@shuyhere/bb-agent 0.0.13 → 0.0.15

package/CHANGELOG.md

@@ -5,6 +5,42 @@ All notable changes to BB-Agent will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.0.15] - 2026-04-12
+
+### Fixed
+
+- fullscreen bash output now streams live stdout/stderr and keeps running, finished, historical, and expanded/collapsed tool blocks visually consistent with width-aware tail previews and elapsed/took footer hints
+- bash tool titles now skip shell prelude lines like `set -e`, show configured timeout values in the UI, and validate invalid timeout arguments instead of accepting zero or non-finite values
+- fixed the session getting stuck after interrupted or failed tool calls by flushing synthetic tool results before later prompts, preventing follow-up turns from failing with missing tool output
+- Codex tool-call request handling is more robust: tool calls are serialized sequentially, orphan tool results are sanitized out of requests, and streamed/done function-call events are deduplicated more safely
+- plain URLs and hyphenated text no longer trigger accidental markdown horizontal-rule rendering while explicit markdown rules and setext headings still render correctly
+- fullscreen resume menu handling now awaits the async resume path correctly instead of dropping back through the synchronous menu flow
+
+### Added
+
+- regression coverage for interrupted tool-call recovery, Codex orphan-tool sanitization, builtin tool-name normalization, fullscreen bash rendering consistency, and bash timeout validation/visibility
+
+## [0.0.14] - 2026-04-12
+
+### Added
+
+- fullscreen now supports extension-driven workflows and structured slash-command outcomes, including menus, hidden dispatches, and richer command result handling
+- `/settings` in fullscreen now exposes compaction controls for `Auto-compact`, `Reserve tokens`, and `Keep recent tokens`
+- skills can now be listed, disabled, and re-enabled from the CLI without deleting their installed files
+- startup model selection now prefers configured provider/model defaults more consistently, with better OpenAI startup fallback behavior
+- added a parity test script against installed pi compaction logic to keep BB token accounting aligned with upstream behavior
+
+### Fixed
+
+- session resume now restores the prior model and thinking level instead of starting with mismatched runtime defaults
+- fullscreen/TUI terminal rendering now sanitizes terminal control text more reliably and avoids ANSI leakage into the UI
+- auto-compaction token estimation now matches pi more closely by using the last successful assistant usage plus trailing estimates, using ceil-based token heuristics, computing `tokens_before` from rebuilt context instead of raw payload size, and ignoring assistant usage from before the latest compaction boundary
+- fullscreen compaction behavior and status reporting are more consistent after auto-compaction and manual compaction events, and local fullscreen actions now show an animated elapsed-time status while they run
+
+### Changed
+
+- fullscreen extension workflows and session compaction support are now merged into the main interaction path on `master`
+
 ## [0.0.13] - 2026-04-09
 
 ### Added
@@ -107,6 +143,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - latest published package includes the post-0.0.7 startup, auth, model-default, and update-notice improvements
 
+[0.0.14]: https://github.com/shuyhere/bb-agent/releases/tag/v0.0.14
 [0.0.13]: https://github.com/shuyhere/bb-agent/releases/tag/v0.0.13
 [0.0.12]: https://github.com/shuyhere/bb-agent/releases/tag/v0.0.12
 [0.0.11]: https://github.com/shuyhere/bb-agent/releases/tag/v0.0.11

package/README.md

@@ -246,7 +246,6 @@ Or set this in `~/.bb-agent/settings.json`:
 - [Development Guide](docs/development.md) — build from source, dev workflow, project structure, debugging
 - [Contributing](CONTRIBUTING.md) — code style, PR process
 - [Changelog](CHANGELOG.md) — release history
-- [Security](SECURITY.md) — vulnerability reporting, security model
 
 ## Development
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@shuyhere/bb-agent",
-  "version": "0.0.13",
+  "version": "0.0.15",
   "description": "BB-Agent — a Rust-native AI coding agent for the terminal",
   "license": "MIT",
   "repository": {

package/scripts/test-pi-token-parity.mjs

@@ -0,0 +1,141 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import * as pi from '/home/shuyhere/projects/tako/node_modules/@mariozechner/pi-coding-agent/dist/core/compaction/compaction.js';
+
+const settings = { enabled: true, reserveTokens: 16384, keepRecentTokens: 20000 };
+
+function bbEstimateContextTokens(messages) {
+  function calc(usage) {
+    return usage.total_tokens > 0
+      ? usage.total_tokens
+      : usage.input + usage.output + usage.cache_read + usage.cache_write;
+  }
+
+  function estimateText(text) {
+    return Math.ceil(text.length / 4);
+  }
+
+  function estimateMessage(message) {
+    switch (message.role) {
+      case 'user':
+        return message.content.reduce((sum, block) => sum + (block.type === 'text' ? estimateText(block.text) : 1200), 0);
+      case 'assistant':
+        return message.content.reduce((sum, block) => {
+          if (block.type === 'text') return sum + estimateText(block.text);
+          if (block.type === 'thinking') return sum + estimateText(block.thinking);
+          if (block.type === 'toolCall') return sum + estimateText(block.name) + estimateText(JSON.stringify(block.arguments ?? {}));
+          return sum;
+        }, 0);
+      case 'toolResult':
+      case 'custom':
+        return message.content.reduce((sum, block) => sum + (block.type === 'text' ? estimateText(block.text) : 1200), 0);
+      case 'bashExecution':
+        return estimateText(message.command) + estimateText(message.output);
+      case 'branchSummary':
+      case 'compactionSummary':
+        return estimateText(message.summary);
+      default:
+        return 0;
+    }
+  }
+
+  const lastUsageIndex = [...messages.keys()].reverse().find((i) => {
+    const m = messages[i];
+    return m.role === 'assistant' && m.stopReason !== 'aborted' && m.stopReason !== 'error' && calc(m.usage) > 0;
+  });
+
+  if (lastUsageIndex == null) {
+    const trailingTokens = messages.reduce((sum, m) => sum + estimateMessage(m), 0);
+    return { tokens: trailingTokens, usageTokens: 0, trailingTokens, lastUsageIndex: null };
+  }
+
+  const usageTokens = calc(messages[lastUsageIndex].usage);
+  const trailingTokens = messages.slice(lastUsageIndex + 1).reduce((sum, m) => sum + estimateMessage(m), 0);
+  return { tokens: usageTokens + trailingTokens, usageTokens, trailingTokens, lastUsageIndex };
+}
+
+test('bb estimator matches installed pi on shared fixtures', () => {
+  const fixtures = [
+    [
+      {
+        role: 'assistant',
+        content: [{ type: 'text', text: 'done' }],
+        provider: 'test',
+        model: 'test',
+        usage: { input: 100, output: 20, cacheRead: 10, cacheWrite: 5, totalTokens: 0 },
+        stopReason: 'stop',
+        timestamp: Date.now(),
+      },
+      { role: 'user', content: [{ type: 'text', text: '12345678' }], timestamp: Date.now() },
+    ],
+    [
+      {
+        role: 'assistant',
+        content: [{ type: 'text', text: 'aborted' }],
+        provider: 'test',
+        model: 'test',
+        usage: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, totalTokens: 500 },
+        stopReason: 'aborted',
+        timestamp: Date.now(),
+      },
+      { role: 'user', content: [{ type: 'text', text: '12345678' }], timestamp: Date.now() },
+    ],
+    [
+      {
+        role: 'assistant',
+        content: [
+          { type: 'text', text: 'hello' },
+          { type: 'thinking', thinking: 'reasoning text' },
+          { type: 'toolCall', id: '1', name: 'read', arguments: { path: 'src/main.rs' } },
+        ],
+        provider: 'test',
+        model: 'test',
+        usage: { input: 300, output: 40, cacheRead: 50, cacheWrite: 0, totalTokens: 0 },
+        stopReason: 'stop',
+        timestamp: Date.now(),
+      },
+      {
+        role: 'toolResult',
+        toolCallId: '1',
+        toolName: 'read',
+        content: [{ type: 'text', text: 'fn main() {}' }],
+        isError: false,
+        timestamp: Date.now(),
+      },
+      {
+        role: 'bashExecution',
+        command: 'ls -la',
+        output: 'file1\nfile2\n',
+        cancelled: false,
+        truncated: false,
+        timestamp: Date.now(),
+      },
+    ],
+  ];
+
+  for (const messages of fixtures) {
+    const piEstimate = pi.estimateContextTokens(messages);
+    const bbEstimate = bbEstimateContextTokens(
+      JSON.parse(
+        JSON.stringify(messages)
+          .replace(/cacheRead/g, 'cache_read')
+          .replace(/cacheWrite/g, 'cache_write')
+          .replace(/totalTokens/g, 'total_tokens')
+          .replace(/stopReason/g, 'stopReason')
+      )
+    );
+
+    assert.deepEqual(bbEstimate, {
+      tokens: piEstimate.tokens,
+      usageTokens: piEstimate.usageTokens,
+      trailingTokens: piEstimate.trailingTokens,
+      lastUsageIndex: piEstimate.lastUsageIndex,
+    });
+
+    const contextWindow = 128000;
+    assert.equal(
+      bbEstimate.tokens > contextWindow - settings.reserveTokens,
+      pi.shouldCompact(piEstimate.tokens, contextWindow, settings)
+    );
+  }
+});