@link-assistant/hive-mind 2.2.0 → 2.2.2

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @link-assistant/hive-mind
 
+## 2.2.2
+
+### Patch Changes
+
+- f9f30d6: Treat an omitted `--think` option as `--think off` across tools, using a zero budget or the lowest supported effort when reasoning cannot be disabled.
+
+## 2.2.1
+
+### Patch Changes
+
+- e86a40e: Add a `--development-log` solve option that prompts agents to collect issue data, then preserves and commits resumable tool sessions under per-session UUID directories.
+
 ## 2.2.0
 
 ### Minor Changes

package/README.hi.md

@@ -173,6 +173,7 @@ claude
 # Use /config command and set:
 # Reduce motion                             true # Will save your ssh trafic, and make Claude Code more responsive (less latency)
 # Thinking mode                             false # Anthropic models perform better and cheaper without thinking
+# `--think` न देने पर Hive Mind इसे `--think off` मानता है।
 # Model                                     haiku # chepear for connection testing manually
 # Claude in Chrome enabled by default       false # No need for Chrome support on server
 
@@ -346,11 +347,11 @@ solve <issue-url> [options]
 
 **सबसे अधिक उपयोग किए जाने वाले विकल्प:**
 
-| विकल्प          | संक्षिप्त | विवरण                                         | डिफ़ॉल्ट   |
-| --------------- | --------- | --------------------------------------------- | ---------- |
-| `--model`       | `-m`      | उपयोग करने वाला AI मॉडल (sonnet, opus, haiku) | sonnet     |
-| `--think`       |           | सोचने का स्तर (low, medium, high, max)        | -          |
-| `--base-branch` | `-b`      | PR के लिए टार्गेट ब्रांच                      | (डिफ़ॉल्ट) |
+| विकल्प          | संक्षिप्त | विवरण                                                     | डिफ़ॉल्ट   |
+| --------------- | --------- | --------------------------------------------------------- | ---------- |
+| `--model`       | `-m`      | उपयोग करने वाला AI मॉडल (sonnet, opus, haiku)             | sonnet     |
+| `--think`       |           | सोचने का स्तर (off, low, medium, high, xhigh, ultra, max) | off        |
+| `--base-branch` | `-b`      | PR के लिए टार्गेट ब्रांच                                  | (डिफ़ॉल्ट) |
 
 **अन्य उपयोगी विकल्प:**
 
@@ -372,12 +373,12 @@ hive <github-url> [options]
 
 **सबसे अधिक उपयोग किए जाने वाले विकल्प:**
 
-| विकल्प         | संक्षिप्त | विवरण                                         | डिफ़ॉल्ट |
-| -------------- | --------- | --------------------------------------------- | -------- |
-| `--model`      | `-m`      | उपयोग करने वाला AI मॉडल (sonnet, opus, haiku) | sonnet   |
-| `--think`      |           | सोचने का स्तर (low, medium, high, max)        | -        |
-| `--all-issues` | `-a`      | सभी इश्यू निगरानी करें (लेबल अनदेखा करें)     | false    |
-| `--once`       |           | एकल रन (लगातार निगरानी न करें)                | false    |
+| विकल्प         | संक्षिप्त | विवरण                                                     | डिफ़ॉल्ट |
+| -------------- | --------- | --------------------------------------------------------- | -------- |
+| `--model`      | `-m`      | उपयोग करने वाला AI मॉडल (sonnet, opus, haiku)             | sonnet   |
+| `--think`      |           | सोचने का स्तर (off, low, medium, high, xhigh, ultra, max) | off      |
+| `--all-issues` | `-a`      | सभी इश्यू निगरानी करें (लेबल अनदेखा करें)                 | false    |
+| `--once`       |           | एकल रन (लगातार निगरानी न करें)                            | false    |
 
 **अन्य उपयोगी विकल्प:**
 

package/README.md

@@ -507,15 +507,15 @@ Free Models via Kilo Gateway (with --tool agent):
 
 Current tool defaults in Hive Mind:
 
-| Tool       | Default model                                                               | Default reasoning behavior                                                               |
-| ---------- | --------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
-| `claude`   | `sonnet`                                                                    | No extra thinking is requested unless you pass `--think` or `--thinking-budget`          |
-| `codex`    | `gpt-5.6-sol` preferred, with runtime fallback to local catalog (`gpt-5.5`) | Codex runs with `reasoning_effort=none` unless you pass `--think` or `--thinking-budget` |
-| `opencode` | `grok-code-fast-1`                                                          | No extra thinking prompt is added for the default model                                  |
-| `agent`    | `nemotron-3-super-free`                                                     | No extra thinking prompt is added for the default model                                  |
-| `gemini`   | `flash`                                                                     | No extra thinking prompt is added for the default model                                  |
-| `qwen`     | `qwen3-coder-plus`                                                          | No extra thinking prompt is added for the default model                                  |
-| `gemini`   | `gemini-2.5-flash`                                                          | No extra thinking prompt is added for the default model                                  |
+| Tool       | Default model                                                               | Default reasoning behavior                                                         |
+| ---------- | --------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- |
+| `claude`   | `sonnet`                                                                    | Defaults to `--think off`: zero budget when supported, otherwise the lowest effort |
+| `codex`    | `gpt-5.6-sol` preferred, with runtime fallback to local catalog (`gpt-5.5`) | Defaults to `--think off`, mapped to `reasoning_effort=none`                       |
+| `opencode` | `grok-code-fast-1`                                                          | Defaults to `--think off`; no positive thinking prompt is added                    |
+| `agent`    | `nemotron-3-super-free`                                                     | Defaults to `--think off`; no positive thinking prompt is added                    |
+| `gemini`   | `flash`                                                                     | Defaults to `--think off`; no positive thinking prompt is added                    |
+| `qwen`     | `qwen3-coder-plus`                                                          | Defaults to `--think off`; no positive thinking prompt is added                    |
+| `gemini`   | `gemini-2.5-flash`                                                          | Defaults to `--think off`; no positive thinking prompt is added                    |
 
 See [docs/CONFIGURATION.md](./docs/CONFIGURATION.md) for the full per-tool defaults and reasoning mappings.
 

package/README.ru.md

@@ -173,6 +173,7 @@ claude
 # Use /config command and set:
 # Reduce motion                             true # Will save your ssh trafic, and make Claude Code more responsive (less latency)
 # Thinking mode                             false # Anthropic models perform better and cheaper without thinking
+# Если `--think` не указан, Hive Mind трактует это как `--think off`.
 # Model                                     haiku # chepear for connection testing manually
 # Claude in Chrome enabled by default       false # No need for Chrome support on server
 
@@ -346,11 +347,11 @@ solve <issue-url> [options]
 
 **Наиболее часто используемые параметры:**
 
-| Параметр        | Сокр. | Описание                                     | По умолчанию   |
-| --------------- | ----- | -------------------------------------------- | -------------- |
-| `--model`       | `-m`  | Используемая модель ИИ (sonnet, opus, haiku) | sonnet         |
-| `--think`       |       | Уровень мышления (low, medium, high, max)    | -              |
-| `--base-branch` | `-b`  | Целевая ветка для PR                         | (по умолчанию) |
+| Параметр        | Сокр. | Описание                                                     | По умолчанию   |
+| --------------- | ----- | ------------------------------------------------------------ | -------------- |
+| `--model`       | `-m`  | Используемая модель ИИ (sonnet, opus, haiku)                 | sonnet         |
+| `--think`       |       | Уровень мышления (off, low, medium, high, xhigh, ultra, max) | off            |
+| `--base-branch` | `-b`  | Целевая ветка для PR                                         | (по умолчанию) |
 
 **Другие полезные параметры:**
 
@@ -372,12 +373,12 @@ hive <github-url> [options]
 
 **Наиболее часто используемые параметры:**
 
-| Параметр       | Сокр. | Описание                                        | По умолчанию |
-| -------------- | ----- | ----------------------------------------------- | ------------ |
-| `--model`      | `-m`  | Используемая модель ИИ (sonnet, opus, haiku)    | sonnet       |
-| `--think`      |       | Уровень мышления (low, medium, high, max)       | -            |
-| `--all-issues` | `-a`  | Мониторинг всех задач (игнорировать метки)      | false        |
-| `--once`       |       | Одиночный запуск (без непрерывного мониторинга) | false        |
+| Параметр       | Сокр. | Описание                                                     | По умолчанию |
+| -------------- | ----- | ------------------------------------------------------------ | ------------ |
+| `--model`      | `-m`  | Используемая модель ИИ (sonnet, opus, haiku)                 | sonnet       |
+| `--think`      |       | Уровень мышления (off, low, medium, high, xhigh, ultra, max) | off          |
+| `--all-issues` | `-a`  | Мониторинг всех задач (игнорировать метки)                   | false        |
+| `--once`       |       | Одиночный запуск (без непрерывного мониторинга)              | false        |
 
 **Другие полезные параметры:**
 

package/README.zh.md

@@ -173,6 +173,7 @@ claude
 # Use /config command and set:
 # Reduce motion                             true # Will save your ssh trafic, and make Claude Code more responsive (less latency)
 # Thinking mode                             false # Anthropic models perform better and cheaper without thinking
+# 未指定 `--think` 时，Hive Mind 按 `--think off` 处理。
 # Model                                     haiku # chepear for connection testing manually
 # Claude in Chrome enabled by default       false # No need for Chrome support on server
 
@@ -346,11 +347,11 @@ solve <issue-url> [options]
 
 **最常用选项：**
 
-| 选项            | 简写 | 描述                                  | 默认值   |
-| --------------- | ---- | ------------------------------------- | -------- |
-| `--model`       | `-m` | 使用的 AI 模型（sonnet、opus、haiku） | sonnet   |
-| `--think`       |      | 思考级别（low、medium、high、max）    | -        |
-| `--base-branch` | `-b` | PR 的目标分支                         | （默认） |
+| 选项            | 简写 | 描述                                                  | 默认值   |
+| --------------- | ---- | ----------------------------------------------------- | -------- |
+| `--model`       | `-m` | 使用的 AI 模型（sonnet、opus、haiku）                 | sonnet   |
+| `--think`       |      | 思考级别（off、low、medium、high、xhigh、ultra、max） | off      |
+| `--base-branch` | `-b` | PR 的目标分支                                         | （默认） |
 
 **其他常用选项：**
 
@@ -372,12 +373,12 @@ hive <github-url> [options]
 
 **最常用选项：**
 
-| 选项           | 简写 | 描述                                  | 默认值 |
-| -------------- | ---- | ------------------------------------- | ------ |
-| `--model`      | `-m` | 使用的 AI 模型（sonnet、opus、haiku） | sonnet |
-| `--think`      |      | 思考级别（low、medium、high、max）    | -      |
-| `--all-issues` | `-a` | 监控所有 Issue（忽略标签）            | false  |
-| `--once`       |      | 单次运行（不持续监控）                | false  |
+| 选项           | 简写 | 描述                                                  | 默认值 |
+| -------------- | ---- | ----------------------------------------------------- | ------ |
+| `--model`      | `-m` | 使用的 AI 模型（sonnet、opus、haiku）                 | sonnet |
+| `--think`      |      | 思考级别（off、low、medium、high、xhigh、ultra、max） | off    |
+| `--all-issues` | `-a` | 监控所有 Issue（忽略标签）                            | false  |
+| `--once`       |      | 单次运行（不持续监控）                                | false  |
 
 **其他常用选项：**
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@link-assistant/hive-mind",
-  "version": "2.2.0",
+  "version": "2.2.2",
   "description": "AI-powered issue solver and hive mind for collaborative problem solving",
   "main": "src/hive.mjs",
   "type": "module",

package/src/agent.prompts.lib.mjs

@@ -8,6 +8,7 @@ import { getExperimentsExamplesSubPrompt } from './experiments-examples.prompts.
 import { getThinkingPromptInstruction } from './thinking-prompt.lib.mjs';
 import { buildWorkLanguageDirective } from './work-language.prompts.lib.mjs';
 import { buildRequestedBaseBranchDirective } from './solve-option-contract.prompts.lib.mjs';
+import { buildDevelopmentLogPrompt } from './development-log.lib.mjs';
 
 /**
  * Build the user prompt for Agent
@@ -66,6 +67,11 @@ export const buildUserPrompt = params => {
     promptLines.push('');
   }
 
+  const developmentLogPrompt = buildDevelopmentLogPrompt({ argv, issueNumber, prNumber }).trim();
+  if (developmentLogPrompt) {
+    promptLines.push(developmentLogPrompt, '');
+  }
+
   const thinkingPromptInstruction = getThinkingPromptInstruction({ tool: 'agent', argv });
   if (thinkingPromptInstruction) {
     promptLines.push(thinkingPromptInstruction);

package/src/claude.prompts.lib.mjs

@@ -10,6 +10,7 @@ import { primaryModelNames } from './models/index.mjs';
 import { getThinkingPromptInstruction } from './thinking-prompt.lib.mjs';
 import { buildWorkLanguageDirective } from './work-language.prompts.lib.mjs';
 import { buildRequestedBaseBranchDirective } from './solve-option-contract.prompts.lib.mjs';
+import { buildDevelopmentLogPrompt } from './development-log.lib.mjs';
 
 /**
  * Build the user prompt for Claude
@@ -79,6 +80,11 @@ export const buildUserPrompt = params => {
     promptLines.push('');
   }
 
+  const developmentLogPrompt = buildDevelopmentLogPrompt({ argv, issueNumber, prNumber }).trim();
+  if (developmentLogPrompt) {
+    promptLines.push(developmentLogPrompt, '');
+  }
+
   const thinkingPromptInstruction = getThinkingPromptInstruction({ tool: 'claude', argv, claudeVersion });
   if (thinkingPromptInstruction) {
     promptLines.push(thinkingPromptInstruction);

package/src/codex.prompts.lib.mjs

@@ -9,6 +9,7 @@ import { getExperimentsExamplesSubPrompt } from './experiments-examples.prompts.
 import { getThinkingPromptInstruction } from './thinking-prompt.lib.mjs';
 import { buildWorkLanguageDirective } from './work-language.prompts.lib.mjs';
 import { buildRequestedBaseBranchDirective } from './solve-option-contract.prompts.lib.mjs';
+import { buildDevelopmentLogPrompt } from './development-log.lib.mjs';
 
 /**
  * Build the user prompt for Codex
@@ -67,6 +68,11 @@ export const buildUserPrompt = params => {
     promptLines.push('');
   }
 
+  const developmentLogPrompt = buildDevelopmentLogPrompt({ argv, issueNumber, prNumber }).trim();
+  if (developmentLogPrompt) {
+    promptLines.push(developmentLogPrompt, '');
+  }
+
   const thinkingPromptInstruction = getThinkingPromptInstruction({ tool: 'codex', argv });
   if (thinkingPromptInstruction) {
     promptLines.push(thinkingPromptInstruction);

package/src/config.lib.mjs

@@ -614,6 +614,10 @@ export const getClaudeEnv = (options = {}) => {
 
     if (effortLevel) {
       env.CLAUDE_CODE_EFFORT_LEVEL = effortLevel;
+    } else if (options.thinkLevel === 'off' && adaptiveThinkingOnly) {
+      // Issue #2032: adaptive-only models reject/ignore a zero manual-thinking budget.
+      // Use the lowest supported effort as the strongest safe best-effort equivalent.
+      env.CLAUDE_CODE_EFFORT_LEVEL = 'low';
     }
   }
 

package/src/development-log.finalize.lib.mjs

@@ -0,0 +1,11 @@
+/**
+ * Build a once-only finalizer so both the normal and error completion paths can
+ * preserve a development log without creating duplicate commits.
+ */
+export const createDevelopmentLogFinalizer = ({ collect, getParams }) => {
+  let resultPromise = null;
+  return () => {
+    if (!resultPromise) resultPromise = Promise.resolve().then(() => collect(getParams()));
+    return resultPromise;
+  };
+};

package/src/development-log.lib.mjs

@@ -0,0 +1,297 @@
+import fs from 'node:fs/promises';
+import os from 'node:os';
+import path from 'node:path';
+
+const sanitizePathSegment = (value, fallback) => {
+  const raw = value === null || value === undefined || value === '' ? fallback : String(value);
+  const sanitized = raw.replace(/[^A-Za-z0-9._-]+/g, '-').replace(/^-+|-+$/g, '');
+  return sanitized || fallback;
+};
+
+const stripDotSlash = value => value.replace(/^\.\//, '');
+const toPosixPath = value => value.split(path.sep).join('/');
+const addDotSlash = value => (value.startsWith('./') ? value : `./${value}`);
+
+const safeFileName = value => sanitizePathSegment(value, 'session');
+
+export const buildDevelopmentLogDirectory = ({ issueNumber, prNumber }) => {
+  const issueSegment = sanitizePathSegment(issueNumber, 'unknown');
+  const prSegment = sanitizePathSegment(prNumber, 'pending');
+  return `./dev/log/issues/${issueSegment}/pulls/${prSegment}`;
+};
+
+export const buildCaseStudyDirectory = ({ issueNumber }) => {
+  const issueSegment = sanitizePathSegment(issueNumber, 'unknown');
+  return `./docs/case-studies/issue-${issueSegment}`;
+};
+
+// Normalize a GitHub issue type (or label) into one of the buckets the
+// development-log prompt distinguishes. Bug issues get the stronger
+// "download all logs" wording; everything else (feature, task, or an
+// unspecified/unknown type) gets the universal data-collection wording.
+export const isBugIssueType = issueType => {
+  if (issueType === null || issueType === undefined) return false;
+  const normalized = String(issueType).trim().toLowerCase();
+  if (!normalized) return false;
+  return normalized === 'bug' || normalized === 'bugs' || normalized.includes('bug') || normalized === 'defect';
+};
+
+// True when the run requested the development log via --development-log
+// (yargs exposes both the camelCase and kebab-case keys).
+export const isDevelopmentLogEnabled = argv => argv?.developmentLog === true || argv?.['development-log'] === true;
+
+export const buildDevelopmentLogPrompt = ({ argv, issueNumber, prNumber, issueType }) => {
+  if (!(argv?.developmentLog || argv?.['development-log'])) return '';
+
+  const developmentLogDirectory = buildDevelopmentLogDirectory({ issueNumber, prNumber });
+  // Automatic support for issue types: when the issue type is "bug" the
+  // instruction asks to download all logs as well; for feature/task issues, or
+  // when no issue type is selected, the universal data-collection wording is used.
+  const resolvedIssueType = issueType ?? argv?.issueType ?? null;
+  const collectionInstruction = isBugIssueType(resolvedIssueType) ? `Download all logs and collect data related about the issue to this repository, make sure we compile that data into the ${developmentLogDirectory} folder.` : `Collect data related about the issue to this repository, make sure we compile that data into the ${developmentLogDirectory} folder.`;
+
+  return `\n${collectionInstruction}\n`;
+};
+
+// Fetch the GitHub issue type (e.g. "Bug", "Feature", "Task") for an issue.
+// Returns null when the type cannot be determined (no type selected, command
+// failure, or non-issue targets). Accepts an injectable command runner so the
+// behavior can be unit tested without hitting the network.
+export const fetchIssueType = async ({ owner, repo, issueNumber, $, log }) => {
+  if (!owner || !repo || !issueNumber || typeof $ !== 'function') return null;
+  try {
+    // eslint-disable-next-line gh-rate-limit/no-direct-gh-exec -- $ is the injected, rate-limit-safe runner (wrapDollarWithGhRetry) passed in by the caller.
+    const result = await $`gh issue view ${issueNumber} --repo ${owner}/${repo} --json issueType`;
+    if (result?.code && result.code !== 0) return null;
+    const stdout = result?.stdout?.toString?.() ?? String(result?.stdout ?? '');
+    if (!stdout.trim()) return null;
+    const parsed = JSON.parse(stdout);
+    const name = parsed?.issueType?.name;
+    return name ? String(name) : null;
+  } catch (error) {
+    await log?.(`ℹ️  Could not determine issue type: ${error.message}`, { verbose: true });
+    return null;
+  }
+};
+
+const fileExists = async filePath => {
+  try {
+    const stat = await fs.stat(filePath);
+    return stat.isFile();
+  } catch {
+    return false;
+  }
+};
+
+const copyIfExists = async ({ sourcePath, destinationPath }) => {
+  if (!(await fileExists(sourcePath))) return false;
+  await fs.copyFile(sourcePath, destinationPath);
+  return true;
+};
+
+const getClaudeSessionFile = ({ repositoryPath, sessionId, homeDir }) => {
+  if (!repositoryPath || !sessionId || !homeDir) return null;
+  const projectDirName = repositoryPath.replace(/\//g, '-');
+  return path.join(homeDir, '.claude', 'projects', projectDirName, `${sessionId}.jsonl`);
+};
+
+// Codex CLI stores its transcript ("rollout") under
+// ~/.codex/sessions/YYYY/MM/DD/rollout-<timestamp>-<sessionId>.jsonl. The date
+// path and timestamp are not derivable from the sessionId, so locate the file
+// by recursively matching the sessionId suffix instead.
+const findCodexSessionFile = async ({ sessionId, homeDir }) => {
+  if (!sessionId || !homeDir) return null;
+  const sessionsRoot = path.join(homeDir, '.codex', 'sessions');
+  try {
+    const entries = await fs.readdir(sessionsRoot, { recursive: true });
+    const match = entries.find(entry => typeof entry === 'string' && entry.includes('rollout-') && entry.endsWith(`-${sessionId}.jsonl`));
+    return match ? path.join(sessionsRoot, match) : null;
+  } catch {
+    return null;
+  }
+};
+
+const copyKnownSessionFiles = async ({ repositoryPath, sessionRelativeDirectory, logFile, sessionId, tool, homeDir }) => {
+  if (!sessionId) return [];
+
+  const sessionDirectory = path.join(repositoryPath, sessionRelativeDirectory);
+  const candidates = [];
+  const logDirectory = logFile ? path.dirname(logFile) : null;
+
+  if (logDirectory) {
+    candidates.push({
+      sourcePath: path.join(logDirectory, `${sessionId}.log`),
+      destinationName: `${tool || 'tool'}-${sessionId}.log`,
+    });
+  }
+
+  if (tool === 'claude') {
+    const claudeSessionFile = getClaudeSessionFile({ repositoryPath, sessionId, homeDir });
+    if (claudeSessionFile) {
+      candidates.push({
+        sourcePath: claudeSessionFile,
+        destinationName: `claude-${sessionId}.jsonl`,
+      });
+    }
+  }
+
+  if (tool === 'codex') {
+    const codexSessionFile = await findCodexSessionFile({ sessionId, homeDir });
+    if (codexSessionFile) {
+      candidates.push({
+        sourcePath: codexSessionFile,
+        destinationName: `codex-${sessionId}.jsonl`,
+      });
+    }
+  }
+
+  const copied = [];
+  const seenSources = new Set();
+  for (const candidate of candidates) {
+    if (!candidate.sourcePath || seenSources.has(candidate.sourcePath)) continue;
+    seenSources.add(candidate.sourcePath);
+
+    const relativePath = `${sessionRelativeDirectory}/${safeFileName(candidate.destinationName)}`;
+    const copiedPath = path.join(sessionDirectory, safeFileName(candidate.destinationName));
+    if (await copyIfExists({ sourcePath: candidate.sourcePath, destinationPath: copiedPath })) {
+      copied.push(addDotSlash(toPosixPath(relativePath)));
+    }
+  }
+
+  return copied;
+};
+
+export const writeDevelopmentLogArtifacts = async ({ repositoryPath, logFile, issueNumber, prNumber, tool, sessionId, branchName, rawCommand, now = new Date(), homeDir = os.homedir() }) => {
+  if (!repositoryPath) {
+    throw new Error('repositoryPath is required to write development-log artifacts');
+  }
+
+  const developmentLogDirectory = buildDevelopmentLogDirectory({ issueNumber, prNumber });
+  const caseStudyDirectory = buildCaseStudyDirectory({ issueNumber });
+  const relativeDirectory = stripDotSlash(developmentLogDirectory);
+  const timestamp = now.toISOString().replace(/[:.]/g, '-');
+  const sessionDirectoryName = safeFileName(sessionId || `run-${timestamp}`);
+  const sessionRelativeDirectory = `${relativeDirectory}/sessions/${sessionDirectoryName}`;
+  const sessionDirectory = path.join(repositoryPath, sessionRelativeDirectory);
+
+  await fs.mkdir(sessionDirectory, { recursive: true });
+
+  let copiedLogRelativePath = null;
+  if (logFile) {
+    copiedLogRelativePath = `${sessionRelativeDirectory}/solve.log`;
+    await fs.copyFile(logFile, path.join(repositoryPath, copiedLogRelativePath));
+  }
+
+  const sessionFiles = await copyKnownSessionFiles({
+    repositoryPath,
+    sessionRelativeDirectory,
+    logFile,
+    sessionId,
+    tool,
+    homeDir,
+  });
+
+  const metadataRelativePath = `${sessionRelativeDirectory}/metadata.json`;
+  const metadata = {
+    schemaVersion: 2,
+    collectedAt: now.toISOString(),
+    issueNumber: issueNumber ?? null,
+    prNumber: prNumber ?? null,
+    branchName: branchName || null,
+    tool: tool || null,
+    sessionId: sessionId || null,
+    rawCommand: rawCommand || null,
+    developmentLogDirectory,
+    caseStudyDirectory,
+    artifacts: {
+      solveLog: copiedLogRelativePath ? addDotSlash(toPosixPath(copiedLogRelativePath)) : null,
+      sessionFiles,
+    },
+  };
+
+  await fs.writeFile(path.join(repositoryPath, metadataRelativePath), `${JSON.stringify(metadata, null, 2)}\n`, 'utf8');
+
+  return {
+    developmentLogDirectory,
+    caseStudyDirectory,
+    relativeDirectory,
+    sessionRelativeDirectory,
+    copiedLogRelativePath: copiedLogRelativePath ? toPosixPath(copiedLogRelativePath) : null,
+    metadataRelativePath: toPosixPath(metadataRelativePath),
+    sessionFiles,
+  };
+};
+
+const getCommandOutput = result => (result?.stderr?.toString?.() || result?.stdout?.toString?.() || '').trim();
+
+export const collectAndCommitDevelopmentLogArtifacts = async ({ enabled, repositoryPath, logFile, issueNumber, prNumber, tool, sessionId, branchName, rawCommand, $, log }) => {
+  if (!enabled) {
+    return { skipped: 'disabled' };
+  }
+
+  if (!repositoryPath) {
+    await log?.('⚠️  Development log requested but no repository path is available', { level: 'warning' });
+    return { skipped: 'missing-repository-path' };
+  }
+
+  try {
+    const artifacts = await writeDevelopmentLogArtifacts({
+      repositoryPath,
+      logFile,
+      issueNumber,
+      prNumber,
+      tool,
+      sessionId,
+      branchName,
+      rawCommand,
+    });
+
+    await log?.(`🧾 Development log artifacts written to ${artifacts.developmentLogDirectory}`);
+
+    if (!$) {
+      return { ...artifacts, committed: false, pushed: false };
+    }
+
+    const addResult = await $({ cwd: repositoryPath })`git add -f -- ${artifacts.relativeDirectory}`;
+    if (addResult.code !== 0) {
+      await log?.(`⚠️  Could not stage development log: ${getCommandOutput(addResult)}`, { level: 'warning' });
+      return { ...artifacts, committed: false, pushed: false };
+    }
+
+    const diffResult = await $({ cwd: repositoryPath })`git diff --cached --quiet -- ${artifacts.relativeDirectory}`;
+    if (diffResult.code === 0) {
+      await log?.('ℹ️  Development log artifacts already committed');
+      return { ...artifacts, committed: false, pushed: false };
+    }
+    if (diffResult.code !== 1) {
+      await log?.(`⚠️  Could not inspect staged development log changes: ${getCommandOutput(diffResult)}`, { level: 'warning' });
+      return { ...artifacts, committed: false, pushed: false };
+    }
+
+    const commitMessage = prNumber ? `Add development log for issue #${issueNumber} PR #${prNumber}` : `Add development log for issue #${issueNumber}`;
+    const commitResult = await $({ cwd: repositoryPath })`git commit -m ${commitMessage} -- ${artifacts.relativeDirectory}`;
+    if (commitResult.code !== 0) {
+      await log?.(`⚠️  Could not commit development log: ${getCommandOutput(commitResult)}`, { level: 'warning' });
+      return { ...artifacts, committed: false, pushed: false };
+    }
+
+    await log?.('✅ Development log committed');
+
+    if (!branchName) {
+      await log?.('ℹ️  Development log committed locally; no branch name available for push');
+      return { ...artifacts, committed: true, pushed: false };
+    }
+
+    const pushResult = await $({ cwd: repositoryPath })`git push origin ${branchName}`;
+    if (pushResult.code !== 0) {
+      await log?.(`⚠️  Could not push development log commit: ${getCommandOutput(pushResult)}`, { level: 'warning' });
+      return { ...artifacts, committed: true, pushed: false };
+    }
+
+    await log?.('✅ Development log pushed');
+    return { ...artifacts, committed: true, pushed: true };
+  } catch (error) {
+    await log?.(`⚠️  Development log collection failed: ${error.message}`, { level: 'warning' });
+    return { skipped: 'error', error };
+  }
+};

package/src/gemini.prompts.lib.mjs

@@ -8,6 +8,7 @@ import { getExperimentsExamplesSubPrompt } from './experiments-examples.prompts.
 import { getThinkingPromptInstruction } from './thinking-prompt.lib.mjs';
 import { buildWorkLanguageDirective } from './work-language.prompts.lib.mjs';
 import { buildRequestedBaseBranchDirective } from './solve-option-contract.prompts.lib.mjs';
+import { buildDevelopmentLogPrompt } from './development-log.lib.mjs';
 
 /**
  * Build the user prompt for Gemini
@@ -57,6 +58,11 @@ export const buildUserPrompt = params => {
     promptLines.push('');
   }
 
+  const developmentLogPrompt = buildDevelopmentLogPrompt({ argv, issueNumber, prNumber }).trim();
+  if (developmentLogPrompt) {
+    promptLines.push(developmentLogPrompt, '');
+  }
+
   const thinkingPromptInstruction = getThinkingPromptInstruction({ tool: 'gemini', argv });
   if (thinkingPromptInstruction) {
     promptLines.push(thinkingPromptInstruction);

package/src/lib.mjs

@@ -937,6 +937,19 @@ export default {
   setupStdioLogInterceptor,
 };
 
+// Issue #1596: log the solve startup banner (version + raw command) and return
+// the raw command string for reuse. Extracted from solve.mjs to keep that file
+// under the 1500-line limit enforced by scripts/check-file-line-limits.sh.
+export const logSolveStartup = async versionInfo => {
+  const rawCommand = process.argv.join(' ');
+  await log('');
+  await log(`🚀 solve v${versionInfo}`);
+  await log('🔧 Raw command executed:');
+  await log(`   ${rawCommand}`);
+  await log('');
+  return rawCommand;
+};
+
 /**
  * Get version information for logging
  * @returns {Promise<string>} Version string

package/src/opencode.prompts.lib.mjs

@@ -8,6 +8,7 @@ import { getExperimentsExamplesSubPrompt } from './experiments-examples.prompts.
 import { getThinkingPromptInstruction } from './thinking-prompt.lib.mjs';
 import { buildWorkLanguageDirective } from './work-language.prompts.lib.mjs';
 import { buildRequestedBaseBranchDirective } from './solve-option-contract.prompts.lib.mjs';
+import { buildDevelopmentLogPrompt } from './development-log.lib.mjs';
 
 /**
  * Build the user prompt for OpenCode
@@ -66,6 +67,11 @@ export const buildUserPrompt = params => {
     promptLines.push('');
   }
 
+  const developmentLogPrompt = buildDevelopmentLogPrompt({ argv, issueNumber, prNumber }).trim();
+  if (developmentLogPrompt) {
+    promptLines.push(developmentLogPrompt, '');
+  }
+
   const thinkingPromptInstruction = getThinkingPromptInstruction({ tool: 'opencode', argv });
   if (thinkingPromptInstruction) {
     promptLines.push(thinkingPromptInstruction);

package/src/option-suggestions.lib.mjs

@@ -207,6 +207,7 @@ const KNOWN_OPTION_NAMES = [
   'prompt-issue-reporting',
   'prompt-architecture-care',
   'prompt-case-studies',
+  'development-log',
   'use-handoff',
   'prompt-playwright-mcp',
   'prompt-check-sibling-pull-requests',

package/src/qwen.prompts.lib.mjs

@@ -8,6 +8,7 @@ import { getExperimentsExamplesSubPrompt } from './experiments-examples.prompts.
 import { getThinkingPromptInstruction } from './thinking-prompt.lib.mjs';
 import { buildWorkLanguageDirective } from './work-language.prompts.lib.mjs';
 import { buildRequestedBaseBranchDirective } from './solve-option-contract.prompts.lib.mjs';
+import { buildDevelopmentLogPrompt } from './development-log.lib.mjs';
 
 /**
  * Build the user prompt for Qwen Code
@@ -57,6 +58,11 @@ export const buildUserPrompt = params => {
     promptLines.push('');
   }
 
+  const developmentLogPrompt = buildDevelopmentLogPrompt({ argv, issueNumber, prNumber }).trim();
+  if (developmentLogPrompt) {
+    promptLines.push(developmentLogPrompt, '');
+  }
+
   const thinkingPromptInstruction = getThinkingPromptInstruction({ tool, argv });
   if (thinkingPromptInstruction) {
     promptLines.push(thinkingPromptInstruction);

package/src/solve.config.lib.mjs

@@ -299,9 +299,9 @@ export const SOLVE_OPTION_DEFINITIONS = {
   },
   think: {
     type: 'string',
-    description: 'Thinking level hint. For Claude, translated to --thinking-budget for Claude Code >= 2.1.12 (off=0, low=~8000, medium=~16000, high=~24000, xhigh/ultra/max=31999) and to CLAUDE_CODE_EFFORT_LEVEL when supported. Fable 5/Mythos 5/Sonnet 5/Opus 4.8/4.7 support xhigh and max; Opus 4.6/Sonnet 4.6/Mythos Preview support max; Opus 4.5 uses high for xhigh/max. `ultra` maps to the highest supported Claude effort (Claude "ultracode"-class reasoning). For Codex (GPT-5.6 Sol), mapped 1:1 to reasoning effort (off=none, low=low, medium=medium, high=high, xhigh=xhigh, ultra=ultra, max=max); GPT-5.6 keeps xhigh and adds max above it, and ultra runs the multi-agent mode paired with a rollout token budget cap. Default: no thinking level is enforced (models run as-is).',
+    description: 'Thinking level hint. For Claude, translated to --thinking-budget for Claude Code >= 2.1.12 (off=0, low=~8000, medium=~16000, high=~24000, xhigh/ultra/max=31999) and to CLAUDE_CODE_EFFORT_LEVEL when supported. Adaptive-only models that cannot disable thinking use their lowest effort for off. Fable 5/Mythos 5/Sonnet 5/Opus 4.8/4.7 support xhigh and max; Opus 4.6/Sonnet 4.6/Mythos Preview support max; Opus 4.5 uses high for xhigh/max. `ultra` maps to the highest supported Claude effort (Claude "ultracode"-class reasoning). For Codex (GPT-5.6 Sol), mapped 1:1 to reasoning effort (off=none, low=low, medium=medium, high=high, xhigh=xhigh, ultra=ultra, max=max); GPT-5.6 keeps xhigh and adds max above it, and ultra runs the multi-agent mode paired with a rollout token budget cap. Default: off.',
     choices: ['off', 'low', 'medium', 'high', 'xhigh', 'ultra', 'max'],
-    default: undefined,
+    default: 'off',
   },
   'thinking-budget': {
     type: 'number',
@@ -504,6 +504,11 @@ export const SOLVE_OPTION_DEFINITIONS = {
     description: 'Create comprehensive case study documentation for the issue including logs, analysis, timeline, root cause investigation, and proposed solutions. Organizes findings into ./docs/case-studies/issue-{id}/ directory. Supported for --tool claude and --tool codex.',
     default: false,
   },
+  'development-log': {
+    type: 'boolean',
+    description: 'Prompt for issue-data collection under ./dev/log/issues/{issue-id}/pulls/{pull-id}, preserve native tool state under sessions/{UUID}, and commit the artifacts when solve finishes. Supported for --tool claude, --tool codex, --tool opencode, --tool agent, --tool qwen, and --tool gemini.',
+    default: false,
+  },
   'use-handoff': {
     type: 'boolean',
     description: '[EXPERIMENTAL] Enable the HANDOFF.md continuity Agent Skill so a session can continue the work of a previous session — even when a different AI tool is used (e.g. Claude and Codex continuing each other in the same pull request). A real SKILL.md (the open Agent Skills standard) is deployed into the working directory so each tool loads it natively (.claude/skills/handoff/ for Claude, .agents/skills/handoff/ for Codex). The AI reads HANDOFF.md (repository root) first when present and keeps it updated with task, current state, decisions, next steps, gotchas, and critical files. HANDOFF.md is committed to the PR branch so it persists across the ephemeral per-session working directories; the SKILL.md itself is re-deployed each session and git-excluded so it never pollutes the PR. The same skill file is used identically for --tool claude and --tool codex. Disabled by default (issue #1877).',
@@ -838,6 +843,14 @@ export const parseArguments = async (yargs = getLinoYargsFactory(), hideBinFn =
   const modelExplicitlyProvided = rawArgs.includes('--model') || rawArgs.includes('-m') || rawArgs.includes('--worker-model');
   const fallbackModelExplicitlyProvided = rawArgs.includes('--fallback-model');
   const planModelExplicitlyProvided = rawArgs.includes('--plan-model');
+  const thinkExplicitlyProvided = hasRawOption(rawArgs, '--think');
+  const thinkingBudgetExplicitlyProvided = hasRawOption(rawArgs, '--thinking-budget');
+
+  // Issue #2032: an omitted --think is equivalent to --think off, except when
+  // an explicit token budget is the user's chosen reasoning control.
+  if (!thinkExplicitlyProvided && thinkingBudgetExplicitlyProvided) {
+    argv.think = undefined;
+  }
 
   // --plan flag expansion (Issue #1223)
   // When --plan is set, it acts as a shortcut for --plan-model opus --worker-model sonnet

package/src/solve.mjs

@@ -21,7 +21,7 @@ const fs = (await use('fs')).promises;
 const crypto = (await use('crypto')).default;
 const memoryCheck = await import('./memory-check.mjs');
 const lib = await import('./lib.mjs');
-const { log, setLogFile, getLogFile, getAbsoluteLogPath, cleanErrorMessage, formatAligned, formatToolExecutionFailure, getVersionInfo, setupVerboseLogInterceptor, setupStdioLogInterceptor } = lib;
+const { log, setLogFile, getLogFile, getAbsoluteLogPath, cleanErrorMessage, formatAligned, formatToolExecutionFailure, getVersionInfo, logSolveStartup, setupVerboseLogInterceptor, setupStdioLogInterceptor } = lib;
 const githubLib = await import('./github.lib.mjs');
 const { sanitizeLogContent, attachLogToGitHub, getToolDisplayName } = githubLib;
 const validation = await import('./solve.validation.lib.mjs');
@@ -62,6 +62,8 @@ const { recordAfterCloneSize, recordAfterAgentSize } = await import('./solve.dis
 const { createOrCheckoutBranch } = await import('./solve.branch.lib.mjs');
 const { startWorkSession, endWorkSession, SESSION_TYPES } = await import('./solve.session.lib.mjs');
 const { attachFinalLogIfMissing } = await import('./attach-logs-guarantee.lib.mjs'); // Issue #1952
+const { collectAndCommitDevelopmentLogArtifacts, fetchIssueType, isDevelopmentLogEnabled } = await import('./development-log.lib.mjs');
+const { createDevelopmentLogFinalizer } = await import('./development-log.finalize.lib.mjs');
 // Issue #1625: centralized markers + tracked comment posting for solve.mjs's
 // own usage-limit notifications (so they're excluded from the
 // "did the AI post anything?" check in --auto-attach-solution-summary).
@@ -72,12 +74,7 @@ const { autoAcceptInviteForRepo } = await import('./solve.accept-invite.lib.mjs'
 const { handleAutoForkOption, handleMaintainerForkAccess } = await import('./solve.fork-detection.lib.mjs');
 const logFile = await initializeLogFile(null);
 const versionInfo = await getVersionInfo();
-await log('');
-await log(`🚀 solve v${versionInfo}`);
-const rawCommand = process.argv.join(' ');
-await log('🔧 Raw command executed:');
-await log(`   ${rawCommand}`);
-await log('');
+const rawCommand = await logSolveStartup(versionInfo);
 
 let finalResourceSnapshotRecorded = false;
 const safeExit = async (code = 0, reason = 'Process completed', options = {}) => {
@@ -489,6 +486,8 @@ if (isPrUrl) {
 }
 // Issues #1212, #1462: Store issueNumber globally for error handlers (attach failure logs to issue when no PR exists)
 global.issueNumber = issueNumber;
+// Issue #1596: detect the issue type so the development-log prompt automatically uses bug vs feature/task wording.
+if (isDevelopmentLogEnabled(argv) && issueNumber) argv.issueType = await fetchIssueType({ owner, repo, issueNumber, $, log });
 const workspaceInfo = argv.enableWorkspaces ? { owner, repo, issueNumber } : null;
 const { tempDir, workspaceTmpDir, needsClone } = await setupTempDirectory(argv, workspaceInfo);
 cleanupContext.tempDir = tempDir;
@@ -497,6 +496,12 @@ cleanupContext.owner = owner;
 cleanupContext.repo = repo;
 if (prNumber) cleanupContext.prNumber = prNumber;
 let limitReached = false;
+let sessionId = null;
+let branchName = null;
+const finalizeDevelopmentLog = createDevelopmentLogFinalizer({
+  collect: collectAndCommitDevelopmentLogArtifacts,
+  getParams: () => ({ enabled: isDevelopmentLogEnabled(argv), repositoryPath: tempDir, logFile: getLogFile(), issueNumber, prNumber, tool: argv.tool || 'claude', sessionId, branchName, rawCommand, $, log }), // prettier-ignore
+});
 try {
   // Set up repository and clone using the new module
   // If --working-directory points to existing repo, needsClone is false and we skip cloning
@@ -531,7 +536,7 @@ try {
     issueUrl,
   });
   // Create or checkout branch using the new module
-  const branchName = await createOrCheckoutBranch({
+  branchName = await createOrCheckoutBranch({
     isContinueMode,
     prBranch,
     issueNumber,
@@ -861,7 +866,7 @@ try {
   }
 
   const { success } = toolResult;
-  let sessionId = toolResult.sessionId;
+  sessionId = toolResult.sessionId;
   let anthropicTotalCostUSD = toolResult.anthropicTotalCostUSD;
   let publicPricingEstimate = toolResult.publicPricingEstimate; // Used by agent tool
   let pricingInfo = toolResult.pricingInfo; // Used by agent tool for detailed pricing
@@ -1461,17 +1466,10 @@ try {
   // Issue #1516: Cleanup after all signals (was before verifyResults, caused premature commits)
   await cleanupClaudeFile(tempDir, branchName, claudeCommitHash, argv);
 
-  // End work session using the new module
-  await endWorkSession({
-    isContinueMode,
-    prNumber,
-    argv,
-    log,
-    formatAligned,
-    $,
-    logsAttached,
-  });
+  await finalizeDevelopmentLog(); // Issue #1596: preserve session before ending work.
+  await endWorkSession({ isContinueMode, prNumber, argv, log, formatAligned, $, logsAttached });
 } catch (error) {
+  await finalizeDevelopmentLog(); // Preserve failed/interrupted sessions too.
   // Don't report authentication errors to Sentry as they are user configuration issues
   if (!error.isAuthError) {
     reportError(error, {