Merge pull request #357 from dignfei/feat/docker-adopt-existing-container

feat(docker): attach a case to an already-running container

Conflicts came from work that landed after the PR was opened, and each is
resolved onto the newer abstraction rather than by keeping the older code:

- `defaultDockerCommandForMode` is registry-driven since #347, so the PR's
  `runsAsRoot` arm became `overlays.docker.rootCommand` (claude only). Claude
  Code still refuses `--dangerously-skip-permissions` as root in 2.1.261 and the
  refusal is visible only inside the container, so an adopted root container
  otherwise just shows a dead pane. Which flag to drop is a per-CLI fact, and
  `test/cli-registry-no-id-branching.test.ts` forbids expressing it as a branch.

- The probe's mode list and its mode -> binary table both duplicated the
  registry. They now read `enabledCliIds()` / `discovery.binaries[0]`, which is
  also what fixes the merge's silent regression: the hand-written list predates
  `omp`, and the run menu gates every docker case on this probe, so owned
  containers would have lost that mode. `shell` needs no arm — it declares no
  binary, so it is dropped from the lookup and reported available regardless.

- The per-mode `mode === 'claude' && !cliDir` chain in `tmux-manager.ts` is one
  `missingCliMessage(mode)` gate since #347; the PR's docker exemption moved onto
  it. Its test now pins the single gate instead of counting seven arms.

- The create arm keeps #349's swap-limit warning filter, which the adopted arm
  never reaches; the run-mode list gains `omp` from #353.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TecFD9hvPYJ1mkkMtBQbT1
This commit is contained in:
Codeman maintainer
2026-09-05 16:21:51 +02:00
144 changed files with 11972 additions and 1772 deletions
+40 -13
View File
@@ -2270,9 +2270,11 @@ class CodemanApp {
? 'Grok'
: mode === 'deepseek'
? 'DeepSeek'
: mode === 'opencode'
? 'OpenCode'
: 'Claude';
: mode === 'omp'
? 'OMP'
: mode === 'opencode'
? 'OpenCode'
: 'Claude';
}
async toggleResponseViewer() {
@@ -2632,29 +2634,52 @@ class CodemanApp {
// string field (e.g. modelDisplayName, which the route also broadcasts) is
// ever shown in this chip, render it via textContent — never interpolate an
// untrusted string into this template.
const seg = (label, p) => {
if (p === null) return '';
// `idle: true` keeps a missing window's SLOT with a dimmed em dash instead of
// dropping it. Claude only: Claude Code documents `five_hour` as "present
// only while the API reports it and its resets_at has not passed", so that
// key leaves the statusline payload whenever no 5-hour session window is
// open, and a chip that silently shrank from two windows to one read as a
// broken feature rather than as an idle window (reported 2026-09-01). A
// missing CODEX bucket means the opposite — that plan has no such limit —
// so those stay omitted rather than showing a dash forever.
const seg = (label, p, idle) => {
if (p === null) {
if (!idle) return '';
return `<span class="pu-win pu-win-idle"><span class="pu-label">${label}</span><span class="pu-val">—</span></span>`;
}
const n = Math.round(Number(p));
if (!Number.isFinite(n)) return '';
return `<span class="pu-win"><span class="pu-label">${label}</span><span class="pu-val ${colorClass(n)}">${n}%</span></span>`;
};
const row = (provider, usage) => {
const windows = [seg('5h', pct(usage?.fiveHour)), seg('7d', pct(usage?.sevenDay))].filter(Boolean);
// The provider label only earns its space when there is more than one
// provider to tell apart: a machine with Claude alone shows bare windows.
const hasWindows = (usage) => pct(usage?.fiveHour) !== null || pct(usage?.sevenDay) !== null;
const labelled = hasWindows(data) && hasWindows(data.codex);
const row = (provider, usage, idle) => {
// hasWindows() gates the row, so a placeholder can only ever appear
// ALONGSIDE a real reading — a provider reporting nothing still renders
// nothing, never a row of em dashes.
if (!hasWindows(usage)) return '';
const windows = [seg('5h', pct(usage?.fiveHour), idle), seg('7d', pct(usage?.sevenDay), idle)].filter(Boolean);
if (!windows.length) return '';
return `<span class="pu-row"><span class="pu-provider">${provider}</span><span class="pu-windows">${windows.join('<span class="pu-sep">·</span>')}</span></span>`;
const label = labelled ? `<span class="pu-provider">${provider}</span>` : '';
return `<span class="pu-row">${label}<span class="pu-windows">${windows.join('<span class="pu-sep">·</span>')}</span></span>`;
};
const rows = [row('Claude', data), row('Codex', data.codex)].filter(Boolean);
const rows = [row('Claude', data, true), row('Codex', data.codex, false)].filter(Boolean);
chip.innerHTML = rows.length ? rows.join('') : '—';
const resetStr = (w) => (w && w.resetAt ? new Date(w.resetAt).toLocaleString() : '—');
const details = (provider, usage) => {
const details = (provider, usage, idle) => {
const lines = [];
const five = pct(usage?.fiveHour);
const seven = pct(usage?.sevenDay);
if (five !== null) lines.push(`5-hour limit: ${five}% used (resets ${resetStr(usage.fiveHour)})`);
else if (idle && seven !== null) lines.push('5-hour limit: no active session window');
if (seven !== null) lines.push(`Weekly limit: ${seven}% used (resets ${resetStr(usage.sevenDay)})`);
return lines.length ? `${provider} plan usage\n${lines.join('\n')}` : '';
};
chip.title = [details('Claude', data), details('Codex', data.codex)].filter(Boolean).join('\n\n') || 'Plan usage limits';
chip.title =
[details('Claude', data, true), details('Codex', data.codex, false)].filter(Boolean).join('\n\n') ||
'Plan usage limits';
}
// Scheduled runs
@@ -4896,7 +4921,7 @@ class CodemanApp {
<span class="tab-status ${status}" aria-hidden="true"></span>
<span class="tab-info">
<span class="tab-name-row">
${mode === 'shell' ? '<span class="tab-mode shell" aria-hidden="true">sh</span>' : mode === 'opencode' ? '<span class="tab-mode opencode" aria-hidden="true">oc</span>' : mode === 'codex' ? '<span class="tab-mode codex" aria-hidden="true">cx</span>' : mode === 'gemini' ? '<span class="tab-mode gemini" aria-hidden="true">gm</span>' : mode === 'antigravity' ? '<span class="tab-mode antigravity" aria-hidden="true">ag</span>' : mode === 'pi' ? '<span class="tab-mode pi" aria-hidden="true">pi</span>' : mode === 'grok' ? '<span class="tab-mode grok" aria-hidden="true">gk</span>' : mode === 'deepseek' ? '<span class="tab-mode deepseek" aria-hidden="true">ds</span>' : ''}
${mode === 'shell' ? '<span class="tab-mode shell" aria-hidden="true">sh</span>' : mode === 'opencode' ? '<span class="tab-mode opencode" aria-hidden="true">oc</span>' : mode === 'codex' ? '<span class="tab-mode codex" aria-hidden="true">cx</span>' : mode === 'gemini' ? '<span class="tab-mode gemini" aria-hidden="true">gm</span>' : mode === 'antigravity' ? '<span class="tab-mode antigravity" aria-hidden="true">ag</span>' : mode === 'pi' ? '<span class="tab-mode pi" aria-hidden="true">pi</span>' : mode === 'grok' ? '<span class="tab-mode grok" aria-hidden="true">gk</span>' : mode === 'deepseek' ? '<span class="tab-mode deepseek" aria-hidden="true">ds</span>' : mode === 'omp' ? '<span class="tab-mode omp" aria-hidden="true">om</span>' : ''}
<span class="tab-name" data-session-id="${id}" data-full-name="${escapeHtml(name)}">${tabLabel}</span>
${inlineSessionActions ? tabActionsHtml : ''}
<span class="tab-detached-badge" aria-hidden="true">detached</span>
@@ -6344,7 +6369,9 @@ class CodemanApp {
? 'Kill Tmux & Grok'
: session.mode === 'deepseek'
? 'Kill Tmux & DeepSeek'
: 'Kill Tmux & Claude Code';
: session.mode === 'omp'
? 'Kill Tmux & OMP'
: 'Kill Tmux & Claude Code';
}
document.getElementById('closeConfirmModal').classList.add('active');
+1 -1
View File
@@ -10,7 +10,7 @@
* @globals {function} scheduleBackground - scheduler.postTask wrapper (background priority)
* @globals {function} getEventCoords - Unified mouse/touch coordinate extractor
* @globals {function} escapeHtml - XSS-safe HTML escaping
* @globals {object} SSE_EVENTS - Centralized SSE event type constants (156 event types; must match backend src/web/sse-events.ts)
* @globals {object} SSE_EVENTS - Centralized SSE event type constants (157 event types; must match backend src/web/sse-events.ts)
* @globals {Array} BUILTIN_RESPAWN_PRESETS - Built-in respawn configuration presets
*
* @dependency None (first in load order)
+1
View File
@@ -80,6 +80,7 @@ const HOME_SESSIONS_MODE_BADGE = {
pi: 'pi',
grok: 'gk',
deepseek: 'ds',
omp: 'om',
};
Object.assign(CodemanApp.prototype, {
+17 -1
View File
@@ -452,6 +452,10 @@
<svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><polygon points="5 3 19 12 5 21 5 3"/></svg>
Run DeepSeek
</button>
<button class="welcome-btn welcome-btn-omp" id="welcomeOmpBtn" style="display: none;" onclick="app.setRunMode('omp'); app.runOmp()">
<svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><polygon points="5 3 19 12 5 21 5 3"/></svg>
Run OMP
</button>
</div>
<div class="welcome-qr" id="welcomeQr" onclick="app.toggleWelcomeQrSize()">
<div class="welcome-qr-inner" id="welcomeQrInner"></div>
@@ -643,6 +647,9 @@
<button class="run-mode-option run-mode-option-install" data-action="deepseek-install" id="runModeDeepSeekInstall" style="display: none;" onclick="app.installDeepSeekProfile()">
<span class="run-mode-dot deepseek"></span>DeepSeek — add a terminal profile…
</button>
<button class="run-mode-option" data-mode="omp" onclick="app.setRunMode('omp')">
<span class="run-mode-dot omp"></span>OMP
</button>
<div class="run-mode-sep"></div>
<button class="run-mode-option" data-mode="shell" onclick="app.setRunMode('shell')">
<span class="run-mode-dot shell"></span>Terminal / Shell
@@ -930,6 +937,7 @@
<option value="pi">Pi</option>
<option value="grok">Grok</option>
<option value="deepseek">DeepSeek</option>
<option value="omp">OMP</option>
</select>
</div>
<div class="form-row"><label>Working Directory</label><input type="text" id="schWorkingDir" placeholder="/absolute/path"></div>
@@ -2020,6 +2028,8 @@
<div class="set-modelgrid" id="appSettingsModelCards" role="radiogroup" aria-label="Model for new Claude sessions" data-search="model opus sonnet haiku fable claude"></div>
<select id="appSettingsClaudeModel" class="set-select set-field-hidden" aria-hidden="true" tabindex="-1">
<option value="" data-meta="Whatever the CLI picks">Default (CLI setting)</option>
<option value="claude-fable-5-1" data-meta="Latest" data-base="claude-fable-5-1" data-ctx="1">Fable 5.1</option>
<option value="claude-fable-5-1[1m]" data-variant="1m" data-base="claude-fable-5-1">Fable 5.1 (1M context)</option>
<option value="claude-fable-5" data-meta="Most powerful" data-base="claude-fable-5" data-ctx="1">Fable 5</option>
<option value="claude-fable-5[1m]" data-variant="1m" data-base="claude-fable-5">Fable 5 (1M context)</option>
<option value="opus" data-meta="Most capable" data-base="opus" data-ctx="1">Opus</option>
@@ -2032,7 +2042,7 @@
<div class="set-row" id="appSettingsContextRow" data-search="1m context window opus long">
<div class="set-row-text">
<span class="set-row-label">1M context window</span>
<span class="set-row-desc" id="appSettingsContextDesc">Available for Fable 5, Opus and Opus 4.6.</span>
<span class="set-row-desc" id="appSettingsContextDesc">Available for Fable 5.1, Fable 5, Opus and Opus 4.6.</span>
</div>
<label class="switch switch-sm"><input type="checkbox" id="appSettingsOpusContext1m"><span class="slider"></span></label>
</div>
@@ -2072,6 +2082,7 @@
</div>
<select id="appSettingsDefaultModel" class="set-select">
<option value="">Default (CLI default)</option>
<option value="claude-fable-5-1">Fable 5.1 (Latest)</option>
<option value="claude-fable-5">Fable 5 (Most powerful)</option>
<option value="opus">Opus (Most capable)</option>
<option value="sonnet">Sonnet (Balanced)</option>
@@ -2086,6 +2097,7 @@
<option value="haiku">Haiku</option>
<option value="sonnet">Sonnet</option>
<option value="opus">Opus</option>
<option value="claude-fable-5-1">Fable 5.1</option>
<option value="claude-fable-5">Fable 5</option>
</select>
</div>
@@ -2096,6 +2108,7 @@
<option value="haiku">Haiku</option>
<option value="sonnet">Sonnet</option>
<option value="opus">Opus</option>
<option value="claude-fable-5-1">Fable 5.1</option>
<option value="claude-fable-5">Fable 5</option>
</select>
</div>
@@ -2106,6 +2119,7 @@
<option value="haiku">Haiku</option>
<option value="sonnet">Sonnet</option>
<option value="opus">Opus</option>
<option value="claude-fable-5-1">Fable 5.1</option>
<option value="claude-fable-5">Fable 5</option>
</select>
</div>
@@ -2116,6 +2130,7 @@
<option value="haiku">Haiku</option>
<option value="sonnet">Sonnet</option>
<option value="opus">Opus</option>
<option value="claude-fable-5-1">Fable 5.1</option>
<option value="claude-fable-5">Fable 5</option>
</select>
</div>
@@ -2710,6 +2725,7 @@
<option value="pi" data-cli="pi">Pi</option>
<option value="grok" data-cli="grok">Grok</option>
<option value="deepseek" data-cli="deepseek">DeepSeek</option>
<option value="omp" data-cli="omp">OMP</option>
<option value="shell">Shell (no agent)</option>
</select>
<span class="form-hint">Which CLI to point the Run button at once the clone finishes. Changeable any time from the Run dropdown.</span>
+2 -1
View File
@@ -56,6 +56,7 @@ const MOBILE_OVERVIEW_RUN_MODES = [
{ mode: 'pi', label: 'Pi', short: 'Pi' },
{ mode: 'grok', label: 'Grok', short: 'Grok' },
{ mode: 'deepseek', label: 'DeepSeek', short: 'DeepSeek' },
{ mode: 'omp', label: 'OMP', short: 'OMP' },
{ mode: 'shell', label: 'Terminal / Shell', short: 'Shell' },
];
@@ -388,7 +389,7 @@ Object.assign(CodemanApp.prototype, {
async resumeMobileOverviewSession(sessionId) {
const row = (this._mobileOverviewPastRows || []).find((r) => r.id === sessionId);
if (!row || !row.workingDir) return;
await this.resumeHistorySession(row.claudeSessionId || row.id, row.workingDir, row.name || undefined);
await this.resumeHistorySession(row.claudeSessionId || row.id, row.workingDir, row.name || undefined, row.mode);
},
// ═══════════════════════════════════════════════════════════════
+20
View File
@@ -1003,6 +1003,20 @@ html.mobile-init .file-browser-panel {
border-color: rgba(150, 170, 255, 0.55) !important;
}
/* OMP mode colors on mobile. Same `!important` rationale as the pi/grok/deepseek blocks above. */
.btn-toolbar.btn-run.mode-omp,
.btn-toolbar.btn-run-gear.mode-omp {
background: #312e81 !important;
border-color: rgba(129, 140, 248, 0.3) !important;
color: #e0e7ff !important;
}
.btn-toolbar.btn-run.mode-omp:active,
.btn-toolbar.btn-run-gear.mode-omp:active {
background: #4f46e5 !important;
border-color: rgba(129, 140, 248, 0.5) !important;
}
/* Run mode dropdown menu — positioned above toolbar on mobile */
.run-mode-menu {
bottom: 100%;
@@ -3086,6 +3100,12 @@ html:is([data-skin="paper-gray"], [data-skin="solarized-light"], [data-skin="cat
color: #ffffff;
}
html:is([data-skin="paper-gray"], [data-skin="solarized-light"], [data-skin="catppuccin-latte"], [data-skin="rose-pine-dawn"]) :is(.btn-toolbar.btn-run.mode-omp, .btn-toolbar.btn-run-gear.mode-omp) {
background: linear-gradient(135deg, #4f46e5, #6366f1);
border-color: #4338ca;
color: #ffffff;
}
html:is([data-skin="paper-gray"], [data-skin="solarized-light"], [data-skin="catppuccin-latte"], [data-skin="rose-pine-dawn"]) :is(.btn-toolbar.btn-run.mode-grok, .btn-toolbar.btn-run-gear.mode-grok) {
background: linear-gradient(135deg, #27272a, #52525b);
border-color: #18181b;
+2 -2
View File
@@ -432,7 +432,7 @@ Object.assign(CodemanApp.prototype, {
_buildCommandPaletteNewSessionItem(query = '') {
const mode = this.runMode || this._runMode || 'claude';
const labels = { claude: 'Claude', opencode: 'OpenCode', codex: 'Codex', gemini: 'Gemini', antigravity: 'Antigravity', pi: 'Pi', grok: 'Grok', deepseek: 'DeepSeek' };
const labels = { claude: 'Claude', opencode: 'OpenCode', codex: 'Codex', gemini: 'Gemini', antigravity: 'Antigravity', pi: 'Pi', grok: 'Grok', deepseek: 'DeepSeek', omp: 'OMP' };
const caseName = this._findCommandPaletteCaseMatch(query) || document.getElementById('quickStartCase')?.value || 'testcase';
return {
id: 'new-session',
@@ -670,7 +670,7 @@ Object.assign(CodemanApp.prototype, {
} else if (record.workingDir) {
// History rows are keyed by the Claude conversation UUID; resumed
// sessions carry theirs separately as claudeSessionId.
void this.resumeHistorySession(s.claudeSessionId || s.sessionId, record.workingDir);
void this.resumeHistorySession(s.claudeSessionId || s.sessionId, record.workingDir, undefined, s.mode);
}
},
});
+59 -6
View File
@@ -407,6 +407,9 @@ Object.assign(CodemanApp.prototype, {
if (mode === 'antigravity') {
return await this.runAntigravity();
}
if (mode === 'omp') {
return await this.runOmp();
}
if (mode === 'pi') {
return await this.runPi();
}
@@ -501,7 +504,7 @@ Object.assign(CodemanApp.prototype, {
// An unreachable container hides every agent mode and explains why, instead
// of silently offering modes that cannot start.
const probeError = isDocker ? this._dockerCaseProbeError?.[caseName] : null;
for (const mode of ['claude', 'opencode', 'codex', 'gemini', 'antigravity', 'pi', 'grok', 'deepseek']) {
for (const mode of ['claude', 'opencode', 'codex', 'gemini', 'antigravity', 'pi', 'grok', 'deepseek', 'omp']) {
const btn = menu.querySelector(`.run-mode-option[data-mode="${mode}"]`);
if (!btn) continue;
let available;
@@ -789,7 +792,7 @@ Object.assign(CodemanApp.prototype, {
btn.append(...parts);
btn.addEventListener('click', (e) => {
e.stopPropagation();
this.resumeHistorySession(s.sessionId, s.workingDir, s.name);
this.resumeHistorySession(s.sessionId, s.workingDir, s.name, s.mode);
});
container.appendChild(btn);
}
@@ -810,7 +813,7 @@ Object.assign(CodemanApp.prototype, {
gearBtn.className = `btn-toolbar btn-run-gear mode-${mode}`;
}
if (label) {
label.textContent = mode === 'opencode' ? 'Run OC' : mode === 'codex' ? 'Run CX' : mode === 'gemini' ? 'Run GM' : mode === 'antigravity' ? 'Run AG' : mode === 'pi' ? 'Run PI' : mode === 'grok' ? 'Run GK' : mode === 'deepseek' ? 'Run DS' : mode === 'shell' ? 'Run SH' : 'Run';
label.textContent = mode === 'opencode' ? 'Run OC' : mode === 'codex' ? 'Run CX' : mode === 'gemini' ? 'Run GM' : mode === 'antigravity' ? 'Run AG' : mode === 'pi' ? 'Run PI' : mode === 'grok' ? 'Run GK' : mode === 'deepseek' ? 'Run DS' : mode === 'omp' ? 'Run OMP' : mode === 'shell' ? 'Run SH' : 'Run';
}
},
@@ -1523,6 +1526,56 @@ Object.assign(CodemanApp.prototype, {
}
},
async runOmp() {
const caseName = document.getElementById('quickStartCase').value || 'testcase';
// Remote/docker cases run omp on the OTHER side — skip the local status probe
// and the local-only config below (quick-start rejects them for remote cases).
const _runLoc = (this.cases || []).find(c => c.name === caseName)?.location;
const isRemote = _runLoc === 'remote' || _runLoc === 'docker';
const ownsLaunchTerminal = this._beginSessionLaunchStatus(`Starting OMP session in ${caseName}...`);
this.terminal.focus();
try {
if (!isRemote) {
const statusRes = await fetch('/api/omp/status');
const status = (await statusRes.json()).data;
if (!status.available) {
this._reportSessionLaunchError(
ownsLaunchTerminal,
'OMP CLI not found. Install with: curl -fsSL https://omp.sh/install | sh'
);
return;
}
}
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), this.loadAppSettingsFromStorage());
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'omp',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
}),
})
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start OMP');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
if (data.data.sessionId) {
await this.selectSession(data.data.sessionId);
}
this.terminal.focus();
} catch (err) {
this._reportSessionLaunchError(ownsLaunchTerminal, err.message);
}
},
/**
* Launch a Grok Build (xAI `grok`) session.
*
@@ -1726,7 +1779,7 @@ Object.assign(CodemanApp.prototype, {
if (detachToggle) detachToggle.checked = this.hasTabDetachOverride(sessionId);
// Reset to an appropriate tab — Summary for external CLIs (Respawn/Ralph are Claude-only)
const isAltMode = session.mode === 'opencode' || session.mode === 'codex' || session.mode === 'gemini' || session.mode === 'antigravity' || session.mode === 'pi' || session.mode === 'grok' || session.mode === 'deepseek';
const isAltMode = session.mode === 'opencode' || session.mode === 'codex' || session.mode === 'gemini' || session.mode === 'antigravity' || session.mode === 'pi' || session.mode === 'grok' || session.mode === 'deepseek' || session.mode === 'omp';
this.switchOptionsTab(isAltMode ? 'summary' : 'respawn');
// Update respawn status display and buttons
@@ -1756,7 +1809,7 @@ Object.assign(CodemanApp.prototype, {
}
// Hide Claude-specific options for external CLI sessions
const isExternalCli = session.mode === 'opencode' || session.mode === 'codex' || session.mode === 'gemini' || session.mode === 'antigravity' || session.mode === 'pi' || session.mode === 'grok' || session.mode === 'deepseek';
const isExternalCli = session.mode === 'opencode' || session.mode === 'codex' || session.mode === 'gemini' || session.mode === 'antigravity' || session.mode === 'pi' || session.mode === 'grok' || session.mode === 'deepseek' || session.mode === 'omp';
const claudeOnlyEls = document.querySelectorAll('[data-claude-only]');
claudeOnlyEls.forEach(el => { el.style.display = isExternalCli ? 'none' : ''; });
@@ -3733,7 +3786,7 @@ Object.defineProperty(CodemanApp.prototype, 'runMode', {
},
set(mode) {
this._runMode =
mode === 'opencode' || mode === 'codex' || mode === 'gemini' || mode === 'antigravity' || mode === 'pi' || mode === 'grok' || mode === 'deepseek' || mode === 'claude'
mode === 'opencode' || mode === 'codex' || mode === 'gemini' || mode === 'antigravity' || mode === 'pi' || mode === 'grok' || mode === 'deepseek' || mode === 'omp' || mode === 'claude'
? mode
: 'claude';
},
+34 -5
View File
@@ -922,7 +922,7 @@ Object.assign(CodemanApp.prototype, {
desc.textContent = inert
? 'The selected model has no 1M variant.'
: base
? 'Available for Fable 5, Opus and Opus 4.6.'
? 'Available for Fable 5.1, Fable 5, Opus and Opus 4.6.'
: 'With no model pinned, this starts new sessions on Opus with a 1M window.';
}
},
@@ -1079,10 +1079,14 @@ Object.assign(CodemanApp.prototype, {
const verEl = this.$('updateCurrentVersion');
if (verEl && data.currentVersion) verEl.textContent = `v${data.currentVersion}`;
if (data.installKind && data.installKind !== 'git') {
this._setUpdateResult(
`This install can't update itself (${escapeHtml(data.installKind)}). Update with <code>npm i -g aicodeman@latest</code>.`
);
// `docker-compose` self-updates in place like `git` does — the container
// restarts itself. Anything else cannot.
if (data.installKind && data.installKind !== 'git' && data.installKind !== 'docker-compose') {
const hint =
data.supervisor === 'docker-compose'
? 'Update from the Docker host with <code>docker/Start-Codeman.sh</code>.'
: 'Update with <code>npm i -g aicodeman@latest</code>.';
this._setUpdateResult(`This install can't update itself (${escapeHtml(data.installKind)}). ${hint}`);
return;
}
if (data.selfUpdateEnabled === false) {
@@ -1093,6 +1097,30 @@ Object.assign(CodemanApp.prototype, {
this._setUpdateResult(escapeHtml(data.error));
return;
}
// A container release that changes the ENVIRONMENT (Dockerfile, compose file
// or new .env keys) cannot be applied by the container restarting itself, so
// the update button is never offered — the host command is, instead. The
// server re-checks this on POST, so hiding the button is UX, not the gate.
const blockers = data.environment?.blockers || [];
if (data.updateAvailable && blockers.length > 0) {
const reasons = blockers
.map((b) => {
const details = b.details?.length ? `<br><code>${escapeHtml(b.details.join(' '))}</code>` : '';
return `<li>${escapeHtml(b.message)}${details}</li>`;
})
.join('');
this._setUpdateResult(
`<strong>v${escapeHtml(data.latestVersion || '')}</strong> needs a rebuild on the Docker host` +
` (current v${escapeHtml(data.currentVersion || '')}):<ul>${reasons}</ul>` +
`Run <code>${escapeHtml(data.environment?.hostCommand || 'docker/Start-Codeman.sh')}</code> there to apply it.`
);
if (notes && data.notes) {
notes.style.display = 'block';
notes.textContent = data.notes;
}
return;
}
if (data.updateAvailable && data.latestVersion) {
this._setUpdateResult(
`Update available: <strong>v${escapeHtml(data.latestVersion)}</strong> &nbsp;(current v${escapeHtml(data.currentVersion || '')})`
@@ -1230,6 +1258,7 @@ Object.assign(CodemanApp.prototype, {
['welcomeClaudeBtn', 'claude'],
['welcomeOpencodeBtn', 'opencode'],
['welcomeAntigravityBtn', 'antigravity'],
['welcomeOmpBtn', 'omp'],
['welcomeGeminiBtn', 'gemini'],
['welcomePiBtn', 'pi'],
['welcomeGrokBtn', 'grok'],
+45 -1
View File
@@ -349,7 +349,8 @@ html:is([data-skin="paper-gray"], [data-skin="solarized-light"], [data-skin="cat
.session-tab .tab-mode.gemini,
.session-tab .tab-mode.antigravity,
.session-tab .tab-mode.pi,
.session-tab .tab-mode.grok
.session-tab .tab-mode.grok,
.session-tab .tab-mode.omp
) {
color: var(--accent-d);
}
@@ -2499,6 +2500,10 @@ body.solo-mode .btn-lifecycle-log {
background: rgba(34, 211, 238, 0.2);
color: #22d3ee;
}
.session-tab .tab-mode.omp {
background: rgba(129, 140, 248, 0.2);
color: #818cf8;
}
.session-tab .tab-mode.pi {
background: rgba(244, 114, 182, 0.2);
@@ -3883,6 +3888,22 @@ body.touch-device .terminal-container .xterm .xterm-helper-textarea {
color: #fff1f7;
transform: translateY(-1px);
}
/* OMP: indigo identity, matching .btn-toolbar.btn-run.mode-omp and
.run-mode-dot.omp so the welcome action reads as the same backend. */
.welcome-btn-omp {
background: linear-gradient(135deg, #1e1b4b 0%, #4f46e5 55%, #6366f1 100%);
border-color: rgba(129, 140, 248, 0.4);
color: #e0e7ff;
box-shadow: 0 2px 8px rgba(129, 140, 248, 0.16), inset 0 1px 0 rgba(255, 255, 255, 0.06);
}
.welcome-btn-omp:hover {
background: linear-gradient(135deg, #312e81 0%, #6366f1 55%, #818cf8 100%);
box-shadow: 0 4px 20px rgba(129, 140, 248, 0.3), 0 0 40px rgba(79, 70, 229, 0.12), inset 0 1px 0 rgba(255, 255, 255, 0.08);
border-color: rgba(165, 180, 252, 0.5);
color: #eef2ff;
transform: translateY(-1px);
}
/* Grok (xAI): monochrome charcoal identity, matching .btn-toolbar.btn-run.mode-grok
and .run-mode-dot.grok so the welcome action reads as the same backend. */
@@ -4992,6 +5013,21 @@ body.touch-device .terminal-container .xterm .xterm-helper-textarea {
border-color: rgba(249, 168, 212, 0.6);
color: #fff1f7;
}
/* OMP mode colors */
.btn-toolbar.btn-run.mode-omp,
.btn-toolbar.btn-run-gear.mode-omp {
background: linear-gradient(135deg, #312e81 0%, #4f46e5 55%, #6366f1 100%);
border-color: rgba(129, 140, 248, 0.5);
color: #e0e7ff;
box-shadow: 0 1px 2px rgba(0, 0, 0, 0.2), inset 0 1px 0 rgba(255, 255, 255, 0.06);
}
.btn-toolbar.btn-run.mode-omp:hover,
.btn-toolbar.btn-run-gear.mode-omp:hover {
background: linear-gradient(135deg, #3730a3 0%, #6366f1 55%, #818cf8 100%);
box-shadow: 0 0 12px rgba(129, 140, 248, 0.35), 0 2px 8px rgba(79, 70, 229, 0.2), inset 0 1px 0 rgba(255, 255, 255, 0.08);
border-color: rgba(165, 180, 252, 0.6);
color: #eef2ff;
}
/* Grok mode colors. Same cascade note as pi above: this base-sheet pair only
renders on the `og` skin — the nested `html:not([data-skin="og"])` block
@@ -5116,6 +5152,7 @@ body.touch-device .terminal-container .xterm .xterm-helper-textarea {
.run-mode-dot.pi { background: #f472b6; }
.run-mode-dot.grok { background: #a1a1aa; }
.run-mode-dot.deepseek { background: #4d6bfe; }
.run-mode-dot.omp { background: #818cf8; }
.run-mode-dot.shell { background: #94a3b8; }
/* Phone-only Enter button (see index.html). Hidden by default at every width;
@@ -12433,6 +12470,13 @@ kbd {
color: var(--text-dim);
opacity: 0.45;
}
/* A window Claude is not currently reporting: the slot stays, dimmed, so the
chip keeps its shape instead of looking like half of it broke. */
.header-plan-usage .pu-win-idle .pu-label,
.header-plan-usage .pu-win-idle .pu-val {
color: var(--text-dim);
opacity: 0.55;
}
/* Green/yellow/red by how much of the window is used up. */
.header-plan-usage .pu-green {
color: #3fb950;
+51 -4
View File
@@ -2193,7 +2193,7 @@ Object.assign(CodemanApp.prototype, {
if (isLive && this.sessions.has(s.sessionId)) {
this.selectSession(s.sessionId);
} else {
this.resumeHistorySession(s.claudeSessionId || s.sessionId, s.workingDir || '', s.name);
this.resumeHistorySession(s.claudeSessionId || s.sessionId, s.workingDir || '', s.name, s.mode);
}
})
);
@@ -2436,7 +2436,7 @@ Object.assign(CodemanApp.prototype, {
} else {
// Resume by the Claude conversation UUID when present (resumed sessions
// carry theirs separately from their Codeman id).
this.resumeHistorySession(s.claudeSessionId || s.sessionId, s.workingDir || '', s.name);
this.resumeHistorySession(s.claudeSessionId || s.sessionId, s.workingDir || '', s.name, s.mode);
}
this.closeSessionManager?.();
closeMenu();
@@ -2904,7 +2904,7 @@ Object.assign(CodemanApp.prototype, {
return `w${startNumber}-${dirName}`;
},
async resumeHistorySession(sessionId, workingDir, existingName) {
async resumeHistorySession(sessionId, workingDir, existingName, mode) {
// Close the run mode menu if open
document.getElementById('runModeMenu')?.classList.remove('active');
// Close folder history modal if open
@@ -2925,13 +2925,45 @@ Object.assign(CodemanApp.prototype, {
const globalSettings = this.loadAppSettingsFromStorage();
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), globalSettings);
const effort = this.getEffortSetting(globalSettings);
// `resumeSessionId` is a Claude conversation UUID (server reads it from
// ~/.claude/projects); an external-CLI row has no such thing, so sending
// it there gets silently ignored while the OMITTED `mode` field defaults
// the create to plain claude — reproducing whatever conversation THAT
// uuid happens to collide with instead of the row's own backend. Row mode
// wins here. Codeman has no cross-restart PTY-reattach outside server
// boot, so "resume" for a non-claude row means relaunching the CLI's own
// continue-most-recent flag (opencode/pi/grok/omp --continue, deepseek
// resumeSession) in the same directory — real conversation continuity,
// just not the literal old process.
const effectiveMode = mode || 'claude';
const modeConfigKey = {
opencode: 'openCodeConfig',
pi: 'piConfig',
grok: 'grokConfig',
omp: 'ompConfig',
}[effectiveMode];
// codex/gemini/antigravity have no wired continuation here yet (their
// configs use an exact conversation id, not a "continue most recent"
// flag, and the row's own `sessionId` is not verified to carry that
// id for these three modes) — `continuesSomething` below is what keeps
// their row from being retired for a resume that didn't actually
// continue anything.
const modeConfig =
modeConfigKey
? { [modeConfigKey]: { continueSession: true } }
: effectiveMode === 'deepseek'
? { deepSeekConfig: { resumeSession: true } }
: {};
const continuesSomething = Boolean(modeConfigKey) || effectiveMode === 'deepseek';
const createRes = await fetch('/api/sessions', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
workingDir,
name,
resumeSessionId: sessionId,
mode: effectiveMode,
...(effectiveMode === 'claude' ? { resumeSessionId: sessionId } : {}),
...modeConfig,
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
...(effort ? { effort } : {}),
}),
@@ -2944,6 +2976,21 @@ Object.assign(CodemanApp.prototype, {
// Start interactive
await fetch(`/api/sessions/${newSessionId}/interactive`, { method: 'POST' });
// Retire the row being resumed: a non-claude "resume" is really a brand
// new Codeman session pointed at the same directory (there is no id to
// reattach to), so without this every resume leaves the old row behind
// as a duplicate — click it 3 times, see the same name 3 times. Claude
// rows are left alone: `sessionId` there is a claudeSessionId, which
// usually has no live/persisted Codeman session of its own to delete.
// Gated on `continuesSomething`: for codex/gemini/antigravity (no
// continuation wired above), this is really a FRESH session with no
// relation to the old row's conversation, so retiring it would discard
// the old conversation with no recovery — worse than the duplicate row
// this guard exists to prevent for the modes that DO continue.
if (effectiveMode !== 'claude' && continuesSomething && sessionId !== newSessionId) {
fetch(`/api/sessions/${sessionId}?killMux=true`, { method: 'DELETE' }).catch(() => {});
}
this.terminal.writeln(`\x1b[90m Session ${name} ready\x1b[0m`);
await this.selectSession(newSessionId);
this.terminal.focus();
+39 -9
View File
@@ -8,11 +8,10 @@
import { join, resolve, relative, isAbsolute } from 'node:path';
import { realpathSync, existsSync, mkdirSync } from 'node:fs';
import fs from 'node:fs/promises';
import { homedir } from 'node:os';
import type { z } from 'zod';
import type { FastifyReply, FastifyRequest } from 'fastify';
import { Session } from '../session.js';
import { ApiErrorCode, createErrorResponse, type AuthUser } from '../types.js';
import { ApiErrorCode, createErrorResponse, type AuthUser, type SessionState } from '../types.js';
import { MAX_CONCURRENT_SESSIONS } from '../config/map-limits.js';
import { parseRalphLoopConfig, extractCompletionPhrase } from '../ralph-config.js';
import { SseEvent } from './sse-events.js';
@@ -21,12 +20,15 @@ import type { EventPort } from './ports/event-port.js';
import type { AuthSessionRecord } from './ports/auth-port.js';
import type { StaleExpirationMap } from '../utils/index.js';
import { dataPath } from '../config/instance.js';
import { getCasesDir } from '../config/cases-dir.js';
import { isMultiUserMode, maxSessionsPerUser, userCasesDir } from '../config/multiuser.js';
import { SYNTHETIC_ADMIN, findUser } from '../user-store.js';
// Shared path constants used across route modules. CASES_DIR (project folders)
// stays shared across instances; SETTINGS_PATH is per-instance runtime state.
export const CASES_DIR = join(homedir(), 'codeman-cases');
// The cases dir is resolved in ONE place (config/cases-dir.ts) because the CLI
// resolves it too, and CODEMAN_CASES_PATH must move both or neither.
export const CASES_DIR = getCasesDir();
export const SETTINGS_PATH = dataPath('settings.json');
/**
@@ -264,6 +266,18 @@ export function revokeUserSessions(
return removed;
}
/**
* The 404 both session-lookup helpers below throw. A missing session and one
* the caller isn't allowed to see get the IDENTICAL error (never 403), so
* existence of another user's session is never leaked.
*/
function sessionNotFoundError(sessionId: string): Error & { statusCode: number; body: unknown } {
return Object.assign(new Error(`Session ${sessionId} not found`), {
statusCode: 404,
body: createErrorResponse(ApiErrorCode.NOT_FOUND, `Session ${sessionId} not found`),
});
}
/**
* Look up a session by ID or throw a structured error.
* Replaces the pattern: `const session = sessions.get(id); if (!session) return createErrorResponse(...)`.
@@ -274,15 +288,31 @@ export function revokeUserSessions(
*/
export function findSessionOrFail(ctx: SessionPort, sessionId: string, req?: FastifyRequest): Session {
const session = ctx.sessions.get(sessionId);
if (!session || (req && !canAccessOwned(getAuthUser(req), session.owner))) {
throw Object.assign(new Error(`Session ${sessionId} not found`), {
statusCode: 404,
body: createErrorResponse(ApiErrorCode.NOT_FOUND, `Session ${sessionId} not found`),
});
}
if (!session) throw sessionNotFoundError(sessionId);
if (req && !canAccessOwned(getAuthUser(req), session.owner)) throw sessionNotFoundError(sessionId);
return session;
}
/**
* Like {@link findSessionOrFail}, for a session that exists ONLY in persisted
* state — a resumed-but-never-reattached row (e.g. a non-claude "Resume" that
* relaunched into a new session and wants to retire the row it can no longer
* reattach to) has no live `Session` instance for `findSessionOrFail` to
* return, so this returns the persisted record instead. Same ownership
* enforcement, same 404-not-403 leak protection — this is that function's
* missing other half, not a separate check reimplemented inline.
*/
export function findPersistedSessionOrFail(
store: { getSession(id: string): SessionState | null },
sessionId: string,
req?: FastifyRequest
): SessionState {
const persisted = store.getSession(sessionId);
if (!persisted) throw sessionNotFoundError(sessionId);
if (req && !canAccessOwned(getAuthUser(req), persisted.owner)) throw sessionNotFoundError(sessionId);
return persisted;
}
/** Shortest prefix accepted for a parent session id (see resolveParentSessionId). */
const PARENT_SESSION_ID_MIN_PREFIX = 8;
+6 -1
View File
@@ -35,6 +35,7 @@ import {
UserStoreError,
} from '../../user-store.js';
import { getAuthUser, requireAdmin, revokeUserSessions } from '../route-helpers.js';
import { webviewCapabilities } from '../../webview-capabilities.js';
import { appendAdminAudit } from '../admin-audit.js';
import { SseEvent } from '../sse-events.js';
import type { AuthPort } from '../ports/auth-port.js';
@@ -179,7 +180,10 @@ export function registerAdminRoutes(app: FastifyInstance, ctx: SessionPort & Aut
if (!gate(req, reply)) return;
const { username } = req.params as { username: string };
const revoked = revokeUserSessions(ctx.authSessions, username);
audit(req, 'user.logout', username, { revoked });
// Web-tab proxy capabilities are a second credential the cookie purge does not
// touch; a forced logout that left them alive would not be a logout.
const revokedWebviews = webviewCapabilities.revokeOwner(normalizeUsername(username));
audit(req, 'user.logout', username, { revoked, revokedWebviews });
return { success: true, data: { revoked } };
});
@@ -201,6 +205,7 @@ export function registerAdminRoutes(app: FastifyInstance, ctx: SessionPort & Aut
await ctx.cleanupSession(id, true, 'admin_delete_user').catch(() => {});
}
revokeUserSessions(ctx.authSessions, username);
webviewCapabilities.revokeOwner(normalizeUsername(username));
if (deleteSpace) await deleteUserSpace(username);
audit(req, 'user.delete', username, { deleteSpace, killedSessions: owned.length });
ctx.broadcast(SseEvent.AdminUsersChanged, {});
+3 -7
View File
@@ -72,7 +72,7 @@ import {
probeAdoptableContainer,
listDockerContainers,
browseInContainer,
DOCKER_ADOPT_PROBE_MODES,
dockerAdoptProbeModes,
readDockerCases,
readDockerHosts,
removeDockerContainer,
@@ -845,11 +845,7 @@ export function registerCaseRoutes(app: FastifyInstance, ctx: EventPort & Config
// hostWorkspacePath only because that is what an owned container's bind
// mount guarantees; adoption mounts nothing, so the probe has to prove it.
const adoptDocker = toSessionDocker(host, dockerCase);
const probe = await probeAdoptableContainer(
adoptDocker,
[...DOCKER_ADOPT_PROBE_MODES],
adoptDocker.containerWorkdir
);
const probe = await probeAdoptableContainer(adoptDocker, dockerAdoptProbeModes(), adoptDocker.containerWorkdir);
if (!probe.ok) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, probe.error || 'container is not adoptable');
}
@@ -930,7 +926,7 @@ export function registerCaseRoutes(app: FastifyInstance, ctx: EventPort & Config
daemonHost: host.daemonHost,
containerName: body.container,
},
[...DOCKER_ADOPT_PROBE_MODES],
dockerAdoptProbeModes(),
body.containerWorkdir
);
return { success: true, data: probe };
+3 -2
View File
@@ -7,6 +7,7 @@
*/
import { FastifyInstance } from 'fastify';
import { getCli } from '../../config/cli-registry/registry.js';
import { ApiErrorCode, createErrorResponse } from '../../types.js';
import { CronJobSchema, CronJobUpdateSchema, CronJobEnabledSchema } from '../schemas.js';
import { canAccessOwned, getAuthUser, isWorkingDirAllowed, ownerFor, parseBody } from '../route-helpers.js';
@@ -45,7 +46,7 @@ export function registerCronRoutes(app: FastifyInstance, ctx: CronPort): void {
// Resolve the owner's grant from the store (AuthUser.role alone can't tell a GRANTED
// regular user from a plain one); mirrors session-routes + the cron fire-time re-check.
if (
(body.agentType === 'shell' || body.launchCommand) &&
(getCli(body.agentType)?.capabilities.privilegedCommandGate || body.launchCommand) &&
!(await canUsernameRunPrivilegedCommands(ownerFor(req)))
) {
return createErrorResponse(
@@ -72,7 +73,7 @@ export function registerCronRoutes(app: FastifyInstance, ctx: CronPort): void {
return createErrorResponse(ApiErrorCode.FORBIDDEN, 'workingDir is outside your workspace');
}
if (
(body.agentType === 'shell' || body.launchCommand) &&
(getCli(body.agentType ?? 'claude')?.capabilities.privilegedCommandGate || body.launchCommand) &&
!(await canUsernameRunPrivilegedCommands(ownerFor(req)))
) {
return createErrorResponse(
+291 -252
View File
@@ -20,15 +20,18 @@ import {
type ApiResponse,
type SessionColor,
type SessionStatus,
type SessionMode,
type CodexConfig,
type GeminiConfig,
type AntigravityConfig,
type PiConfig,
type GrokConfig,
type DeepSeekConfig,
type OmpConfig,
} from '../../types.js';
import { Session, isAltScreenStripMode, isMuxAltScreenOnlyStripMode } from '../../session.js';
import { Session, isAltScreenStripMode, isExternalCliMode, isMuxAltScreenOnlyStripMode } from '../../session.js';
import { SseEvent } from '../sse-events.js';
import { webviewCapabilities } from '../../webview-capabilities.js';
import {
CreateSessionSchema,
SessionNameSchema,
@@ -65,6 +68,7 @@ import {
autoConfigureRalph,
canAccessOwned,
CASES_DIR,
findPersistedSessionOrFail,
findSessionOrFail,
getAuthUser,
isAdmin,
@@ -79,6 +83,9 @@ import {
validatePathWithinBase,
} from '../route-helpers.js';
import { canUsernameRunPrivilegedCommands, resolveClaudeModeForUsername } from '../../user-store.js';
import { enabledClis, getCli } from '../../config/cli-registry/registry.js';
import { resolveCliLaunchError } from '../../utils/cli-launcher.js';
import { legacyConfigForMode } from '../../session-cli-registry-bridge.js';
import { isMultiUserMode } from '../../config/multiuser.js';
import { AUTH_COOKIE_NAME } from '../middleware/auth.js';
import {
@@ -137,6 +144,8 @@ import {
toSessionDocker,
} from '../../docker-hosts.js';
import { LRUMap } from '../../utils/lru-map.js';
import { findLatestOmpSessionId } from '../../utils/omp-session-resolver.js';
import { scanOmpSessionsHistory } from '../../omp-transcript.js';
import {
getLastTranscriptResponse,
isExternalCliTranscriptMode,
@@ -352,12 +361,54 @@ export function _resetPasteRateBuckets(): void {
*/
async function clampExternalCliBypassForOwner(
owner: string | undefined,
codexConfig: CodexConfig | undefined,
geminiConfig: GeminiConfig | undefined,
antigravityConfig: AntigravityConfig | undefined,
piConfig: PiConfig | undefined,
grokConfig: GrokConfig | undefined,
deepSeekConfig: DeepSeekConfig | undefined
configs: Record<string, unknown>
): Promise<Record<string, unknown>> {
if (await canUsernameRunPrivilegedCommands(owner)) return configs;
const out = { ...configs };
for (const entry of enabledClis()) {
const field = entry.launch.legacyConfigField;
if (!field) continue;
// `privilegedParams[].param` names the REGISTRY param, so it has to be translated to the
// legacy wire field on the way out — the same `legacyConfigAliases` hop `configSetenvValues`
// already makes. Writing `param` straight through would put it in a DIFFERENT namespace
// from every other `param` in the schema, and a name that is right in one and wrong in the
// other is a SILENT no-op: no load error, no failing test, the clamp simply stops clamping.
// Codex is where the two names differ (`bypassApprovals` vs `dangerouslyBypassApprovals`),
// and `schema.ts` refuses an entry naming a param it never declared.
const aliases = entry.launch.legacyConfigAliases ?? {};
const existing = out[field] as Record<string, unknown> | undefined;
let next = existing;
for (const { param, clampTo, materializeWhenAbsent } of entry.capabilities.privilegedParams) {
// MATERIALIZE vs ONLY-IF-SENT is the whole design of this clamp, and the two are not
// interchangeable — see CliCapabilities.privilegedParams. Materialize where the CLI's
// own absent-config default is ITSELF unsafe (gemini defaults to yolo; pi's default is
// an interactive trust prompt the session user could just answer "yes" to), so a
// caller who sends no config at all still gets clamped.
if (next === undefined && !materializeWhenAbsent) continue;
next = { ...(next ?? {}), [aliases[param] ?? param]: clampTo };
}
if (next !== existing) out[field] = next;
}
return out;
}
/**
* Test hook, and the positional shape the clamp has always been called with in tests.
*
* The clamp itself is now generic over the registry, which is what makes a CUSTOM CLI's
* privileged flag clampable with no code here — previously the five config objects were
* named individually, so `privilegedParams` on anything outside that list was declared but
* unreachable.
*/
export async function _clampExternalCliBypassForOwner(
owner: string | undefined,
codexConfig?: CodexConfig,
geminiConfig?: GeminiConfig,
antigravityConfig?: AntigravityConfig,
piConfig?: PiConfig,
grokConfig?: GrokConfig,
deepSeekConfig?: DeepSeekConfig
): Promise<{
codexConfig: CodexConfig | undefined;
geminiConfig: GeminiConfig | undefined;
@@ -366,40 +417,30 @@ async function clampExternalCliBypassForOwner(
grokConfig: GrokConfig | undefined;
deepSeekConfig: DeepSeekConfig | undefined;
}> {
const granted = await canUsernameRunPrivilegedCommands(owner);
if (granted) return { codexConfig, geminiConfig, antigravityConfig, piConfig, grokConfig, deepSeekConfig };
// Non-granted: force codex/antigravity bypass off (only meaningful when a config was
// sent) and materialize gemini to auto_edit (clamps an explicit 'yolo' and the yolo default)
// and pi to --no-approve (clamps an explicit true AND pi's own "ask" default).
const clampedCodex = codexConfig ? { ...codexConfig, dangerouslyBypassApprovals: false } : codexConfig;
const clampedGemini: GeminiConfig = { ...(geminiConfig ?? {}), approvalMode: 'auto_edit' };
const clampedAntigravity = antigravityConfig
? { ...antigravityConfig, dangerouslySkipPermissions: false }
: antigravityConfig;
const clampedPi: PiConfig = { ...(piConfig ?? {}), approveProjectTrust: false };
const clampedGrok = grokConfig ? { ...grokConfig, alwaysApprove: false } : grokConfig;
const clampedDeepSeek = deepSeekConfig
? { ...deepSeekConfig, permissionMode: 'workspace-write' as const }
: deepSeekConfig;
return {
codexConfig: clampedCodex,
geminiConfig: clampedGemini,
antigravityConfig: clampedAntigravity,
piConfig: clampedPi,
grokConfig: clampedGrok,
deepSeekConfig: clampedDeepSeek,
const out = await clampExternalCliBypassForOwner(owner, {
codexConfig,
geminiConfig,
antigravityConfig,
piConfig,
grokConfig,
deepSeekConfig,
});
return out as {
codexConfig: CodexConfig | undefined;
geminiConfig: GeminiConfig | undefined;
antigravityConfig: AntigravityConfig | undefined;
piConfig: PiConfig | undefined;
grokConfig: GrokConfig | undefined;
deepSeekConfig: DeepSeekConfig | undefined;
};
}
/** Test hook: the clamp is the multi-user safety gate for the external CLIs' privileged flags. */
export const _clampExternalCliBypassForOwner = clampExternalCliBypassForOwner;
/**
* Env-var keys a non-granted owner must not be able to set, because each one
* hands back privilege the config clamp above just removed — or, for the last,
* redirects a credential the server injects.
* hands back privilege the config clamp above just removed, or redirects a
* credential-resolution endpoint.
*
* All are DeepSeek's, and all are reachable because `DSH_*` and `DEEPSEEK_*` are
* The DeepSeek three are reachable because `DSH_*` and `DEEPSEEK_*` are
* allowlisted `envOverrides` prefixes (schemas.ts) — which they have to be, since
* that is also how a user configures the harness's non-privileged knobs.
*
@@ -410,26 +451,38 @@ export const _clampExternalCliBypassForOwner = clampExternalCliBypassForOwner;
* - `DSH_HOME` points the launcher at a profile tree, and a profile's plugin code
* executes at BOOT, before any approval row can apply. A user who can write a
* workspace can put a profile in it, so this is the wider of the two.
* - `DEEPSEEK_BASE_URL` aims the provider endpoint, and `_configureDeepSeek()`
* - `DEEPSEEK_BASE_URL` aims the provider endpoint, and `_configureCliEnv()`
* forwards the SERVER's own `DEEPSEEK_API_KEY` into every dsh pane before
* `applyEnvOverrides()` runs — so a non-granted owner who could set the base
* URL would have the operator's API key sent as a bearer credential to a host
* of their choosing. (`DEEPSEEK_API_KEY` itself stays overridable: supplying
* your OWN key removes privilege rather than granting it.)
* - `OMP_AUTH_BROKER_URL`/`OMP_AUTH_BROKER_TOKEN` are where omp resolves
* credentials from — the same shape as `DEEPSEEK_BASE_URL` above, reachable
* because `OMP_*` is an allowlisted prefix. Unlike DeepSeek, Codeman does not
* forward any operator-held key into an omp pane today (omp's provider
* credentials live in `~/.omp` config files, not env vars), so there is no
* known concrete exfiltration path yet — clamped defensively anyway, since a
* non-granted owner redirecting where a shared multi-tenant deployment
* resolves auth from is not something to allow silently (found in
* Ark0N/Codeman#353 review; omp's own knobs are otherwise mostly `PI_*`,
* already allowlisted for pi and not addressed here — see resolveOmpHome()).
*/
const OWNER_CLAMPED_ENV_KEYS = ['DSH_PERMISSION_MODE', 'DSH_HOME', 'DEEPSEEK_BASE_URL'] as const;
function ownerClampedEnvKeys(): string[] {
return enabledClis().flatMap((entry) => entry.capabilities.privilegedEnvKeys);
}
/**
* Env-var half of the multi-user bypass clamp.
*
* `clampExternalCliBypassForOwner()` clamps the per-CLI CONFIG, and for every CLI
* but DeepSeek that is the whole story. Here it is not: `applyEnvOverrides()` runs
* AFTER `_configureDeepSeek()` in tmux-manager, so an override sent on the SAME
* AFTER `_configureCliEnv()` in tmux-manager, so an override sent on the SAME
* request lands last and wins, and a non-granted owner could restore
* `danger-full-access` on the very request the config clamp downgraded.
*
* Keys are DROPPED rather than rewritten: dropping falls through to what
* `_configureDeepSeek()` exports, which is the clamped config and the server's own
* `_configureCliEnv()` exports, which is the clamped config and the server's own
* `DSH_HOME`, i.e. exactly the intended state. No-op in single-user mode and for a
* granted owner, like every other clamp here
* (`canUsernameRunPrivilegedCommands()` returns true when `!isMultiUserMode()`),
@@ -440,38 +493,17 @@ async function clampEnvOverridesForOwner(
envOverrides: Record<string, string> | undefined
): Promise<Record<string, string> | undefined> {
if (!envOverrides) return envOverrides;
if (!OWNER_CLAMPED_ENV_KEYS.some((key) => key in envOverrides)) return envOverrides;
const keys = ownerClampedEnvKeys();
if (!keys.some((key) => key in envOverrides)) return envOverrides;
if (await canUsernameRunPrivilegedCommands(owner)) return envOverrides;
const clamped = { ...envOverrides };
for (const key of OWNER_CLAMPED_ENV_KEYS) delete clamped[key];
for (const key of keys) delete clamped[key];
return clamped;
}
/** Test hook: the env-var half of the same multi-user safety gate. */
export const _clampEnvOverridesForOwner = clampEnvOverridesForOwner;
/**
* Why a DeepSeek session cannot start, or null when it can.
*
* Availability for this mode is TWO questions, not one, because `dsh` is a
* profile launcher rather than an agent: the binary must resolve (and prove it
* is the harness and not Debian's dancer's shell), AND a profile that can occupy
* a pane must exist. Reporting only the first would let the Run button spawn a
* pane that dies instantly, which is the single most confusing failure this mode
* can produce, so each half gets its own actionable message.
*
* A profile named EXPLICITLY is checked on both counts: existence, and whether
* it is pane-capable — `web` serves a browser UI and `headless` answers one task
* and exits, so both would present as "the tab immediately died".
*/
async function resolveDeepSeekLaunchError(requestedProfile?: string): Promise<string | null> {
// Thin async wrapper: the implementation moved into the resolver module so
// CRON fires can ask the same question before constructing a Session; the
// dynamic import keeps this file's startup free of the probe machinery.
const { resolveDeepSeekLaunchError: impl } = await import('../../utils/deepseek-cli-resolver.js');
return impl(requestedProfile);
}
// ═══════════════════════════════════════════════════════════════
// Agent wait helpers (shared by GET /wait, GET /wait-output, POST /input)
// ═══════════════════════════════════════════════════════════════
@@ -745,6 +777,36 @@ async function injectAgentSkill(casePath: string): Promise<void> {
// bypassing the `workspaceHooksEnabled` setting. Route handlers here resolve the
// setting through the ConfigPort (tests stub it) and pass it as the second arg.
/**
* A "Resume"/"continue" request for a NEW omp-mode session (the frontend's
* resumeHistorySession(), or anyone hitting the API directly) carries
* `continueSession: true` but no id — omp has none to give it, since Codeman
* has never tracked its own conversation UUID. Left as `--continue`, that
* picks whichever session file in the directory is newest, which silently
* drifts to the WRONG conversation the moment a second omp session (this
* one, a sibling worker, a stray manual run) has touched the same directory
* more recently. Resolve the real id up front instead, same as the
* dead-pane-respawn path in session.ts does, so even the FIRST relaunch of a
* resumed conversation is pinned rather than guessed.
*/
export function resolveOmpConfigForCreate(
mode: SessionMode,
workingDir: string,
ompConfig: OmpConfig | undefined
): OmpConfig | undefined {
if (mode !== 'omp') return undefined;
if (!ompConfig || ompConfig.resumeSessionId || !ompConfig.continueSession) {
return ompConfig;
}
const resolvedId = findLatestOmpSessionId(workingDir);
if (!resolvedId) {
console.warn(
`[Session] OMP: no session file found under ${workingDir} to pin --resume; falling back to ambiguous --continue`
);
}
return resolvedId ? { ...ompConfig, resumeSessionId: resolvedId } : ompConfig;
}
export function registerSessionRoutes(
app: FastifyInstance,
ctx: SessionPort & EventPort & ConfigPort & InfraPort & AuthPort & TabLayoutPort
@@ -761,6 +823,10 @@ export function registerSessionRoutes(
if (sessionToken) {
ctx.authSessions?.delete(sessionToken);
}
// The web-tab proxy authenticates on capabilities, not on this cookie, so a
// logout has to retire them too or every dashboard URL opened during this
// login keeps relaying without one (WebviewCapabilityStore.revokeOwner).
webviewCapabilities.revokeOwner(ownerFor(req));
reply.clearCookie(AUTH_COOKIE_NAME, { path: '/' });
return {};
});
@@ -826,7 +892,10 @@ export function registerSessionRoutes(
// Multi-user: shell mode is arbitrary command execution as the host account,
// gated behind the same grant as bypass (section 6.3). Resolve the owner's grant
// from the store so a GRANTED regular user is not wrongly denied (AuthUser role alone can't tell).
if (body.mode === 'shell' && !(await canUsernameRunPrivilegedCommands(owner))) {
if (
getCli(body.mode ?? 'claude')?.capabilities.privilegedCommandGate &&
!(await canUsernameRunPrivilegedCommands(owner))
) {
return createErrorResponse(ApiErrorCode.FORBIDDEN, 'Shell sessions require the can-bypass-permissions grant');
}
@@ -859,14 +928,11 @@ export function registerSessionRoutes(
// repos that POST /api/sessions can target, as those may have hand-authored
// values).
const managedCasesBase = resolveCasesDir(getAuthUser(req));
// `!isExternalCliMode()` is byte-identical to the eight-mode `!==` chain it replaces
// (claude and shell are the two non-external modes) and, unlike the chain, cannot fall
// behind the next CLI added.
const canStripDisk =
body.mode !== 'opencode' &&
body.mode !== 'codex' &&
body.mode !== 'gemini' &&
body.mode !== 'antigravity' &&
body.mode !== 'pi' &&
body.mode !== 'grok' &&
body.mode !== 'deepseek' &&
!isExternalCliMode(body.mode ?? 'claude') &&
body.envOverrides &&
Object.keys(body.envOverrides).length > 0 &&
(workingDir.startsWith(CASES_DIR + '/') || workingDir.startsWith(managedCasesBase + '/'));
@@ -918,52 +984,24 @@ export function registerSessionRoutes(
}
}
// Check OpenCode availability if requested. The error text comes from the
// resolver (formatCliNotFoundMessage) so it names where resolution looked —
// server PATH, login shell, common directories — same for the modes below.
if (body.mode === 'opencode') {
const { isOpenCodeAvailable, getOpenCodeNotFoundMessage } = await import('../../utils/opencode-cli-resolver.js');
if (!isOpenCodeAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getOpenCodeNotFoundMessage());
}
}
// Check Codex availability if requested
if (body.mode === 'codex') {
const { isCodexAvailable, getCodexNotFoundMessage } = await import('../../utils/codex-cli-resolver.js');
if (!isCodexAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getCodexNotFoundMessage());
}
}
// Check Gemini availability if requested
if (body.mode === 'gemini') {
const { isGeminiAvailable, getGeminiNotFoundMessage } = await import('../../utils/gemini-cli-resolver.js');
if (!isGeminiAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getGeminiNotFoundMessage());
}
}
if (body.mode === 'antigravity') {
const { isAntigravityAvailable, getAntigravityNotFoundMessage } =
await import('../../utils/antigravity-cli-resolver.js');
if (!isAntigravityAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getAntigravityNotFoundMessage());
}
}
if (body.mode === 'pi') {
const { isPiAvailable, getPiNotFoundMessage } = await import('../../utils/pi-cli-resolver.js');
if (!isPiAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getPiNotFoundMessage());
}
}
if (body.mode === 'deepseek') {
const err = await resolveDeepSeekLaunchError(body.deepSeekConfig?.profile);
if (err) return createErrorResponse(ApiErrorCode.OPERATION_FAILED, err);
}
if (body.mode === 'grok') {
const { isGrokAvailable, getGrokNotFoundMessage } = await import('../../utils/grok-cli-resolver.js');
if (!isGrokAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getGrokNotFoundMessage());
// Refuse up front if the requested CLI cannot start, rather than spawning a pane that
// dies on `command not found`. The message comes from the resolver, so it names where
// resolution actually looked (server PATH, login shell, the entry's search dirs); a
// LAUNCHER CLI answers with its own more specific reason instead — for dsh, whether the
// binary is missing, no pane-capable profile exists, or the profile the caller NAMED
// cannot drive a pane, which are three different things to go and fix.
//
// Scoped to EXTERNAL CLIs, matching what this route has always pre-flighted: claude and
// shell deliberately fall through to tmux-manager's own not-found throw instead, and
// pulling them forward here would change which error a missing claude produces.
const requestedMode = body.mode ?? 'claude';
if (getCli(requestedMode)?.capabilities.external) {
const cliLaunchError = await resolveCliLaunchError(
requestedMode,
legacyConfigForMode(requestedMode, body as unknown as Record<string, unknown>)
);
if (cliLaunchError) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, cliLaunchError);
}
}
@@ -1000,25 +1038,25 @@ export function registerSessionRoutes(
const globalNice = await ctx.getGlobalNiceConfig();
const modelConfig = await ctx.getModelConfig();
const mode = body.mode || 'claude';
// Where a model override comes from is a capability, and the three answers are
// genuinely different mechanisms:
// 'flag' — the CLI takes --model, so read the value the caller sent
// in that CLI's own config object.
// 'claude-settings-file' — claude alone, whose model is written to
// <case>/.claude/settings.local.json rather than passed as
// a flag, so the app-wide default applies here.
// 'none' — shell has no model; deepseek's is a composition entry in
// the profile's config tree, not a session field
// (docs/deepseek-integration.md). Both get nothing.
const modelSource = getCli(mode)?.capabilities.model;
const model =
mode === 'opencode'
? body.openCodeConfig?.model
: mode === 'codex'
? body.codexConfig?.model
: mode === 'gemini'
? body.geminiConfig?.model
: mode === 'antigravity'
? body.antigravityConfig?.model
: mode === 'pi'
? body.piConfig?.model
: mode === 'grok'
? body.grokConfig?.model
: // DeepSeek's model is a composition entry in the profile's config
// tree, not a session flag, so there is deliberately nothing to
// read here (see docs/deepseek-integration.md).
mode !== 'shell' && mode !== 'deepseek'
? modelConfig?.defaultModel || undefined
: undefined;
modelSource?.source === 'flag'
? (legacyConfigForMode(mode, body as unknown as Record<string, unknown>)?.[modelSource.param ?? 'model'] as
| string
| undefined)
: modelSource?.source === 'claude-settings-file'
? modelConfig?.defaultModel || undefined
: undefined;
const claudeModeConfig = await ctx.getClaudeModeConfig();
// Section 6.3: force non-granted users to a classifier-guarded mode.
const effectiveClaudeMode = await resolveClaudeModeForUsername(claudeModeConfig.claudeMode, owner);
@@ -1030,7 +1068,7 @@ export function registerSessionRoutes(
piConfig: gatedPiConfig,
grokConfig: gatedGrokConfig,
deepSeekConfig: gatedDeepSeekConfig,
} = await clampExternalCliBypassForOwner(
} = await _clampExternalCliBypassForOwner(
owner,
body.codexConfig,
body.geminiConfig,
@@ -1057,6 +1095,7 @@ export function registerSessionRoutes(
piConfig: mode === 'pi' ? gatedPiConfig : undefined,
grokConfig: mode === 'grok' ? gatedGrokConfig : undefined,
deepSeekConfig: mode === 'deepseek' ? gatedDeepSeekConfig : undefined,
ompConfig: resolveOmpConfigForCreate(mode, workingDir, body.ompConfig),
resumeSessionId: validatedResumeId,
envOverrides: await clampEnvOverridesForOwner(owner, body.envOverrides),
effort: body.effort,
@@ -1072,7 +1111,7 @@ export function registerSessionRoutes(
await ctx.setupSessionListeners(session);
// Pre-seed the agent skill's preamble cache so its §0 bootstrap is a two-line
// loader (see seedAgentSessionPreamble). Local claude sessions only; best-effort.
if (mode === 'claude' && !remote && (await ctx.getAgentSkillEnabled())) {
if (getCli(mode)?.capabilities.agentSkillInjection && !remote && (await ctx.getAgentSkillEnabled())) {
await seedAgentSessionPreamble(session.id).catch((err: unknown) =>
console.warn(`[agent-skill] preamble seed failed for ${session.id}: ${getErrorMessage(err)}`)
);
@@ -1125,9 +1164,26 @@ export function registerSessionRoutes(
const query = req.query as { killMux?: string };
const killMux = query.killMux !== 'false'; // Default to true
// Security: owner-scoped lookup 404s foreign/missing sessions uniformly (no existence leak, no cross-user kill).
const session = findSessionOrFail(ctx, id, req);
// A resumed/detached-but-never-live row (e.g. a non-claude "Resume" that
// relaunched into a NEW session and wants to retire the old one it can no
// longer reattach to) has no entry in ctx.sessions at all — only in
// persisted state. Fall back to removing that persisted record directly
// rather than 404ing: the caller means "make this row go away", and a
// stale duplicate row is exactly what's left behind otherwise. Pinned
// sessions keep their existing demote-not-delete protection.
if (!ctx.sessions.has(id)) {
// Called for its existence/ownership 404 side effect only — demoteOrRemoveSession
// below re-looks-up the record by id, so the returned SessionState is unused here.
findPersistedSessionOrFail(ctx.store, id, req);
ctx.store.demoteOrRemoveSession(id);
// Mirrors the broadcast at the tail of the live-session cleanup path
// (_doCleanupSession in server.ts) — without it, other open tabs keep
// showing the retired row until their next unrelated fetch.
ctx.broadcast(SseEvent.SessionDeleted, { id });
return {};
}
const session = findSessionOrFail(ctx, id, req);
await ctx.cleanupSession(session.id, killMux, 'user_delete');
return {};
});
@@ -1277,19 +1333,21 @@ export function registerSessionRoutes(
}
try {
// Auto-detect completion phrase from CLAUDE.md BEFORE starting (only if globally enabled and not explicitly disabled by user)
// Ralph tracker is not supported for opencode / codex / gemini / antigravity / pi sessions.
// Keep this list in step with isExternalCliMode(): _processExpensiveParsers() returns early
// for those modes, so a tracker enabled here would never be fed, and the session would
// still report ralphEnabled + Ralph UI state that no other external CLI shows.
// Auto-detect completion phrase from CLAUDE.md BEFORE starting (only if globally
// enabled and not explicitly disabled by user).
//
// `isExternalCliMode()` is what the eight-mode `!==` chain this replaces was FOR: its
// own comment asked the next person to keep the list in step with that predicate by
// hand. Calling it instead is byte-identical today (claude and shell are the two
// non-external modes, exactly what the chain admitted) and cannot drift.
//
// ⚠️ Deliberately NOT `capabilities.ralph`, which the quick-start path below reads:
// that capability is claude-only, so using it here would stop auto-enabling Ralph for
// SHELL sessions, which this path has always done. The two paths genuinely disagree
// about shell, and they disagree upstream too — reconciling them is a behaviour change
// and belongs in its own PR, not in a refactor that is meant to change nothing.
if (
session.mode !== 'opencode' &&
session.mode !== 'codex' &&
session.mode !== 'gemini' &&
session.mode !== 'antigravity' &&
session.mode !== 'pi' &&
session.mode !== 'grok' &&
session.mode !== 'deepseek' &&
!isExternalCliMode(session.mode) &&
ctx.store.getConfig().ralphEnabled &&
!session.ralphTracker.autoEnableDisabled
) {
@@ -2028,7 +2086,7 @@ export function registerSessionRoutes(
// Codex sessions don't write to ~/.claude/projects — their transcripts
// live in ~/.codex/sessions/**. Branch to a Codex-specific reader so the
// response-viewer works for Codex panes too.
if (session.mode === 'codex') {
if (getCli(session.mode)?.capabilities.transcript === 'codex-rollout') {
const codexQuery = req.query as { context?: string };
return await readCodexLastResponse(session, codexQuery.context === 'full');
}
@@ -2048,7 +2106,7 @@ export function registerSessionRoutes(
// and return "nothing said yet" forever — an agent polling that worker
// would starve on an answer that exists. Those configurations keep the
// pane segmenter below: coarse, but the real conversation.
if (session.mode === 'deepseek' && !session.docker && !session.remote) {
if (getCli(session.mode)?.capabilities.transcript === 'deepseek-zstd' && !session.docker && !session.remote) {
const deepSeekQuery = req.query as { context?: string };
const full = deepSeekQuery.context === 'full';
const transcript = await readDeepSeekLastResponse(session, { blocks: full });
@@ -2191,7 +2249,7 @@ export function registerSessionRoutes(
const WINDOW_MS = 15_000;
const otherSubmits: number[] = [];
for (const s of ctx.sessions.values()) {
if (s.id !== session.id && s.mode === 'codex' && s.lastSubmitAt) {
if (s.id !== session.id && getCli(s.mode)?.capabilities.transcript === 'codex-rollout' && s.lastSubmitAt) {
otherSubmits.push(s.lastSubmitAt);
}
}
@@ -2536,7 +2594,8 @@ export function registerSessionRoutes(
// During long thinking phases, Ink rewrites the same rows thousands of times
// (500KB+). Without stripping, tail mode returns only spinner frames and
// the terminal appears empty when switching tabs.
let strippedBuffer = session.mode === 'shell' ? rawBuffer : stripInkRedrawBloat(rawBuffer);
let strippedBuffer =
getCli(session.mode)?.capabilities.stripInkBloat === false ? rawBuffer : stripInkRedrawBloat(rawBuffer);
// Strip alt-screen toggles and scrollback-erase from Codex/Claude byte
// streams. xterm.js obeys them by switching to its scrollback-less alt
@@ -2858,6 +2917,7 @@ export function registerSessionRoutes(
piConfig,
grokConfig,
deepSeekConfig,
ompConfig,
envOverrides,
effort,
parentSessionId,
@@ -2865,7 +2925,7 @@ export function registerSessionRoutes(
// Multi-user: shell mode is arbitrary host-account execution, gated by the grant.
// Resolve the owner's grant from the store so a GRANTED regular user is not wrongly denied.
if (mode === 'shell' && !(await canUsernameRunPrivilegedCommands(owner))) {
if (getCli(mode)?.capabilities.privilegedCommandGate && !(await canUsernameRunPrivilegedCommands(owner))) {
return createErrorResponse(ApiErrorCode.FORBIDDEN, 'Shell sessions require the can-bypass-permissions grant');
}
@@ -2908,6 +2968,7 @@ export function registerSessionRoutes(
piConfig ||
grokConfig ||
deepSeekConfig ||
ompConfig ||
openCodeConfig
) {
return createErrorResponse(
@@ -2942,6 +3003,7 @@ export function registerSessionRoutes(
piConfig ||
grokConfig ||
deepSeekConfig ||
ompConfig ||
openCodeConfig
) {
return createErrorResponse(
@@ -2971,7 +3033,9 @@ export function registerSessionRoutes(
// The probe already exec'd into the container; carry its facts onto the
// live session so the launch chain does not have to re-ask.
sessionDocker.runsAsRoot = probe.runsAsRoot;
if (mode !== 'shell' && !probe.availableModes?.includes(mode)) {
// No `mode !== 'shell'` arm: a mode with no binary of its own is reported
// available by the probe unconditionally, so this reads the same answer for it.
if (!probe.availableModes?.includes(mode)) {
return createErrorResponse(
ApiErrorCode.OPERATION_FAILED,
`"${mode}" is not installed in container "${sessionDocker.containerName}". Adoption never modifies the container — install it inside, or pick another mode.`
@@ -3016,69 +3080,35 @@ export function registerSessionRoutes(
casePath = dockerCase.hostWorkspacePath; // a REAL host dir (bind-mounted into the container)
docker = sessionDocker;
// Seed resume so a relaunch resumes the case's last conversation from the
// bind-mounted transcript (decision: resume-on-start default ON).
if (sessionDocker.resumeOnStart && dockerCase.lastClaudeSessionId) {
// Seed only Claude's resume id. Codex, Gemini, and the other CLIs have
// separate conversation stores and must never receive a Claude UUID.
if (mode === 'claude' && sessionDocker.resumeOnStart && dockerCase.lastClaudeSessionId) {
dockerResumeId = dockerCase.lastClaudeSessionId;
}
} else {
// Check OpenCode availability if requested. Error text comes from the
// resolver so it carries the resolution diagnostics; same for the modes below.
if (mode === 'opencode') {
const { isOpenCodeAvailable, getOpenCodeNotFoundMessage } =
await import('../../utils/opencode-cli-resolver.js');
if (!isOpenCodeAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getOpenCodeNotFoundMessage());
// Same pre-flight as POST /api/sessions: refuse before spawning a pane that would die
// on `command not found`, with the resolver's own diagnostics, and a launcher CLI's
// more specific reason (dsh: binary vs no pane-capable profile vs the profile the
// caller named). External CLIs only — claude and shell fall through to tmux-manager's
// own not-found throw, exactly as before.
if (getCli(mode)?.capabilities.external) {
const qsLaunchError = await resolveCliLaunchError(
mode,
legacyConfigForMode(mode, {
openCodeConfig,
codexConfig,
geminiConfig,
antigravityConfig,
piConfig,
grokConfig,
deepSeekConfig,
} as unknown as Record<string, unknown>)
);
if (qsLaunchError) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, qsLaunchError);
}
}
// Check Codex availability if requested
if (mode === 'codex') {
const { isCodexAvailable, getCodexNotFoundMessage } = await import('../../utils/codex-cli-resolver.js');
if (!isCodexAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getCodexNotFoundMessage());
}
}
// Check Gemini availability if requested
if (mode === 'gemini') {
const { isGeminiAvailable, getGeminiNotFoundMessage } = await import('../../utils/gemini-cli-resolver.js');
if (!isGeminiAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getGeminiNotFoundMessage());
}
}
// Check Antigravity availability if requested
if (mode === 'antigravity') {
const { isAntigravityAvailable, getAntigravityNotFoundMessage } =
await import('../../utils/antigravity-cli-resolver.js');
if (!isAntigravityAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getAntigravityNotFoundMessage());
}
}
// Check Pi availability if requested
if (mode === 'pi') {
const { isPiAvailable, getPiNotFoundMessage } = await import('../../utils/pi-cli-resolver.js');
if (!isPiAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getPiNotFoundMessage());
}
}
// Check Grok availability if requested
if (mode === 'grok') {
const { isGrokAvailable, getGrokNotFoundMessage } = await import('../../utils/grok-cli-resolver.js');
if (!isGrokAvailable()) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, getGrokNotFoundMessage());
}
}
// Check DeepSeek Harness availability if requested (binary AND a pane-capable profile).
if (mode === 'deepseek') {
const err = await resolveDeepSeekLaunchError(deepSeekConfig?.profile);
if (err) return createErrorResponse(ApiErrorCode.OPERATION_FAILED, err);
}
// Resolve case path: check linked-cases registry first, then fall back to CASES_DIR.
// This mirrors the behaviour of resolveCasePath() in case-routes so that linked
// external project directories are honoured by quick-start just like regular case routes.
@@ -3125,14 +3155,15 @@ export function registerSessionRoutes(
writeFileSync(join(resolvedCasePath, 'CLAUDE.md'), claudeMd);
// Write .claude/settings.local.json with hooks for desktop notifications
// (Claude-specific — OpenCode, Codex, Gemini, Antigravity, Pi and Grok use their own systems)
// (Claude-specific — OpenCode, Codex, Gemini, Antigravity, Pi, Grok, DeepSeek and OMP use their own systems)
if (
mode !== 'opencode' &&
mode !== 'codex' &&
mode !== 'gemini' &&
mode !== 'antigravity' &&
mode !== 'pi' &&
mode !== 'grok'
mode !== 'grok' &&
mode !== 'omp'
) {
await writeHooksConfig(resolvedCasePath);
}
@@ -3148,7 +3179,7 @@ export function registerSessionRoutes(
// reads `.claude` hooks, so a shell/codex quick-start should not author a block
// of its own. Skipped for remote cases — resolvedCasePath is a REMOTE path that
// doesn't exist on the local filesystem.
if (mode === 'claude') {
if (getCli(mode)?.capabilities.hooks === 'always') {
await applyWorkspaceHooks(resolvedCasePath, await ctx.getWorkspaceHooksEnabled());
} else {
await refreshStaleCodemanHooks(resolvedCasePath).catch(() => {});
@@ -3160,7 +3191,7 @@ export function registerSessionRoutes(
// (`.claude/skills/` is a Claude Code surface); skipped for remote cases, whose
// casePath lives on another host. Docker cases qualify: hostWorkspacePath is a
// real host dir and the skill crosses the bind mount like the rest of `.claude/`.
if (!remote && mode === 'claude' && (await ctx.getAgentSkillEnabled())) {
if (!remote && getCli(mode)?.capabilities.agentSkillInjection && (await ctx.getAgentSkillEnabled())) {
await injectAgentSkill(resolvedCasePath);
}
@@ -3171,7 +3202,7 @@ export function registerSessionRoutes(
// shell or external-CLI quick-start must not author a block of its own (the same
// rule the existing-case branch above states; this branch used to exclude just
// the five external CLIs and let `shell` through).
if (docker && docker.hooksEnabled && mode === 'claude') {
if (docker && docker.hooksEnabled && getCli(mode)?.capabilities.hooks === 'always') {
try {
if (!existsSync(join(resolvedCasePath, 'CLAUDE.md'))) {
const templatePath = await ctx.getDefaultClaudeMdPath();
@@ -3193,24 +3224,14 @@ export function registerSessionRoutes(
// Model override → <case>/.claude/settings.local.json (claude-mode; local AND
// docker — the docker workspace is a real host dir, so the settings file crosses
// the bind mount and the in-container claude reads it). Remote was rejected above.
if (mode === 'claude' && modelOverride !== undefined) {
if (getCli(mode)?.capabilities.model.source === 'claude-settings-file' && modelOverride !== undefined) {
await updateCaseModel(resolvedCasePath, modelOverride || null);
}
// Strip stale disk entries for keys this request is actively setting (Claude only —
// see POST /api/sessions for full rationale).
if (
mode !== 'opencode' &&
mode !== 'codex' &&
mode !== 'gemini' &&
mode !== 'antigravity' &&
mode !== 'pi' &&
mode !== 'grok' &&
mode !== 'deepseek' &&
!remote &&
envOverrides &&
Object.keys(envOverrides).length > 0
) {
// Same chain, same replacement as the create path above: byte-identical, drift-proof.
if (!isExternalCliMode(mode) && !remote && envOverrides && Object.keys(envOverrides).length > 0) {
await stripCaseEnvKeys(resolvedCasePath, Object.keys(envOverrides));
}
@@ -3218,23 +3239,22 @@ export function registerSessionRoutes(
// Apply global Nice priority config and model config from settings
const niceConfig = await ctx.getGlobalNiceConfig();
const qsModelConfig = await ctx.getModelConfig();
// See the create path for why this is a capability rather than a mode ladder.
const qsModelSource = getCli(mode)?.capabilities.model;
const qsModel =
mode === 'opencode'
? openCodeConfig?.model
: mode === 'codex'
? codexConfig?.model
: mode === 'gemini'
? geminiConfig?.model
: mode === 'antigravity'
? antigravityConfig?.model
: mode === 'pi'
? piConfig?.model
: mode === 'grok'
? grokConfig?.model
: // DeepSeek's model lives in the profile's config tree, not here.
mode !== 'shell' && mode !== 'deepseek'
? qsModelConfig?.defaultModel || undefined
: undefined;
qsModelSource?.source === 'flag'
? (legacyConfigForMode(mode, {
openCodeConfig,
codexConfig,
geminiConfig,
antigravityConfig,
piConfig,
grokConfig,
deepSeekConfig,
} as unknown as Record<string, unknown>)?.[qsModelSource.param ?? 'model'] as string | undefined)
: qsModelSource?.source === 'claude-settings-file'
? qsModelConfig?.defaultModel || undefined
: undefined;
const qsClaudeModeConfig = await ctx.getClaudeModeConfig();
const qsEffectiveClaudeMode = await resolveClaudeModeForUsername(qsClaudeModeConfig.claudeMode, owner);
// Section 6.3: clamp Codex/Gemini/Antigravity bypass switches for a non-granted owner (no-op single-user/granted).
@@ -3245,7 +3265,7 @@ export function registerSessionRoutes(
piConfig: qsGatedPiConfig,
grokConfig: qsGatedGrokConfig,
deepSeekConfig: qsGatedDeepSeekConfig,
} = await clampExternalCliBypassForOwner(
} = await _clampExternalCliBypassForOwner(
owner,
codexConfig,
geminiConfig,
@@ -3274,6 +3294,7 @@ export function registerSessionRoutes(
piConfig: mode === 'pi' ? qsGatedPiConfig : undefined,
grokConfig: mode === 'grok' ? qsGatedGrokConfig : undefined,
deepSeekConfig: mode === 'deepseek' ? qsGatedDeepSeekConfig : undefined,
ompConfig: resolveOmpConfigForCreate(mode, resolvedCasePath, ompConfig),
envOverrides: qsGatedEnvOverrides,
effort,
remote,
@@ -3285,7 +3306,7 @@ export function registerSessionRoutes(
// Auto-detect completion phrase from CLAUDE.md BEFORE broadcasting
// so the initial state already has the phrase configured (only if globally enabled)
if (mode === 'claude' && !remote && !docker && ctx.store.getConfig().ralphEnabled) {
if (getCli(mode)?.capabilities.ralph && !remote && !docker && ctx.store.getConfig().ralphEnabled) {
autoConfigureRalph(session, resolvedCasePath, ctx);
if (!session.ralphTracker.enabled) {
session.ralphTracker.enable();
@@ -3299,7 +3320,7 @@ export function registerSessionRoutes(
await ctx.setupSessionListeners(session);
// Pre-seed the agent skill's preamble cache so its §0 bootstrap is a two-line
// loader (see seedAgentSessionPreamble). Local claude sessions only; best-effort.
if (mode === 'claude' && !remote && !docker && (await ctx.getAgentSkillEnabled())) {
if (getCli(mode)?.capabilities.agentSkillInjection && !remote && !docker && (await ctx.getAgentSkillEnabled())) {
await seedAgentSessionPreamble(session.id).catch((err: unknown) =>
console.warn(`[agent-skill] preamble seed failed for ${session.id}: ${getErrorMessage(err)}`)
);
@@ -3314,7 +3335,7 @@ export function registerSessionRoutes(
// Start in the appropriate mode
try {
if (mode === 'shell') {
if (getCli(mode)?.capabilities.startMode === 'shell') {
await session.startShell();
getLifecycleLog().log({
event: 'started',
@@ -4122,6 +4143,24 @@ export function registerSessionRoutes(
// Projects dir may not exist.
}
// OMP's own session files (~/.omp/agent/sessions) — the non-claude twin
// of the scan above; see omp-transcript.ts for why this exists at all.
try {
for (const h of scanOmpSessionsHistory()) {
history.push({
sessionId: h.sessionId,
workingDir: h.workingDir,
sizeBytes: h.sizeBytes,
lastModified: h.lastModified,
firstPrompt: h.firstPrompt,
lastPrompt: h.lastPrompt,
mode: 'omp',
});
}
} catch {
// Best-effort, same as the claude scan above.
}
// Mux process stats (best-effort; guard against mocks lacking the method).
let mux: MuxStatInput[] = [];
try {
+24 -3
View File
@@ -5,6 +5,7 @@
*/
import { FastifyInstance } from 'fastify';
import { getCli } from '../../config/cli-registry/registry.js';
import { join, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { existsSync, mkdirSync, readdirSync } from 'node:fs';
@@ -389,6 +390,9 @@ export function registerSystemRoutes(
'in-flight': { http: 409, api: ApiErrorCode.ALREADY_EXISTS },
'up-to-date': { http: 409, api: ApiErrorCode.ALREADY_EXISTS },
'not-git': { http: 400, api: ApiErrorCode.INVALID_INPUT },
// A container release that changes the ENVIRONMENT: not a client error to
// retry, it needs a host-side rebuild (docs/docker-self-update.md).
'env-blocked': { http: 409, api: ApiErrorCode.INVALID_INPUT },
disabled: { http: 403, api: ApiErrorCode.INVALID_INPUT },
'bad-tag': { http: 400, api: ApiErrorCode.INVALID_INPUT },
error: { http: 500, api: ApiErrorCode.INTERNAL_ERROR },
@@ -614,8 +618,13 @@ export function registerSystemRoutes(
// same negative-pid signal as runGit() in git-clone.ts, which is the
// synchronous-spawn precedent this endpoint is modelled on.
detached: true,
// dsh bundles its own package manager, so no system pnpm is required —
// but it still needs a HOME to resolve $DSH_HOME against.
// Inherit the environment: this needs a HOME to resolve $DSH_HOME
// against, and a PATH carrying `pnpm`. ⚠️ `dsh plugin` does NOT bundle a
// package manager — it `spawnSync`s a literal `pnpm` with no npm
// fallback, so on a host without one this exits 127 and dsh's own
// stderr ("pnpm not found on PATH") is what reaches the caller through
// the OPERATION_FAILED detail below. That is the same missing
// dependency that broke the docker agent image in issue #352.
env: process.env,
});
} catch (err) {
@@ -694,6 +703,17 @@ export function registerSystemRoutes(
};
});
// ========== OMP ==========
app.get('/api/omp/status', async () => {
const { isOmpAvailable, resolveOmpDir, getOmpCliVersion } = await import('../../utils/omp-cli-resolver.js');
return {
available: isOmpAvailable(),
path: resolveOmpDir(),
version: getOmpCliVersion(),
};
});
// ═══════════════════════════════════════════════════════════════
// State & Lifecycle (cleanup, lifecycle log, stats)
// ═══════════════════════════════════════════════════════════════
@@ -1024,7 +1044,8 @@ export function registerSystemRoutes(
if (statusLineTelemetry === true) {
const dirs = new Set<string>();
for (const session of ctx.sessions.values()) {
if (session.mode === 'claude' && session.workingDir) dirs.add(session.workingDir);
if (getCli(session.mode)?.capabilities.statusLineTelemetry && session.workingDir)
dirs.add(session.workingDir);
}
await Promise.all([...dirs].map((dir) => applyStatusLineConfig(dir, true).catch(() => {})));
}
+48 -15
View File
@@ -33,7 +33,8 @@ import { randomUUID } from 'node:crypto';
import { Readable } from 'node:stream';
import type { FastifyInstance, FastifyReply, FastifyRequest } from 'fastify';
import { WebSocket as WsClient } from 'ws';
import type { WebSocket } from 'ws';
import type { ClientOptions as WsClientOptions, WebSocket } from 'ws';
import type { Response as UndiciResponse } from 'undici';
import { getDataDir } from '../../config/instance.js';
import {
MAX_LIVE_WEBVIEW_FRAMES,
@@ -47,6 +48,8 @@ import {
} from '../../config/webview-limits.js';
import { readWebviews, writeWebviews } from '../../webview-store.js';
import { webviewCapabilities } from '../../webview-capabilities.js';
import { egressBlockedReason, webviewEgressLookup, webviewFetch, type EgressLookup } from '../webview-egress.js';
import { blockedWebviewHostReason } from '../webview-egress-policy.js';
import { ApiErrorCode, createErrorResponse } from '../../types.js';
import type { Webview, WebviewOpenData, WebviewProbe } from '../../types.js';
import { AUTH_COOKIE_NAME } from '../middleware/auth.js';
@@ -293,7 +296,7 @@ async function probeUrl(url: string): Promise<WebviewProbe> {
}
try {
const response = await fetch(target.href, {
const response = await webviewFetch(target, {
method: 'GET',
redirect: 'manual',
signal: AbortSignal.timeout(WEBVIEW_PROBE_TIMEOUT_MS),
@@ -326,6 +329,12 @@ async function probeUrl(url: string): Promise<WebviewProbe> {
reason,
};
} catch (err) {
const blocked = egressBlockedReason(err);
if (blocked) {
// Refused by policy, not unreachable: say so, or the user reads it as a
// network problem and starts debugging their firewall.
return { reachable: false, framable: false, recommendedMode: 'proxy', reason: blocked };
}
const message = err instanceof Error ? err.message : String(err);
return {
reachable: false,
@@ -476,19 +485,19 @@ async function proxyRequest(
// string (it can carry the dashboard's tokens).
const logTarget = `${req.method} ${upstream.origin}${upstream.pathname}`;
let response: Response;
let response: UndiciResponse;
try {
response = await fetch(upstream.href, {
response = await webviewFetch(upstream, {
method: req.method,
headers,
body: hasBody ? (req.body as Readable) : undefined,
// Required by undici whenever the body is a stream.
...(hasBody ? { duplex: 'half' } : {}),
...(hasBody ? { duplex: 'half' as const } : {}),
// Redirects are rewritten into the proxy prefix instead of followed, so the
// browser's URL stays inside the frame and relative assets keep resolving.
redirect: 'manual',
signal: abort.signal,
} as RequestInit);
});
} catch (err) {
const elapsed = Date.now() - startedAt;
if (clientGone) {
@@ -496,6 +505,13 @@ async function proxyRequest(
// failure, so no warn (it would read as the dashboard being broken).
return reply;
}
const blocked = egressBlockedReason(err);
if (blocked) {
// Policy refusal, distinct from "unreachable": a record saved before the
// egress rule existed, or a name that now resolves into a blocked range.
console.warn(`[Webview] refused by egress policy: ${logTarget} (webview "${webview.name}"): ${blocked}`);
return reply.code(403).type('text/plain').send(`Forbidden: ${blocked}`);
}
if (headerTimedOut) {
console.warn(
`[Webview] upstream sent no response headers within ${WEBVIEW_UPSTREAM_TIMEOUT_MS}ms: ` +
@@ -644,6 +660,13 @@ function proxyWebSocket(socket: WebSocket, req: FastifyRequest<{ Params: ProxyPa
return;
}
// An IP literal never reaches the lookup hook (net.connect skips DNS for it),
// so the literal form is judged here and the resolved form in the lookup.
if (blockedWebviewHostReason(upstream.hostname)) {
socket.close(4003, 'Forbidden');
return;
}
socketCounts.set(webview.id, live + 1);
let released = false;
const release = () => {
@@ -655,16 +678,21 @@ function proxyWebSocket(socket: WebSocket, req: FastifyRequest<{ Params: ProxyPa
};
const protocols = req.headers['sec-websocket-protocol'];
// `lookup` is absent from ws's ClientOptions typings but flows through
// http.request to net.connect untouched, which is where the resolved
// address is judged (see webview-egress.ts).
const upstreamOptions: WsClientOptions & { lookup: EgressLookup } = {
headers: {
origin: upstream.origin,
...(webview.trusted && req.headers.cookie ? { cookie: String(req.headers.cookie) } : {}),
},
handshakeTimeout: WEBVIEW_WS_HANDSHAKE_TIMEOUT_MS,
lookup: webviewEgressLookup,
};
const upstreamSocket = new WsClient(
upstreamWebSocketUrl(upstream),
protocols ? String(protocols).split(/,\s*/) : [],
{
headers: {
origin: upstream.origin,
...(webview.trusted && req.headers.cookie ? { cookie: String(req.headers.cookie) } : {}),
},
handshakeTimeout: WEBVIEW_WS_HANDSHAKE_TIMEOUT_MS,
}
upstreamOptions
);
// Buffer anything the browser sends before the upstream handshake completes,
@@ -703,9 +731,14 @@ function proxyWebSocket(socket: WebSocket, req: FastifyRequest<{ Params: ProxyPa
socket.on('close', (code: number, reason: Buffer) => closeBoth(code, reason?.toString()));
upstreamSocket.on('close', (code: number, reason: Buffer) => closeBoth(code, reason?.toString()));
socket.on('error', () => closeBoth());
upstreamSocket.on('error', () => {
upstreamSocket.on('error', (err: Error) => {
release();
if (socket.readyState === socket.OPEN) socket.close(1011, 'Upstream error');
if (socket.readyState !== socket.OPEN) return;
// A name that resolved into a blocked range fails inside the connect, so it
// surfaces here rather than at the sync check above; report it as the same
// policy refusal, not as the dashboard being broken.
if (egressBlockedReason(err)) socket.close(4003, 'Forbidden');
else socket.close(1011, 'Upstream error');
});
})();
}
+119 -35
View File
@@ -10,6 +10,7 @@
import { z } from 'zod';
import { SAFE_PATH_PATTERN, isSafePushEndpoint } from '../utils/index.js';
import { isValidWebviewUrl } from './webview-proxy.js';
import { isBlockedWebviewUrl } from './webview-egress-policy.js';
import {
MAX_TERMINAL_BUFFER_BYTES,
MAX_TERMINAL_SCROLLBACK_LINES,
@@ -18,6 +19,8 @@ import {
} from '../config/terminal-history.js';
import { MAX_EDITABLE_BYTES } from '../config/file-editing.js';
import { MIN_MATCH_LENGTH, MAX_MATCH_LENGTH } from '../config/agent-wait.js';
import { enabledCliIds, enabledClis } from '../config/cli-registry/registry.js';
import type { SessionMode } from '../types.js';
// ========== Path Validation ==========
@@ -119,37 +122,84 @@ export const FileWriteSchema = z
})
.strict();
// ========== Env Var Allowlist ==========
/** Allowlisted env var key prefixes */
const ALLOWED_ENV_PREFIXES = [
'CLAUDE_CODE_',
'OPENCODE_',
'CODEX_',
'GEMINI_',
'GOOGLE_',
'ANTIGRAVITY_',
'PI_',
'GROK_',
'XAI_',
// DeepSeek Harness: `DSH_*` carries the launcher's own documented inputs
// (DSH_HOME, DSH_PERMISSION_MODE, DSH_TELEMETRY_MODE, and the DSH_TUI_* knobs
// the terminal front door reads); `DEEPSEEK_*` is the vendor namespace holding
// DEEPSEEK_API_KEY / DEEPSEEK_BASE_URL, the same narrow-vendor reasoning that
// admitted XAI_* for grok. Foreign provider keys stay out: a dsh settings.yaml
// can name ANY env var as a provider credential (apiKeyEnv), which is pi's
// 34-provider-key problem in a new shape, and the answer is the same one.
'DSH_',
'DEEPSEEK_',
];
/**
* The run-mode ids the API currently accepts: every ENABLED registry entry.
*
* Exported so anything needing the authoritative list derives it from here rather than
* restating the nine names (which is how the old literal enum drifted from the run menu).
*/
export function sessionModeIds(): string[] {
return enabledCliIds();
}
/**
* Allowlisted exact env var keys (checked alongside the prefixes).
* CLAUDE_CONFIG_DIR relocates the Claude CLI's user config (credentials,
* settings, stats) so a case can run on a separate Claude subscription (#255).
* Exact match only — CLAUDE_CONFIG_DIR_EXTRA etc. stay rejected.
* Validation for a run mode, resolved AT PARSE TIME.
*
* ⚠️ Deliberately not a `z.enum([...])`. An enum has to be handed its members when the
* SCHEMA OBJECT is built, which happens once at module import — so a CLI enabled while the
* server was running kept failing validation with INVALID_INPUT until a restart, even
* though the run menu already offered it. Checking membership inside the refinement moves
* the question to when the request is actually validated.
*
* The cast is because callers type this field as `SessionMode`; the runtime check above is
* what actually constrains it.
*/
const ALLOWED_ENV_KEYS = new Set(['CLAUDE_CONFIG_DIR']);
function sessionModeSchema(): z.ZodType<SessionMode> {
return (
z
.string()
// Bounded BEFORE the membership check, and before the failure message quotes the value
// back. `.max(24)` matches the `cliId` pattern in cli-registry/schema.ts — no id longer
// than that can ever be registered, so nothing legitimate is rejected — and it means a
// rejected mode cannot echo a body-limit-sized string into an error string and a log
// line. Without it the only bound on either was the HTTP body limit.
.max(24)
.superRefine((value, ctx) => {
const allowed = sessionModeIds();
if (!allowed.includes(value)) {
ctx.addIssue({
code: 'custom',
message: `Invalid run mode ${JSON.stringify(value)}. Enabled modes: ${allowed.join(', ')}`,
});
}
}) as unknown as z.ZodType<SessionMode>
);
}
// ========== Env Var Allowlist ==========
/**
* Allowlisted env var key prefixes, contributed by the ENABLED CLIs in the registry
* (`env.allowedPrefixes`) — `CLAUDE_CODE_`, `OPENCODE_`, `CODEX_`, `GEMINI_`, `GOOGLE_`,
* `ANTIGRAVITY_`, `PI_`, `GROK_`, `XAI_`, `DSH_`, `DEEPSEEK_` as shipped.
*
* ⚠️ Resolved AT PARSE TIME, not at module load. This used to be a frozen array computed
* once when the module was imported, which meant a CLI enabled while the server was running
* had its env prefix rejected until a restart — validation and the run menu disagreeing
* about which CLIs exist. Reading the registry per call costs a memoized array lookup.
*
* ⚠️ This is ONE GLOBAL LIST applied with no mode context, so admitting a prefix for one CLI
* widens it for every mode at once. That is why an entry only ever contributes its own
* VENDOR namespace: pi's ~34 provider keys (ANTHROPIC_API_KEY, OPENAI_API_KEY, HF_TOKEN, …)
* share no prefix and stay out, and a dsh `settings.yaml` can nominate ANY env var as a
* provider credential — same problem, same answer. Those CLIs authenticate via their own
* `/login` or the server process's own environment.
*/
function allowedEnvPrefixes(): string[] {
return enabledClis().flatMap((entry) => entry.env.allowedPrefixes);
}
/**
* Allowlisted exact env var keys (checked alongside the prefixes), likewise contributed by
* enabled registry entries via `env.allowedKeys`.
*
* As shipped this is claude's CLAUDE_CONFIG_DIR, which relocates the Claude CLI's user
* config (credentials, settings, stats) so a case can run on a separate Claude subscription
* (#255). Exact match only — CLAUDE_CONFIG_DIR_EXTRA etc. stay rejected.
*/
function allowedEnvKeys(): Set<string> {
return new Set(enabledClis().flatMap((entry) => entry.env.allowedKeys));
}
/** Env var keys that are always blocked (security-sensitive) */
const BLOCKED_ENV_KEYS = new Set([
@@ -162,11 +212,17 @@ const BLOCKED_ENV_KEYS = new Set([
'OPENCODE_SERVER_PASSWORD', // Security-sensitive: server auth password
]);
/** Validate that an env var key is allowed */
/**
* Validate that an env var key is allowed.
*
* ⚠️ `BLOCKED_ENV_KEYS` is checked FIRST and is deliberately NOT registry-driven. It is a
* hard floor: a rogue or fat-fingered `allowedPrefixes` entry (say `''`, which prefixes
* everything) still cannot unblock PATH or LD_PRELOAD.
*/
function isAllowedEnvKey(key: string): boolean {
if (BLOCKED_ENV_KEYS.has(key)) return false;
if (ALLOWED_ENV_KEYS.has(key)) return true;
return ALLOWED_ENV_PREFIXES.some((prefix) => key.startsWith(prefix));
if (allowedEnvKeys().has(key)) return true;
return allowedEnvPrefixes().some((prefix) => key.startsWith(prefix));
}
/** Zod schema for env overrides with allowlist enforcement */
@@ -180,7 +236,7 @@ const safeEnvOverridesSchema = z
},
{
message:
'envOverrides contains blocked or disallowed env var keys. Only CLAUDE_CODE_*, OPENCODE_*, CODEX_*, GEMINI_*, GOOGLE_*, ANTIGRAVITY_*, PI_*, GROK_*, XAI_*, DSH_*, DEEPSEEK_* keys and CLAUDE_CONFIG_DIR are allowed.',
'envOverrides contains blocked or disallowed env var keys. Only CLAUDE_CODE_*, OPENCODE_*, CODEX_*, GEMINI_*, GOOGLE_*, ANTIGRAVITY_*, PI_*, GROK_*, XAI_*, DSH_*, DEEPSEEK_*, OMP_* keys and CLAUDE_CONFIG_DIR are allowed.',
}
);
@@ -345,6 +401,25 @@ const GrokConfigSchema = z
})
.optional();
/**
* Schema for OMP CLI-specific configuration.
*/
const OmpConfigSchema = z
.object({
model: z
.string()
.max(100)
.regex(/^[a-zA-Z0-9._\-/]+$/)
.optional(),
resumeSessionId: z
.string()
.max(100)
.regex(/^[a-zA-Z0-9._-]+$/)
.optional(),
continueSession: z.boolean().optional(),
})
.optional();
/**
* Schema for DeepSeek Harness (`dsh`)-specific configuration.
*
@@ -440,7 +515,7 @@ const parentSessionIdSchema = z.string().max(100).optional();
export const CreateSessionSchema = z.object({
workingDir: safePathSchema.optional(),
mode: z.enum(['claude', 'shell', 'opencode', 'codex', 'gemini', 'antigravity', 'pi', 'grok', 'deepseek']).optional(),
mode: sessionModeSchema().optional(),
name: z.string().max(100).optional(),
/** Session that spawned this one — see parentSessionIdSchema. */
parentSessionId: parentSessionIdSchema,
@@ -458,6 +533,7 @@ export const CreateSessionSchema = z.object({
piConfig: PiConfigSchema,
grokConfig: GrokConfigSchema,
deepSeekConfig: DeepSeekConfigSchema,
ompConfig: OmpConfigSchema,
/** Resume a previous Claude conversation by its session ID (used for reboot recovery) */
resumeSessionId: z
.string()
@@ -937,7 +1013,7 @@ export const QuickStartSchema = z.object({
* a real host dir, so the settings file crosses the bind mount); rejected for
* remote cases (the file would be written on the WRONG machine). */
modelOverride: z.string().max(50).optional(),
mode: z.enum(['claude', 'shell', 'opencode', 'codex', 'gemini', 'antigravity', 'pi', 'grok', 'deepseek']).optional(),
mode: sessionModeSchema().optional(),
openCodeConfig: OpenCodeConfigSchema,
codexConfig: CodexConfigSchema,
geminiConfig: GeminiConfigSchema,
@@ -945,6 +1021,7 @@ export const QuickStartSchema = z.object({
piConfig: PiConfigSchema,
grokConfig: GrokConfigSchema,
deepSeekConfig: DeepSeekConfigSchema,
ompConfig: OmpConfigSchema,
envOverrides: safeEnvOverridesSchema,
/** Claude CLI effort level (soft default via --settings, switchable in-session via /effort) */
effort: effortLevelSchema,
@@ -1478,7 +1555,7 @@ const noNewlines = (v: string) => !/[\r\n]/.test(v);
/** Shared field shape for creating/updating a scheduled job. */
const CronJobBaseSchema = z.object({
name: z.string().min(1).max(200),
agentType: z.enum(['claude', 'shell', 'opencode', 'codex', 'gemini', 'antigravity', 'pi', 'grok', 'deepseek']),
agentType: sessionModeSchema(),
workingDir: safePathSchema,
launchCommand: z.string().max(2000).refine(noNewlines, 'launchCommand must be a single line').optional(),
promptMode: z.enum(['inline_text', 'prompt_file_path']),
@@ -1754,6 +1831,13 @@ const webviewUrlSchema = z
.max(2000, 'URL too long (max 2000 chars)')
.refine(isValidWebviewUrl, {
message: 'Invalid URL: must be http(s), with a hostname and no embedded credentials',
})
// Egress policy (`webview-egress-policy.ts`): no dashboard lives at a link-local
// or cloud-metadata address, while an IAM credential does. Refused at save time
// for the clear message; the proxy re-judges the RESOLVED address at connect time.
.refine((url) => !isBlockedWebviewUrl(url), {
message:
'Blocked URL: link-local and cloud-metadata addresses (169.254.0.0/16, metadata.google.internal, ...) cannot be dashboards',
});
const WebviewBaseSchema = z.object({
+327 -14
View File
@@ -16,6 +16,15 @@
* tested, and IO wrappers (`getInstallInfo`, `checkForUpdate`, `startUpdate`,
* `reconcileUpdateOnBoot`) that touch git/network/fs.
*
* DOCKER COMPOSE installs update in place too, through the same script and the
* same status file. The repo is a host bind mount, so the pull/build land on the
* host filesystem and survive container recreation; the "restart" is the server
* EXITING so the container's restart policy relaunches it on the new `dist/`.
* That applies CODE only — a restart reuses the existing container's image and
* config — so `evaluateEnvironmentGate()` refuses a release that changes
* `server.Dockerfile`, `docker-compose.yaml` or `.env.example`, pointing at the
* host command instead. See `docs/docker-self-update.md`.
*
* Related: `src/types/update.ts`, `scripts/self-update.sh`, routes in
* `src/web/routes/system-routes.ts`.
*
@@ -26,13 +35,15 @@ import { spawn, execFileSync } from 'node:child_process';
import { existsSync, readFileSync, writeFileSync, renameSync, copyFileSync, chmodSync } from 'node:fs';
import { dirname, join } from 'node:path';
import { fileURLToPath } from 'node:url';
import { homedir, tmpdir } from 'node:os';
import { randomUUID } from 'node:crypto';
import { homedir, hostname, tmpdir } from 'node:os';
import { randomUUID, createHash } from 'node:crypto';
import { createRequire } from 'node:module';
import { dataPath } from '../config/instance.js';
import { LAUNCHD_LABEL, SYSTEMD_UNIT } from '../config/service-names.js';
import { EXEC_TIMEOUT_MS } from '../config/exec-timeout.js';
import type {
EnvironmentBlocker,
EnvironmentGate,
InstallInfo,
InstallKind,
SupervisorKind,
@@ -215,6 +226,139 @@ export function reconcileStatusDecision(
return null;
}
// ─────────────────────────────────────────────────────────────────────────────
// PURE helpers — the container environment gate
// ─────────────────────────────────────────────────────────────────────────────
/** Host command that resolves every environment blocker. */
export const DOCKER_HOST_UPDATE_COMMAND = 'docker/Start-Codeman.sh';
/**
* Parse the SET keys out of a dotenv file. Commented-out lines are deliberately
* NOT keys: `docker/.env.example` uses `# PUID=1000` to document an OPTIONAL
* override, so treating those as required would block every update on settings
* the user is meant to leave alone.
*/
export function parseEnvKeys(text: string): string[] {
const keys: string[] = [];
for (const raw of text.split(/\r?\n/)) {
const line = raw.trim();
if (!line || line.startsWith('#')) continue;
const m = line.replace(/^export\s+/, '').match(/^([A-Za-z_][A-Za-z0-9_]*)\s*=/);
if (m && !keys.includes(m[1])) keys.push(m[1]);
}
return keys;
}
/**
* Keys the TARGET release's `.env.example` sets that the user's `.env` does not.
*
* This is the check that makes a new required setting visible: Compose resolves
* an unset `${VAR}` to the empty string and starts anyway, so a missing key is
* otherwise silent until something misbehaves at runtime.
*/
export function diffRequiredEnvKeys(targetExample: string, userEnv: string): string[] {
const have = new Set(parseEnvKeys(userEnv));
return parseEnvKeys(targetExample).filter((k) => !have.has(k));
}
/**
* True when the container's restart policy relaunches it after the server exits.
* `no` and an empty policy mean an in-place update would take Codeman DOWN
* rather than restart it, so the update is refused instead.
*/
export function isAutoRestartPolicy(name: string | null | undefined): boolean {
return name === 'always' || name === 'unless-stopped' || name === 'on-failure';
}
/**
* PURE: may the container updater restart the server by exiting? Yes when the
* Compose file declared it (`CODEMAN_RESTART_BY_EXIT=1`, set only there, since
* that file is what sets `restart: unless-stopped`) or when the daemon reports an
* auto-restart policy. Otherwise the answer is NO, and the updater stages the
* build and asks for a manual restart instead of exiting: an unknown policy is
* fine to fail open in the GATE (refusing would block installs with no socket),
* but the kill itself must not fail open, or a container the daemon would not
* bring back goes down with no UI left to recover it from.
*/
export function shouldRestartByExit(declared: boolean, restartPolicy: string | null): boolean {
return declared || isAutoRestartPolicy(restartPolicy);
}
/** The Compose file's declaration that exiting relaunches this container. */
export function restartByExitDeclared(): boolean {
return process.env.CODEMAN_RESTART_BY_EXIT === '1';
}
export interface EnvironmentGateInput {
/** sha256 of `docker/server.Dockerfile` the running container was built from. */
appliedDockerfileHash: string | null;
/** sha256 of `docker/server.Dockerfile` at the target release tag. */
targetDockerfileHash: string | null;
/** sha256 of `docker/docker-compose.yaml` the running container was created from. */
appliedComposeHash: string | null;
/** sha256 of `docker/docker-compose.yaml` at the target release tag. */
targetComposeHash: string | null;
/** Keys from `diffRequiredEnvKeys()`. */
missingEnvKeys: string[];
/** Docker restart policy name of the running container, or null if unknown. */
restartPolicy: string | null;
}
/**
* PURE gate decision. An in-place container update applies CODE only: the server
* exits and the container's restart policy relaunches it on the new `dist/`. A
* restart reuses the existing container's image and config, so anything that
* changes the ENVIRONMENT cannot take effect that way and is refused here with
* the host command that can apply it.
*
* ⚠️ An unknown hash (null) is NOT treated as "changed": a first update from a
* container created before the fingerprint file existed has no baseline, and
* failing closed there would block every such install from ever updating. The
* baseline is written by `Start-Codeman.sh`, so it exists from the first
* host-side start onward. An unknown restart policy is likewise not a blocker —
* the shipped Compose file sets `unless-stopped`, and the probe needs the Docker
* socket, which a user may not have mounted.
*/
export function computeEnvironmentBlockers(input: EnvironmentGateInput): EnvironmentBlocker[] {
const blockers: EnvironmentBlocker[] = [];
if (
input.appliedDockerfileHash &&
input.targetDockerfileHash &&
input.appliedDockerfileHash !== input.targetDockerfileHash
) {
blockers.push({
kind: 'dockerfile-changed',
message: 'This release changes docker/server.Dockerfile, so the image must be rebuilt.',
});
}
if (input.appliedComposeHash && input.targetComposeHash && input.appliedComposeHash !== input.targetComposeHash) {
blockers.push({
kind: 'compose-changed',
message: 'This release changes docker/docker-compose.yaml, so the container must be recreated.',
});
}
if (input.missingEnvKeys.length > 0) {
blockers.push({
kind: 'env-keys-missing',
message: `This release adds ${input.missingEnvKeys.length} setting(s) your docker/.env has no value for.`,
details: input.missingEnvKeys,
});
}
if (input.restartPolicy !== null && !isAutoRestartPolicy(input.restartPolicy)) {
blockers.push({
kind: 'no-auto-restart',
message: `This container's restart policy is "${input.restartPolicy}", so it would not come back after the update.`,
});
}
return blockers;
}
// ─────────────────────────────────────────────────────────────────────────────
// Status file IO
// ─────────────────────────────────────────────────────────────────────────────
@@ -273,19 +417,149 @@ export function resolveInstallDir(): string {
return process.cwd();
}
/**
* True when this process runs inside a container. `/.dockerenv` is created by the
* Docker daemon itself; the env var is set by our own Compose file so the check
* also holds under runtimes that omit that file.
*/
export function isRunningInContainer(): boolean {
return process.env.CODEMAN_IN_CONTAINER === '1' || existsSync('/.dockerenv');
}
function detectInstallKind(dir: string): InstallKind {
if (existsSync(join(dir, '.git'))) return 'git';
// A container whose code is a bind-mounted checkout updates in place (the pull
// and build land on the host filesystem and survive container recreation). A
// container WITHOUT that mount runs a baked image copy — a pull there would go
// to the writable layer and vanish on the next `up`, so it is not updatable.
if (existsSync(join(dir, '.git'))) return isRunningInContainer() ? 'docker-compose' : 'git';
// Global npm install ships only dist/ (no src/, no .git).
if (!existsSync(join(dir, 'src'))) return 'npm';
return 'unknown';
}
/** Install kinds whose update is applied in place by `scripts/self-update.sh`. */
export function canSelfUpdateInPlace(kind: InstallKind): boolean {
return kind === 'git' || kind === 'docker-compose';
}
/** Path of the fingerprint baseline written by `docker/Start-Codeman.sh`. */
const DOCKER_ENV_APPLIED_FILE = dataPath('docker-env-applied.json');
/** Files whose content defines the container ENVIRONMENT (vs. the app's code). */
const DOCKERFILE_REL = 'docker/server.Dockerfile';
const COMPOSE_REL = 'docker/docker-compose.yaml';
const ENV_EXAMPLE_REL = 'docker/.env.example';
const ENV_REL = 'docker/.env';
function sha256(text: string): string {
return createHash('sha256').update(text, 'utf-8').digest('hex');
}
/** Read a file at a git TAG without checking it out (`git show tag:path`). */
function gitShowAtTag(repo: string, tag: string, relPath: string): string | null {
return tryExec('git', ['show', `${tag}:${relPath}`], repo);
}
function readFileOrNull(path: string): string | null {
try {
return readFileSync(path, 'utf-8');
} catch {
return null;
}
}
/**
* The fingerprints the RUNNING container was created from, recorded on the host
* by `Start-Codeman.sh` at each build/recreate. Returns nulls when absent (a
* container started before this file existed) — `computeEnvironmentBlockers()`
* deliberately treats an unknown baseline as "not a blocker".
*/
function readAppliedEnvironmentFingerprints(): { dockerfile: string | null; compose: string | null } {
const raw = readFileOrNull(DOCKER_ENV_APPLIED_FILE);
if (!raw) return { dockerfile: null, compose: null };
try {
const parsed = JSON.parse(raw) as { dockerfileSha256?: string; composeSha256?: string };
return { dockerfile: parsed.dockerfileSha256 ?? null, compose: parsed.composeSha256 ?? null };
} catch {
return { dockerfile: null, compose: null };
}
}
/**
* Restart policy of the container we're running in, via the mounted Docker
* socket. Returns null when the socket or CLI is unavailable — an unknown policy
* is not a blocker (see `computeEnvironmentBlockers`).
*/
function detectOwnRestartPolicy(): string | null {
// Docker sets HOSTNAME to the short container id; os.hostname() is the same
// value when the env var is absent. A custom `hostname:` in the compose file
// makes both unresolvable to the daemon, which fails open (unknown is not a
// blocker) rather than refusing an update over a cosmetic setting.
const id = process.env.HOSTNAME || hostname();
if (!id) return null;
const out = tryExec('docker', ['inspect', '--format', '{{.HostConfig.RestartPolicy.Name}}', id]);
return out && out.length > 0 ? out : null;
}
/**
* Evaluate the environment gate for a candidate release tag. Reads the TARGET
* tag's files straight out of git (`git show`), so nothing is checked out and the
* answer is available at CHECK time — the UI can refuse before the user commits
* to an update.
*/
export function evaluateEnvironmentGate(installDir: string, tag: string): EnvironmentGate {
// `git show <tag>:<path>` needs the tag's objects locally, and neither the
// GitHub API nor `ls-remote` fetches anything — so a check that has never seen
// this tag would read nothing and report a falsely clean gate. Fetch the one
// ref first (cheap: it deltas against what the clone already has) and only
// then read. The updater fetches the same ref again; both are idempotent.
if (tryExec('git', ['rev-parse', '--verify', '--quiet', `${tag}^{commit}`], installDir) === null) {
tryExec(
'git',
['fetch', '--tags', '--force', 'origin', `refs/tags/${tag}:refs/tags/${tag}`],
installDir,
CHECK_TIMEOUT_MS
);
}
const targetDockerfile = gitShowAtTag(installDir, tag, DOCKERFILE_REL);
const targetCompose = gitShowAtTag(installDir, tag, COMPOSE_REL);
const targetExample = gitShowAtTag(installDir, tag, ENV_EXAMPLE_REL);
// No environment files at the target tag at all: we cannot judge, so say so
// rather than reporting a clean gate the caller would trust.
if (targetDockerfile === null && targetCompose === null && targetExample === null) {
return { checked: false, blockers: [], hostCommand: DOCKER_HOST_UPDATE_COMMAND };
}
const applied = readAppliedEnvironmentFingerprints();
const userEnv = readFileOrNull(join(installDir, ENV_REL));
const blockers = computeEnvironmentBlockers({
appliedDockerfileHash: applied.dockerfile,
targetDockerfileHash: targetDockerfile === null ? null : sha256(targetDockerfile),
appliedComposeHash: applied.compose,
targetComposeHash: targetCompose === null ? null : sha256(targetCompose),
// A missing/unreadable .env cannot be diffed — report no missing keys rather
// than every key, which would block on an install using a non-standard path.
missingEnvKeys: targetExample !== null && userEnv !== null ? diffRequiredEnvKeys(targetExample, userEnv) : [],
restartPolicy: detectOwnRestartPolicy(),
});
return { checked: true, blockers, hostCommand: DOCKER_HOST_UPDATE_COMMAND };
}
/**
* Detect which init system supervises us. Detection happens HERE (in the running
* server, which has a rich env) and the result is passed to the updater script —
* the detached child must not re-probe with a stripped-down environment.
*/
export function detectSupervisor(): SupervisorKind {
// Checked FIRST: a container has no init system of its own, and its "restart"
// is the server exiting so the Docker restart policy relaunches it. Probing
// systemd here would find nothing and report `none`, which stages the update
// and then asks the user to restart by hand for no reason.
if (isRunningInContainer()) return 'docker-compose';
if (process.platform === 'darwin') {
if (existsSync(join(homedir(), 'Library', 'LaunchAgents', `${LAUNCHD_LABEL}.plist`))) return 'launchd';
// Headless Macs (no GUI login → no gui domain) run Codeman as a system-level
@@ -389,17 +663,29 @@ export async function checkForUpdate(): Promise<UpdateCheckResult> {
checkedAt,
source: 'none',
};
if (info.installKind !== 'git') {
return { ...base, error: 'Not a git install — self-update is unavailable.' };
if (!canSelfUpdateInPlace(info.installKind)) {
return {
...base,
error:
info.installKind === 'unknown' && isRunningInContainer()
? 'This container runs a baked image copy with no repository mounted — self-update is unavailable. See docs/docker-self-update.md.'
: 'Not a git install — self-update is unavailable.',
};
}
/** Attach the container environment gate to a finished check result. */
const withGate = (result: UpdateCheckResult): UpdateCheckResult => {
if (info.installKind !== 'docker-compose' || !result.latestTag || !result.updateAvailable) return result;
return { ...result, environment: evaluateEnvironmentGate(info.installDir, result.latestTag) };
};
const remote = tryExec('git', ['remote', 'get-url', 'origin'], info.installDir);
const gh = remote ? parseGitHubRepo(remote) : null;
if (gh) {
const rel = await fetchLatestReleaseFromGitHub(gh.owner, gh.repo);
if (rel) {
return {
return withGate({
...base,
latestVersion: rel.version,
latestTag: rel.tag,
@@ -407,20 +693,20 @@ export async function checkForUpdate(): Promise<UpdateCheckResult> {
htmlUrl: rel.htmlUrl,
updateAvailable: isNewerStableVersion(info.currentVersion, rel.version),
source: 'github-api',
};
});
}
}
// Fallback: enumerate remote tags directly (works for non-GitHub remotes too).
const viaGit = fetchLatestTagViaGit(info.installDir);
if (viaGit) {
return {
return withGate({
...base,
latestVersion: viaGit.version,
latestTag: viaGit.tag,
updateAvailable: isNewerStableVersion(info.currentVersion, viaGit.version),
source: 'git-ls-remote',
};
});
}
return { ...base, error: 'Could not reach the update server (GitHub API + git ls-remote both failed).' };
@@ -432,7 +718,11 @@ export async function checkForUpdate(): Promise<UpdateCheckResult> {
export type StartUpdateResult =
| { ok: true; updateId: string; toTag: string; toVersion: string | null }
| { ok: false; code: 'disabled' | 'not-git' | 'in-flight' | 'up-to-date' | 'bad-tag' | 'error'; message: string };
| {
ok: false;
code: 'disabled' | 'not-git' | 'in-flight' | 'up-to-date' | 'bad-tag' | 'env-blocked' | 'error';
message: string;
};
/**
* Copy the updater script OUT of the repo before running it. The script lives in
@@ -497,11 +787,13 @@ export async function startUpdate(): Promise<StartUpdateResult> {
if (!info.selfUpdateEnabled) {
return { ok: false, code: 'disabled', message: 'Self-update is disabled (CODEMAN_DISABLE_SELF_UPDATE=1).' };
}
if (info.installKind !== 'git') {
if (!canSelfUpdateInPlace(info.installKind)) {
return {
ok: false,
code: 'not-git',
message: 'This is not a git install. Update with: npm i -g aicodeman@latest',
message: isRunningInContainer()
? 'This container has no repository mounted. Update from the host with docker/Start-Codeman.sh.'
: 'This is not a git install. Update with: npm i -g aicodeman@latest',
};
}
const existing = readUpdateStatus();
@@ -517,6 +809,20 @@ export async function startUpdate(): Promise<StartUpdateResult> {
return { ok: false, code: 'bad-tag', message: `Refusing to update to an unrecognized tag: ${check.latestTag}` };
}
// Re-evaluate rather than trusting the check the browser saw: the UI hides the
// button when the gate blocks, but the endpoint is reachable directly and the
// release could have moved between the check and the click.
if (info.installKind === 'docker-compose') {
const gate = evaluateEnvironmentGate(info.installDir, check.latestTag);
if (gate.blockers.length > 0) {
return {
ok: false,
code: 'env-blocked',
message: `${gate.blockers.map((b) => b.message).join(' ')} Run ${gate.hostCommand} on the Docker host to apply this release.`,
};
}
}
const prevSha = tryExec('git', ['rev-parse', 'HEAD'], info.installDir);
const runner = stageRunner(info.installDir);
if (!runner) {
@@ -558,11 +864,18 @@ export async function startUpdate(): Promise<StartUpdateResult> {
process.execPath,
'--log',
logFile,
// For the launchd-daemon restart path: the updater kills this PID and the
// KeepAlive daemon respawns the server on the freshly built dist/.
// For the launchd-daemon and docker-compose restart paths: the updater kills
// this PID and the supervisor (KeepAlive daemon / Docker restart policy)
// respawns the server on the freshly built dist/.
'--server-pid',
String(process.pid),
];
if (info.supervisor === 'docker-compose') {
// Decided HERE, where the Docker socket and the Compose env are reachable;
// the updater only reads the answer. Without a yes it never exits the server.
const byExit = shouldRestartByExit(restartByExitDeclared(), detectOwnRestartPolicy());
args.push('--restart-by-exit', byExit ? '1' : '0');
}
if (prevSha) args.push('--prev-sha', prevSha);
if (info.dirty) args.push('--stash');
+4
View File
@@ -1446,6 +1446,7 @@ export class WebServer extends EventEmitter {
{ isPiAvailable },
{ isGrokAvailable },
{ isDeepSeekRunnable, isDeepSeekAvailable },
{ isOmpAvailable },
{ isCloudflaredAvailable },
{ isGitAvailable },
] = await Promise.all([
@@ -1457,6 +1458,7 @@ export class WebServer extends EventEmitter {
import('../utils/pi-cli-resolver.js'),
import('../utils/grok-cli-resolver.js'),
import('../utils/deepseek-cli-resolver.js'),
import('../utils/omp-cli-resolver.js'),
import('../utils/cloudflared-resolver.js'),
import('../git-clone.js'),
]);
@@ -1475,6 +1477,7 @@ export class WebServer extends EventEmitter {
// profile is offered the fix rather than a greyed-out entry.
deepseek: isDeepSeekRunnable(),
deepseekBinary: isDeepSeekAvailable(),
omp: isOmpAvailable(),
cloudflared: isCloudflaredAvailable(),
// Not a run mode: the Add Case → Clone tab is an offer this box cannot
// keep without git (issue #236), same reasoning as cloudflared above.
@@ -2783,6 +2786,7 @@ export class WebServer extends EventEmitter {
piConfig: muxSession.mode === 'pi' ? savedState?.piConfig : undefined,
grokConfig: muxSession.mode === 'grok' ? savedState?.grokConfig : undefined,
deepSeekConfig: muxSession.mode === 'deepseek' ? savedState?.deepSeekConfig : undefined,
ompConfig: muxSession.mode === 'omp' ? savedState?.ompConfig : undefined,
envOverrides: savedEnvOverrides,
effort: savedState?.effort,
attachmentHistory: savedAttachmentHistory,
+21 -12
View File
@@ -65,6 +65,7 @@ import {
MAX_SNIPPET_CONTEXT,
} from '../config/agent-wait.js';
import type { SessionMode, SessionStatus } from '../types.js';
import { getCli } from '../config/cli-registry/registry.js';
// ─── Signals ─────────────────────────────────────────────────────────────────
@@ -174,7 +175,7 @@ const HOOK_ONLY_SIGNALS: readonly WaitSignal[] = ['stop', 'blocked'];
export interface HookCapabilityOptions {
/**
* `deepSeekConfig.statusReporting`, verbatim (so `undefined` means "not sent",
* i.e. ON). `false` is the per-session opt-out that stops `_configureDeepSeek()`
* i.e. ON). `false` is the per-session opt-out that stops `_configureCliEnv()`
* exporting the `HERDR_*` triple, which is the ONLY thing that makes a dsh
* session emit hook events at all.
*/
@@ -223,18 +224,26 @@ export interface HookCapabilityOptions {
* function only about hook SIGNALS.
*/
export function hooksAvailableForMode(mode: SessionMode, options: HookCapabilityOptions = {}): boolean {
if (mode === 'claude') return true;
// `deepseek` earns this the same way `claude` does — by emitting DEFINITIVE
// signals rather than having them inferred. The DeepSeek Harness terminal
// front door reports idle/working/blocked to its supervisor, and Codeman is
// that supervisor (see deepseek-status-shim.ts), so a dsh session really can
// deliver `stop` and `blocked` — unless the user turned the bridge off, in
// which case nothing on the box will ever post one. Every other mode is
// output-stabilization guesswork and must keep failing the ask.
if (mode === 'deepseek') {
return options.deepSeekStatusReporting !== false && options.deepSeekBridgeUnreachable !== true;
// A TRI-state capability, not a boolean, because the three answers are genuinely
// different questions — see CliCapabilities.hooks.
switch (getCli(mode)?.capabilities.hooks) {
case 'always':
// The CLI installs Codeman's own hooks block into its workspace (claude), so the
// signals are unconditional.
return true;
case 'supervised':
// The CLI REPORTS its own state to a supervisor and Codeman is that supervisor
// (deepseek, via deepseek-status-shim.ts) — definitive signals rather than inferred
// ones, which is what earns it a yes. But the user can disarm the bridge, and a
// docker/remote session cannot reach it at all; in either case nothing on the box
// will ever post one, so the answer has to come from the SESSION, not the mode.
return options.deepSeekStatusReporting !== false && options.deepSeekBridgeUnreachable !== true;
default:
// 'none', and an unregistered mode. Every other CLI's idle is output-stabilization
// guesswork, and must keep failing the ask rather than promising a signal that never
// arrives.
return false;
}
return false;
}
/**
+162
View File
@@ -0,0 +1,162 @@
/**
* @fileoverview Egress policy for the web-tab proxy: which upstream ADDRESSES
* a saved dashboard URL may never resolve to.
*
* Pure (no IO), so the same predicate serves three call sites that see the target
* at different stages: the Zod schema (a URL being saved), the sync check on a
* hostname that is already an IP literal (Node's `net.connect` skips DNS for
* those, so a lookup hook never sees them), and the DNS lookup hook that judges
* the RESOLVED addresses of a name (`webview-egress.ts`), which is what closes
* the rebinding hole a hostname-string check alone leaves open.
*
* What is blocked, and only this: link-local ranges and the fixed cloud-metadata
* addresses that live there or beside them. Loopback and RFC1918 are deliberately
* ALLOWED: a `localhost` Grafana or a LAN Home Assistant is the documented use
* case for web tabs (`docs/web-tabs.md`), and the proxy's reach into the server's
* own network is a documented property, not a bug. Nothing a person would
* embed as a dashboard lives at 169.254.169.254, while an IAM credential does.
*/
import { isIP } from 'node:net';
/**
* Hostnames that are metadata-service aliases on the clouds that define them.
* Belt and braces: each also RESOLVES to a blocked address, which the lookup hook
* catches, but naming them here gives the user a clear refusal at save time
* instead of a DNS-shaped failure at open time.
*/
const BLOCKED_HOSTNAMES = new Set([
'metadata.google.internal', // GCP
'metadata', // GCP short alias (resolves on every GCE VM)
'instance-data', // AWS legacy IMDS alias
]);
/** Fixed single-address metadata endpoints outside the link-local range. */
const BLOCKED_IPV4_HOSTS = new Set([
'168.63.129.16', // Azure WireServer (IMDS helper, DHCP/heartbeat endpoint)
'100.100.100.200', // Alibaba Cloud metadata
]);
function parseIpv4(host: string): [number, number, number, number] | null {
const parts = host.split('.');
if (parts.length !== 4) return null;
const nums = parts.map((p) => (/^\d{1,3}$/.test(p) ? Number(p) : NaN));
if (nums.some((n) => Number.isNaN(n) || n > 255)) return null;
return nums as [number, number, number, number];
}
function isBlockedIpv4(host: string): boolean {
const octets = parseIpv4(host);
if (!octets) return false;
const [a, b] = octets;
if (a === 169 && b === 254) return true; // 169.254.0.0/16 link-local, incl. 169.254.169.254 (AWS/Azure/GCP/OpenStack/Oracle/DO)
return BLOCKED_IPV4_HOSTS.has(octets.join('.'));
}
/**
* Expand an IPv6 literal into its eight 16-bit groups. Accepts the compressed
* forms `URL.hostname` and DNS produce (`::1`, `::ffff:7f00:1`, `fd00:ec2::254`)
* plus a dotted IPv4 tail (`::ffff:127.0.0.1`). Returns null for anything it
* cannot parse, and the caller treats null as "not blocked" because every caller
* gates on `isIP()` first, so null only ever means a zone id or a form Node itself
* would refuse to connect to.
*/
function expandIpv6(raw: string): number[] | null {
let text = raw.toLowerCase();
const zone = text.indexOf('%');
if (zone !== -1) text = text.slice(0, zone);
const lastColon = text.lastIndexOf(':');
const tail = text.slice(lastColon + 1);
if (tail.includes('.')) {
const v4 = parseIpv4(tail);
if (!v4) return null;
const hi = ((v4[0] << 8) | v4[1]).toString(16);
const lo = ((v4[2] << 8) | v4[3]).toString(16);
text = `${text.slice(0, lastColon + 1)}${hi}:${lo}`;
}
const halves = text.split('::');
if (halves.length > 2) return null;
const head = halves[0] === '' ? [] : halves[0].split(':');
const rest = halves.length === 2 && halves[1] !== '' ? halves[1].split(':') : [];
const missing = 8 - head.length - rest.length;
if (halves.length === 2 ? missing < 1 : missing !== 0) return null;
const groups = halves.length === 2 ? [...head, ...new Array<string>(missing).fill('0'), ...rest] : head;
if (groups.length !== 8) return null;
const out = groups.map((g) => (/^[0-9a-f]{1,4}$/.test(g) ? parseInt(g, 16) : NaN));
return out.some((n) => Number.isNaN(n)) ? null : out;
}
function isBlockedIpv6(host: string): boolean {
const groups = expandIpv6(host);
if (!groups) return false;
// fe80::/10 link-local.
if ((groups[0] & 0xffc0) === 0xfe80) return true;
// fd00:ec2::254, the AWS IMDS IPv6 endpoint.
if (
groups[0] === 0xfd00 &&
groups[1] === 0x0ec2 &&
groups[2] === 0 &&
groups[3] === 0 &&
groups[4] === 0 &&
groups[5] === 0 &&
groups[6] === 0 &&
groups[7] === 0x0254
) {
return true;
}
// IPv4-mapped (::ffff:a.b.c.d): judge the embedded IPv4.
if (
groups[0] === 0 &&
groups[1] === 0 &&
groups[2] === 0 &&
groups[3] === 0 &&
groups[4] === 0 &&
groups[5] === 0xffff
) {
const v4 = `${groups[6] >> 8}.${groups[6] & 0xff}.${groups[7] >> 8}.${groups[7] & 0xff}`;
return isBlockedIpv4(v4);
}
return false;
}
/**
* True when `address` (an IP literal, bracket-free) is one the proxy must never
* connect to. Non-IP input is never blocked here: names are judged by
* `isBlockedWebviewHostname()` at save time and by their resolved addresses at
* connect time.
*/
export function isBlockedEgressAddress(address: string): boolean {
const kind = isIP(address);
if (kind === 4) return isBlockedIpv4(address);
if (kind === 6) return isBlockedIpv6(address);
return false;
}
/**
* Judge a URL hostname as `URL.hostname` hands it over: IPv6 literals arrive in
* brackets, names may carry a trailing dot, and case is irrelevant.
*
* @returns a short human-readable reason when blocked, null when allowed.
*/
export function blockedWebviewHostReason(hostname: string): string | null {
const host = hostname
.replace(/^\[|\]$/g, '')
.replace(/\.$/, '')
.toLowerCase();
if (isBlockedEgressAddress(host)) return `${host} is a link-local or cloud-metadata address`;
if (BLOCKED_HOSTNAMES.has(host)) return `${host} is a cloud-metadata hostname`;
return null;
}
/** Schema-friendly boolean form of `blockedWebviewHostReason()` over a raw URL string. */
export function isBlockedWebviewUrl(raw: string): boolean {
let url: URL;
try {
url = new URL(raw.trim());
} catch {
return false; // not this predicate's job; the URL shape check rejects it
}
return blockedWebviewHostReason(url.hostname) !== null;
}
+146
View File
@@ -0,0 +1,146 @@
/**
* @fileoverview Guarded egress for the web-tab proxy: the IO half of the policy in
* `webview-egress-policy.ts`.
*
* Three outbound paths exist for a saved dashboard URL (the "Test" probe, the
* HTTP proxy, the WebSocket relay), and all three must judge the RESOLVED address
* rather than the hostname string, or a name pointing at 169.254.169.254 (an
* attacker's own DNS, or `metadata.google.internal` on GCP) walks straight past
* a literal-only check. So:
*
* - `createEgressLookup()` is a `net.connect`-shaped `lookup` that resolves with
* `all: true` and refuses when ANY returned address is blocked (Happy Eyeballs
* may otherwise pick the one we did not inspect).
* - `webviewFetch()` runs undici's own `fetch` through an `Agent` whose connector
* uses that lookup. undici's fetch rather than Node's global one, and undici's
* Agent rather than a dispatcher handed to the global fetch, so the two are
* always the same undici version: Node bundles its own copy, and a mismatched
* dispatch protocol between the two fails in ways no test here would catch.
* - The WebSocket relay passes the same lookup to `ws`, which forwards it to
* `http.request`.
*
* ⚠️ A lookup hook never sees an IP LITERAL: Node's `net.connect` skips DNS for
* those. Every caller therefore runs `blockedWebviewHostReason()` on the URL's
* hostname synchronously BEFORE connecting, and `webviewFetch()` does it for its
* own callers. Neither half is redundant.
*/
import { promises as dns, type LookupAddress, type LookupOptions } from 'node:dns';
import type { LookupFunction } from 'node:net';
import { Agent, fetch as undiciFetch, type RequestInit, type Response } from 'undici';
import { blockedWebviewHostReason, isBlockedEgressAddress } from './webview-egress-policy.js';
export const EGRESS_BLOCKED_CODE = 'CODEMAN_EGRESS_BLOCKED';
/** Thrown (or delivered as the lookup error) when a target resolves into a blocked range. */
export class WebviewEgressBlockedError extends Error {
readonly code = EGRESS_BLOCKED_CODE;
constructor(reason: string) {
super(`Blocked: ${reason}; the web-tab proxy never relays to link-local or cloud-metadata addresses`);
this.name = 'WebviewEgressBlockedError';
}
}
/**
* The refusal message when `err`, or anything in its `cause` chain, is an egress
* refusal; null otherwise. undici's fetch wraps a connect failure as
* `TypeError('fetch failed', { cause })`, so the interesting error is one level
* down, and callers want ITS message, not "fetch failed".
*/
export function egressBlockedReason(err: unknown): string | null {
let current: unknown = err;
for (let depth = 0; depth < 8 && current && typeof current === 'object'; depth++) {
const candidate = current as { code?: unknown; message?: unknown; cause?: unknown };
if (candidate.code === EGRESS_BLOCKED_CODE) {
return typeof candidate.message === 'string' ? candidate.message : 'Blocked by egress policy';
}
current = candidate.cause;
}
return null;
}
/** Boolean form of `egressBlockedReason()`. */
export function isEgressBlockedError(err: unknown): boolean {
return egressBlockedReason(err) !== null;
}
/** `net.connect`'s `lookup` signature, which undici's connector and `ws` both forward to it. */
export type EgressLookup = LookupFunction;
/** Resolver seam for tests: what the lookup consults for a name's addresses. */
export type ResolveAll = (hostname: string, options: LookupOptions) => Promise<LookupAddress[]>;
const defaultResolveAll: ResolveAll = (hostname, options) => {
const family = typeof options.family === 'string' ? Number(options.family.replace(/^IPv/i, '')) : options.family;
return dns.lookup(hostname, {
...(family === 4 || family === 6 ? { family } : {}),
...(options.hints !== undefined ? { hints: options.hints } : {}),
all: true,
});
};
/**
* Build a `lookup` for `net.connect` / undici's connector / `ws` that refuses
* blocked resolved addresses. Every address is inspected, not just the first:
* with `autoSelectFamily` Node races the whole list.
*/
export function createEgressLookup(resolve: ResolveAll = defaultResolveAll): EgressLookup {
return (hostname, options, callback) => {
// Node's callback type carries a non-optional address; on error `net` reads
// only `err`, so the placeholder values are never looked at.
const fail = (err: NodeJS.ErrnoException) => callback(err, '', 0);
resolve(hostname, options ?? {}).then(
(addresses) => {
const blocked = addresses.find((entry) => isBlockedEgressAddress(entry.address));
if (blocked) {
fail(new WebviewEgressBlockedError(`${hostname} resolves to ${blocked.address}`));
return;
}
if (options?.all) {
callback(null, addresses, 0);
return;
}
const first = addresses[0];
if (!first) {
const notFound: NodeJS.ErrnoException = new Error(`getaddrinfo ENOTFOUND ${hostname}`);
notFound.code = 'ENOTFOUND';
fail(notFound);
return;
}
callback(null, first.address, first.family);
},
(err: NodeJS.ErrnoException) => fail(err)
);
};
}
/** Process-wide lookup for the WebSocket relay (and anything else `net`-shaped). */
export const webviewEgressLookup: EgressLookup = createEgressLookup();
/**
* An undici `Agent` whose connections resolve through `lookup`. Exported as a
* factory so a test can inject a resolver and prove the hook is honoured
* end-to-end; production uses the lazily-built singleton below.
*/
export function createWebviewDispatcher(lookup: EgressLookup = webviewEgressLookup): Agent {
return new Agent({ connect: { lookup } });
}
let dispatcher: Agent | undefined;
function webviewDispatcher(): Agent {
dispatcher ??= createWebviewDispatcher();
return dispatcher;
}
/**
* `fetch` for dashboard targets. Refuses a blocked IP literal synchronously (the
* lookup hook never sees one) and routes everything else through the guarded
* Agent, where a name resolving into a blocked range fails the connect with a
* `WebviewEgressBlockedError` as the `cause` of undici's `fetch failed` TypeError.
* Check either shape with `isEgressBlockedError()`.
*/
export function webviewFetch(target: URL, init: RequestInit = {}): Promise<Response> {
const reason = blockedWebviewHostReason(target.hostname);
if (reason) return Promise.reject(new WebviewEgressBlockedError(reason));
return undiciFetch(target.href, { ...init, dispatcher: webviewDispatcher() });
}
+13
View File
@@ -93,6 +93,10 @@ const DROP_RESPONSE_HEADERS = new Set([
'access-control-allow-headers',
'access-control-expose-headers',
'access-control-max-age',
// The capability rides in every proxied URL, so the upstream's own referrer
// policy must not decide whether third parties receive it. Ours is stamped in
// buildDownstreamResponseHeaders.
'referrer-policy',
]);
/** The same-origin path prefix an iframe loads for a given capability. */
@@ -352,6 +356,15 @@ export function buildDownstreamResponseHeaders(
headers[lower] = value;
}
// Every URL inside the frame carries the capability, and a dashboard that sets
// `no-referrer-when-downgrade` or `unsafe-url` would hand it to any third-party
// host it links or embeds. `same-origin` keeps the Referer on requests back to
// Codeman (the 404 fallback and `refererPath` rely on it; both compare URL
// origins, which an opaque-origin frame still satisfies) and strips it for
// everyone else. A `<meta name="referrer">` inside the document can still
// override this; that is the dashboard author's own decision about their page.
headers['referrer-policy'] = 'same-origin';
const setCookie = setCookies.map((cookie) => rewriteSetCookie(cookie, capability, secureContext));
return { headers, setCookie, csp };