout.
19
21
-**The agent now knows its own permission posture.** A live permissions-state reminder renders the enforced profile, safe-mode/yolo/auto flags, mutation/network allowances, session-approved actions, and the shell gate's command-shaping rules — re-emitted exactly when the posture changes (/yolo, /auto, /trust, new approvals) instead of the model discovering policy through denied tool calls.
20
22
-**Edits recover from whitespace and smart-punctuation drift.** StrReplaceFile no longer hard-fails with "old string not found" when the only mismatch is trailing whitespace, indentation, or smart quotes/dashes: a graduated line-window ladder relocates the edit, replaces the actual file slice (preserving CRLF endings), and names the relaxation it used in the tool message. Multiple fuzzy hits without replace_all still error, so ambiguity is never silently resolved.
@@ -32,6 +34,8 @@ GitHub Releases page; `0.8.0` is the new starting line.
32
34
-**Inline `/command` references get acted on, not just explained away.** When a message mentions a slash command mid-sentence (e.g. "your `/goal` today is to `/plan` and build the page"), the command doesn't auto-run — but the agent no longer leads its reply by reporting it as failed. The per-turn reminder and the system prompt now steer the agent to act on the intent: call the real `EnterPlanMode` tool for `/plan` (clarified as a genuine, callable tool so models stop doubting it exists), pursue the described objective for `/goal`, load `/skill:<name>` via `ReadSkill`, and apply equivalent guidance for other commands — only surfacing how to invoke the literal command when genuinely needed.
33
35
-**The "thinking" shimmer no longer runs while a foreground command does.** When the agent started a long-running foreground process — a dev server via `npm`/`docker`, a watch task — the shimmering verb spinner ("Working…/Thinking…") kept animating for the whole turn, implying the agent was busy when it was really just awaiting the subprocess. The spinner is now suppressed while any foreground tool is mid-execution; the tool card's own animated running marker (and its streaming output) carries the liveness, so the shimmer means "the agent is thinking" again and reappears the moment the command returns.
34
36
37
+
Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.42.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
38
+
35
39
## 0.41.0 (2026-06-11)
36
40
37
41
- **New `/goal` command — goal-driven execution that loops until verified.** `/goal <objective>` sets a persistent thread goal the agent pursues across turns, restarts, and context compaction until it is verifiably complete. It kicks off immediately with a success-criteria derivation prompt and is re-injected each turn with fidelity rules (no scope-shrinking, no easier-to-test substitutes) and an evidence-based completion audit — completion may only be claimed after every requirement is proven against current state. The new root-only `UpdateGoal` tool marks the goal `complete` (after that audit) or `blocked` (after a strict three-strike audit) and stops the reminders; opt-in `goal.auto_continue` (new config table, default off, `max_continuations` 1–10, capped at 3) drives automatic continuation turns toward the goal until it is marked, a tool call is rejected, or the cap is reached, with a wrap-up instruction on the final continuation. Subcommands: `view`, `pause`, `resume`, `clear`. Objectives are injected as untrusted data, never as higher-priority instructions.
Copy file name to clipboardExpand all lines: README.md
+24-23Lines changed: 24 additions & 23 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -50,14 +50,15 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
50
50
51
51
---
52
52
53
-
## 🆕 What's New in 0.41.0
53
+
## 🆕 What's New in 0.42.0
54
54
55
-
-**Goal-driven execution: new `/goal`, `/best-practices`, and `/learn` commands.**`/goal <objective>` sets a persistent thread goal the agent pursues across turns, restarts, and compaction until it is verifiably complete — with an evidence-based completion audit, a root-only `UpdateGoal` tool to mark it `complete`/`blocked`, and opt-in `goal.auto_continue` to loop automatically toward it. `/best-practices` (alias `/bp`) injects engineering-discipline guidance now also shipped always-on in the default prompt, and `/learn` distills session lessons into per-project memory.
56
-
-**Statusline v2: a full redesign of the shell footer.** Colored segments with a gradient context bar, working spinner, live token speed, session cost/budget, thinking-effort badge, git diff counts, elapsed time, and a clock — all fail-closed and tunable via the new `/statusline` command (persisted under `[tui.statusline]`), with ASCII fallback and narrow-width graceful degradation.
57
-
-**Agentic orchestration hardening.** Parallel subagents and background tasks get distinctive codenames, foreground `RunAgents` batches run concurrently and roll up child RISKS/BLOCKERS, the review pipeline decomposes large diffs and adversarially verifies every finding, and restricted-profile subagents are now offline, secret-scrubbed, and workspace-jailed by default — enforced at execution time, not just prompted.
58
-
-**TUI polish.** Flicker-free streaming on synchronized-output terminals, inline ghost-completion for slash commands, monotonic tool-call rows, shell error briefs that surface the failing command's output, and no more transient `<invalid>` flashes or raw-mode hangs on exit.
55
+
-**Parallel coding agents are truly isolated.**`isolation="worktree"` is now enforced, not just recorded: each background write agent runs in its own git worktree of HEAD and reports its worktree path with a diff summary so changes merge deliberately, while foreground shell commands and relative-path edits resolve against the agent's own work dir. Worktrees with commits ahead of their base are retained instead of orphaned, and worktree add/remove serializes per repo.
56
+
-**The agent knows its own permission posture — and stops asking when it shouldn't.** A live permissions-state reminder renders the enforced profile, safe-mode/yolo/auto flags, mutation/network allowances, and shell-gate rules, re-emitted exactly when the posture changes. Provably read-only commands (`ls`, `git status`) no longer interrupt the root agent with an approval dialog, via a fail-closed positive allowlist.
57
+
-**Edits recover from whitespace and smart-punctuation drift.**`StrReplaceFile` no longer hard-fails when the only mismatch is trailing whitespace, indentation, or smart quotes/dashes — a graduated line-window ladder relocates the edit, preserves CRLF endings, and names the relaxation it used. Ambiguous fuzzy matches still error rather than silently resolving.
58
+
-**MCP servers are controllable.** Per-server `enabledTools`/`disabledTools` arrays in `mcp.json` scope a noisy server down to the tools you want, and a new `mcp.client.startup_timeout_ms` (default 30s) means a hung server can no longer stall every turn — `/mcp` now shows one actionable line per failed server.
59
+
-**Quality of life.**`/model` switches now carry the conversation forward via a plain-text summary instead of starting fresh; typo'd config keys warn with their dotted path and source file (`PYTHINKER_STRICT_CONFIG=1` escalates to a startup error); project-scope hooks load only after `/trust`; the in-app updater recovers from Homebrew's untrusted-tap refusal; `/export` redacts secret-named values; inline `/command` references get acted on; and the thinking shimmer no longer animates while a foreground command runs.
59
60
60
-
Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.41.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
61
+
Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.42.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
61
62
62
63
63
64
---
@@ -147,7 +148,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
@@ -44,7 +44,7 @@ On Windows, run the PowerShell bootstrap. It downloads the native installer, ver
44
44
irm https://pythinker.com/install.ps1 | iex
45
45
```
46
46
47
-
You can also download `PythinkerSetup-0.41.0.exe` manually from the [latest release](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
47
+
You can also download `PythinkerSetup-0.42.0.exe` manually from the [latest release](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
Copy file name to clipboardExpand all lines: docs/en/release-notes/breaking-changes.md
+7Lines changed: 7 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,6 +4,13 @@ This page documents breaking changes in Pythinker Code releases and provides mig
4
4
5
5
## Unreleased
6
6
7
+
## 0.42.0 (2026-06-12)
8
+
9
+
No configuration or session-data breaking changes. Two behavior changes may affect scripted or automated use:
10
+
11
+
-**Text-mode error diagnostics now go to stderr.** Previously they were interleaved on stdout. If you scrape `pythinker` stdout in text mode for error text, capture `2>&1` or switch to `--output-format stream-json`.
12
+
-**Project- and local-scope hooks now require trusting the project.** A cloned repo's `.pythinker/config.toml` hooks no longer auto-run at session start — run `/trust` once per project to record a durable decision (stored user-side in `trusted_projects.json`). Until then, those hooks are stripped with a warning naming the fix.
13
+
7
14
## 0.41.0 (2026-06-11)
8
15
9
16
No breaking changes. This release is compatible with 0.40.1 user configuration, native installs, and session data.
0 commit comments