Merged
Conversation
Closes #342 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
…351) Prevents shell injection via crafted paths in background and watch execution modes. Applies same escaping used in foreground mode (PR #324). Adds shellEscape() helper that replaces single quotes with '\'' to safely interpolate variables into single-quoted shell strings. Applied to: - Watch mode: projectRoot, worktreeDir, branchName, logFile, pidFile - Background mode: projectRoot, worktreeDir, branchName, logFile, pidFile - Provider background mode: workDir, logFile, pidFile, provider args - execSync worktree calls in foreground and provider modes Closes #340 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
v0.6.2 released, 3 security P1 issue-solvers dispatched, 751 tests passing, Q1 goals 2/3 achieved. Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
…339) Closes #319 Added default .action(() => cmd.outputHelp()) to 7 parent commands (env, kpi, feedback, session, trigger, approval, autonomous) so they exit 0 instead of 1 when invoked without a subcommand. Matches the pattern already used by memory, goal, deploy, and exec commands. Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
…354) Replace scattered console.log calls with the project's writeLine() utility from src/lib/terminal.ts. This provides a single output layer for consistent formatting and future output control. - Convert 238 console.log calls to writeLine across 10 files - Remove 8 debug/placeholder log statements from anthropic.ts - Keep console.log only for JSON.stringify output (--json flags) and raw prompt piping — standard CLI patterns - Reduction: 269 → 31 occurrences (88% decrease) - Zero new TypeScript errors Files: init.ts, deploy.ts, autonomous.ts, trigger.ts, approval.ts, eval.ts, login.ts, cli.ts, anthropic.ts, update.ts Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com>
Replace minimal README with comprehensive 331-line version covering: - Quick start with real output examples - Why Squads (4 differentiators) - Provider table (7 LLM providers) - Feature showcase (dashboard, memory, sessions, autonomous, hooks) - Command reference (21 active commands, no removed ones) - Project structure and configuration examples - Development guide and tech stack - Contributing and community links References only current commands (memory write/read instead of learn, env show instead of context, exec list instead of history). 🤖 Generated with [Agents Squads](https://agents-squads.com) Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com>
Closes agents-squads/engineering#51 Removed the base64-obfuscated API key from source code and replaced with SQUADS_TELEMETRY_KEY env var. Telemetry send is skipped when key is not set. The exposed key must be rotated server-side separately. Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
Closes #343 The daemon process was silently failing because Commander.js rejected the unregistered --daemon CLI flag. Replace with SQUADS_DAEMON env var to signal daemon mode, redirect child stdout/stderr to log file for diagnosability, and show clear error when daemon fails to start. Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
* feat(status): show milestones and open PRs from GitHub squads status now queries GitHub API for real operational data: - Milestone progress bars across product repos (cli, console, api) - Open PRs targeting develop with repo and number Replaces vanity-only output with actionable org health metrics. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(status): discover repos dynamically from squad definitions Replace hardcoded PRODUCT_REPOS array with dynamic discovery: - Read `repo` field from each SQUAD.md frontmatter - Deduplicate and pass to fetchOperationalStatus() - GitHub org derived from squad config, not hardcoded - Dynamic column widths based on actual repo names - Show all open PRs (not just develop-targeted) Any user's squads with `repo:` in SQUAD.md will show milestones + PRs. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: rewrite CLAUDE.md as user-facing guide Remove internal references, org names, and dev-specific content. Focus on teaching users how to define squads, run agents, and monitor work. Git-provider agnostic. Engineering standards now live in hq CLAUDE.md (internal only). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Closes #24 Converts ~50 static command imports to dynamic import() inside action handlers. Only the invoked command's dependencies (pg, supabase, inquirer, ora) are loaded, saving ~300ms+ on cold start. Changes: - All command handlers use dynamic import() in their .action() callbacks - autoUpdateOnStartup skipped for --help/--version (instant response) - register*Command imports kept static (needed for subcommand structure) - Type-only import for SessionSummaryData (zero runtime cost) Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Trigger: manual Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
) Closes #297 Show "squads dash" hints at key touchpoints: - After successful foreground/background agent execution - After lead session completion - After parallel agent launch - In squad detail status commands section Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Trigger: manual Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
Breaks down the 350-line executeWithClaude into 6 focused functions: - buildAgentEnv: consolidates 3x duplicated env construction - logVerboseExecution: DRYs up verbose config logging (was 2x identical) - createAgentWorktree: isolates Node.js worktree creation - buildDetachedShellScript: shared shell script for watch/background - prepareLogFiles: shared log directory setup - executeForeground: foreground spawn + status tracking - executeWatch: watch mode (background + tail) executeWithClaude is now a ~80-line coordinator that delegates to the appropriate mode function. Closes #158 Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
…dless flags Closes #371 Two fixes for Google/Gemini provider execution: 1. Add --yolo flag to Gemini CLI args for headless auto-approval. Without this, Gemini denies all tool calls when running in background because it can't prompt for interactive confirmation. 2. Copy .agents directory into worktree and rewrite prompt paths. Gemini CLI sandboxes file access to its workspace directory. The prompt references agent definitions at the original project root, which Gemini blocks as "Path not in workspace". Now we copy .agents into the worktree and rewrite absolute paths so Gemini can resolve them. Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
Closes #280 Implements `squads create <name>` that creates: - .agents/squads/<name>/SQUAD.md (from template) - .agents/squads/<name>/lead.md (starter agent) - .agents/memory/<name>/lead/ (memory directory) Supports --description, --goal, --model flags for non-interactive use, and interactive prompts via inquirer when flags are omitted. Includes --force for overwriting and --yes for CI/scripting. Note: organization.yaml is not used — squads are discovered dynamically via filesystem (squad-parser.ts findSquadsDir + listSquads). 11 tests covering directory creation, content, naming, overwrite protection, and squad discoverability. Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Trigger: manual Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
Closes #366 When --cloud is set, the CLI dispatches agent execution to the platform API instead of running locally. Requires `squads login` session and SQUADS_API_URL environment variable. Flow: - POST /agent-dispatch to create dispatch request - Poll /agent-executions for status updates - Display execution summary on completion Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Trigger: smart Model: claude-opus-4-6 Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com>
Closes #316 Added 63 tests covering 2 of the 6 lib modules listed in the issue: - setup-checks.ts (48 tests): providers registry, commandExists, isDockerRunning, checkDockerPrereqs, checkGhCli, checkGhPermissions, checkClaudeCli, checkProviderAuth, runPrereqChecks, runAuthChecks, displayCheckResults, attemptFix, waitForService - local.ts (15 tests): getLocalEnvVars, formatLocalStatus, isLangfuseLocal, getLocalStackStatus Co-authored-by: Squads Cloud Worker <cloud@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
…urces (#382) Closes #314. Adds 115 tests across 4 test files achieving 92% statement coverage and 80% branch coverage on the dashboard module: - dashboard-loader.test.ts: 16 tests for findDashboardsDir, listDashboards, loadDashboard, clearDashboardCache, loadAllDashboards, findDashboard - dashboard-renderers.test.ts: 49 tests for formatValue (all formats), getThresholdColor, calculateColumnWidths, and renderView (all view types) - dashboard-sources.test.ts: 31 tests for buildQuery, buildWhereClause, parseDateRange, and postgresSource stub - dashboard-engine.test.ts: 19 tests for executeDashboard, renderDashboard, and showAvailableDashboards with mocked dependencies Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com>
…381) Closes #51 Changes: - db.test.ts: Enable 4 previously skipped baseline tests (saveBaseline, getLatestBaseline, getBaselineByName, listBaselines) — stubs are implemented, tests were incorrectly marked as not-yet-implemented - sessions.test.ts: Add 30 new tests covering file-system operations: findAgentsDir, getSessionsDir, getHistoryFilePath, getActiveSessions, getSessionSummary, startSession, stopSession, updateHeartbeat, cleanupStaleSessions — all use temp dirs to avoid test pollution Also expanded detectSquad, detectAIProcessesFast, getLiveSessionSummaryFast Total: 63 → 104 tests passing, 0 skipped Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com>
Post-execution instructions (branch, commit, PR workflow) now loaded from .agents/config/post-execution.md instead of inline template string in run.ts. Separates prompt content from code. Same pattern as approval-instructions.md. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This reverts commit 9999f92700c02af522e15cae29097a60f249cf15.
…eck (#389) * fix(ci): run CI on PRs to develop — quality gate for agent PRs Agents create PRs targeting develop. Without CI on develop PRs, broken code gets merged undetected. This is the #1 quality gap. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(quality): pre-commit hook runs build + tests on source changes Agents were committing broken code (e.g. #384: tests that fail on import). Now any commit touching .ts/.tsx/.js files must pass both `npm run build` and `npm run test` before the commit goes through. This is the #1 quality gate — prevents slop at the source. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tests): align failing tests with implementation - deploy.test: capture process.stdout.write instead of console.log (deployCommand uses writeLine which writes to stdout) - eval.test: same stdout capture fix for JSON output test - infra.test: use POSTGRES_PORT env var (default 5433) to match docker-compose pattern - local.test: expect port 5432 in DATABASE_URL matching getLocalEnvVars() - setup-checks.test: expect 'warning' (not 'missing') when Docker is not installed, matching checkDockerPrereqs() implementation - Deleted verify-token.test.ts (tested nonexistent verifyToken export) Co-Authored-By: Claude <noreply@anthropic.com> * fix(agents): proper PR workflow — target develop, daemon env, auth check - Post-execution: agents now open PRs targeting `develop` with structured body - Daemon (autonomous.ts): unset CLAUDECODE env to allow nested claude sessions - Auth check: downgrade missing credentials from block to warn (keychain auth) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(run): extract post-execution prompt to template file Post-execution instructions (branch, commit, PR workflow) now loaded from .agents/config/post-execution.md instead of inline template string. Separates prompt content from code. Same pattern as approval-instructions.md. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Add missing env-config.ts (imported by run.ts but never committed) - Fix Commander action spread types with @ts-expect-error directives - Add inquirer type declaration for create command Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
…tines' (#392) Regex only matched '## Routines' exactly, missing Engineering squad's '## Growth Routines' header. Now matches any word before 'Routines'. Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Multi-agent conversation orchestration for squad runs:
- Lead briefs → scanners discover → workers execute → lead reviews → verifiers check
- Shared transcript between agents for context continuity
- Convergence detection (continuation signals beat convergence signals)
- Cost ceiling ($25 default) and max turns (20 default) safety limits
- --task flag for founder directives (replaces lead briefing)
- Transcript persistence to .agents/conversations/{squad}/
New files:
- src/lib/conversation.ts — types, transcript, agent classification, convergence
- src/lib/workflow.ts — turn execution, orchestration loop, transcript persistence
`squads run <squad>` now runs a full conversation instead of just the lead agent.
`squads run <squad> -a <agent>` still runs individual agents (unchanged).
Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(auth): add verifyToken function and passing test suite Closes #384 Adds verifyToken(token, apiUrl) to src/lib/auth.ts: - Calls GET /auth/verify with Bearer token header - Maps snake_case API response to camelCase (display_name→name, subscription_plan→plan) - Returns null on non-ok responses, network errors, and timeouts/aborts - 5-second abort timeout to prevent hanging Creates test/verify-token.test.ts with all 6 specified tests: 1. Returns user data on 200 with snake_case→camelCase mapping 2. Returns null on non-ok response (e.g. 401) 3. Returns null on network error (silent) 4. Returns null on timeout/abort 5. Sends Bearer token in Authorization header 6. Builds correct URL from apiUrl param Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli * fix(auth): update verifyToken signature and response to match API spec Revises the initial implementation based on actual API contract: - Parameter order: verifyToken(apiUrl, token) — apiUrl first - Endpoint: /auth/cli/verify (not /auth/verify) - Response shape: { email, tenantId, tenantSlug, tenantName, status } mapping from snake_case { tenant_id, tenant_slug, tenant_name } - Updates test/verify-token.test.ts to use vi.stubGlobal per-test with afterEach cleanup for better test isolation All 6 tests pass. Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli --------- Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com>
* test(commands): add unit tests for goal and list commands Adds 21 new tests covering: - goal.test.ts (14 tests): goalSetCommand, goalListCommand, goalCompleteCommand, goalProgressCommand — including edge cases for invalid indexes, non-existent squads, metric annotations - list.test.ts (7 tests): JSON output validation, agent counts, no-project error handling, table and agents view rendering Partial fix for #47 — covers 2 of 19 untested command files. Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 * test: add unit tests for feedback and progress commands Closes #47 (partial — 2 of 15 untested commands) Added 19 tests covering: - feedback: add, show, parse history, rating validation, learnings - progress: start/complete tasks, display, verbose mode, task IDs Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 --------- Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com>
…ification - classifyAgent now uses role descriptions from SQUAD.md (primary) with name-based fallback — no more regex substring collisions - Strip **bold** markers from agent names in table parser - Replace regex convergence/continuation signals with phrase matching - "keychain auth" → "OAuth" in run output Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- session.test.ts: 11 tests covering sessionStartCommand, sessionStopCommand, sessionHeartbeatCommand, and detectSquadCommand (start/stop/heartbeat lifecycle, quiet mode, missing .agents dir) - learn.test.ts: 14 tests covering learnCommand, learnShowCommand, and learnSearchCommand (default squad, specific squad, fallback, category inference, tag extraction, search, filters) Part of #47 — adds coverage for 2 more previously untested commands. Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli Co-authored-by: kokevidaurre <kokevidaurre@users.noreply.github.com>
docs: add 8 missing commands to README command reference Adds autonomy, cognition, deploy, detect-squad, exec, orchestrate, session, and version to the README command tables. Closes #557.
Agents were creating PRs with the founder's personal auth, blocking self-approval due to branch protection. Now injects GitHub App bot token so agents operate as bot identity, enabling auto-merge. Also fixes lead merge instruction to use --auto flag (waits for CI). Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
Pause squads with unresolved escalations (blocked/needs-human issues). Grade each execution A-F using heuristics (merged PR=A, no artifacts=F). Feed quality signals into cognition engine. Adjust daemon scoring based on agent quality history — high performers get boosted, slop gets deprioritized. Closes #566, closes #567 Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
…565) Closes #555 Add 40 tests covering all exported functions in src/lib/slack.ts (previously 0% coverage): - slackApi: auth header, POST body, error handling - isSlackConfigured: env var check - getApprovalTier: YAML parsing for auto/notify/approve/confirm tiers - getSquadChannelId: channel lookup and error cases - postNotification: message posting with blocks - postApprovalRequest: approval buttons and notify tier - waitForApproval: reaction polling, context parsing, timeout - requestApprovalAndWait: tier routing and fallback behavior - createSquadChannel: creation, topic setting, name_taken handling - notifyTonightStart/Complete: session notification formatting Co-Authored-By: engineering/issue-solver <engineering-issue-solver@agents-squads.com> Agent: engineering/issue-solver Squad: engineering Model: claude-opus-4-6 Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com>
Closes #553 Add 16 unit tests covering runConversation and saveTranscript: - runConversation: no squads dir, no lead, convergence on lead signal, cost ceiling, max turns, task directive, repo cwd resolution, unclassifiable agent exclusion - saveTranscript: no squads dir returns null, creates dir, skips existing dir, returns .md path, writes turn content, cost estimate, empty transcript, squad name in path Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com>
Closes #554 Add 18 unit tests covering: - checkServiceAvailable: unknown service, container not running, docker error, healthy postgres, guidance show/suppress, health URL fail/pass/non-ok, starting health status - showServiceSetupGuide: unknown service, known service output, setup steps, env vars, all services, footer Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com>
* fix(lint): eliminate 62 ESLint no-unused-vars warnings Closes #550 Removes unused imports and renames unused variables across 10 files. All no-unused-vars warnings reduced from 62 → 0. Remaining 34 warnings are no-explicit-any (tracked in #551). Files changed: - daemon.ts: remove LoopState, SquadSignal, GhIssue, defaultState, getLastRunAge - dashboard.ts: remove formatCostBar, fetchRateLimits - doctor.ts: remove homedir, bold, icons imports - health.ts: rename options → _options (unused param) - run.ts: remove getPRsWithReviewFeedback, buildReviewTask, getBeliefsContext, homedir, checkNewPRs; use empty catch for fail-safe blocks - stats.ts: remove getOutcomeRecords - anthropic.ts: rename skillId → _skillId (stub functions) - cognition.ts: remove execSync import - outcomes.ts: rename unmergedPRs → _unmergedPRs - workflow.ts: remove readFileSync, execAsync, promisify; rename model → _model, stderr → _stderr Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli Model: claude-sonnet-4-6 * fix(lint): restore exec import and add callback types in workflow.ts Re-adds `exec` import removed by lint cleanup (still used at line 194). Adds explicit types to exec callback params to fix TS7006 errors. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Closes #348 Cut verbose features prose (Dashboard, Memory System, Session Detection, Autonomous Execution, Claude Code Integration JSON) and condensed Configuration examples into a quick reference. Kept all command tables, quick start, why squads, providers, project structure, and dev setup. Result: clear getting started in <5 steps, links to docs for advanced topics, all stale Claude Code hooks JSON removed. Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com>
Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com>
Professional README with clear usage, base squads, prerequisites. Remove: old tarball, briefs/, .agents/, dashboard.png. Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
* test(outcomes): add 37 tests for outcome tracking module Closes #574 Covers: - gradeExecution: all grade paths (A, B, C, D, F) with edge cases - computeScorecard: empty records, period filtering, rate calculations - computeAllScorecards: unique agent grouping, sort, persist - getAgentQualityScore: minimum threshold, grade average - getOutcomeScoreModifier: waste/merge/quality modifier thresholds - recordArtifacts: dedup, no-repo guard, gh CLI failures - pollOutcomes: PR/issue state transitions, age-out, graceful failures - getScorecards / getOutcomeRecords: cached reads Co-Authored-By: cli/issue-solver <cli-issue-solver@agents-squads.com> Agent: cli/issue-solver Squad: cli * refactor(test): simplify outcomes.test.ts — extract makeOutcomes() helper - Add makeOutcomes() helper to eliminate 10+ inline outcomes object copies - Replace all { ...makeRecord().outcomes, ... } antipattern with makeOutcomes({ ... }) - Remove redundant mockReadFileSync.mockReturnValue() calls in modifier tests (setupStore() already sets the mock; duplicating it was confusing) - Fix implicit test ordering dependency in bonus modifier test by using explicit setupStore() instead of relying on previous test's mock state All 37 tests pass. Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
Three changes to prevent test file collision during parallel execution: 1. pool: 'forks' in vitest.config.ts — each file runs in its own process, preventing GIT_DIR env var deletions in one file's beforeAll from leaking into other concurrently-running test files. 2. HOME: cwd in runCli env — the CLI reads ~/.squads/config.json via os.homedir(). With HOME=cwd, each test's config writes go to an isolated temp path instead of the shared real home directory. 3. Math.random() suffix on all temp dir names — eliminates same-millisecond collision on machines where Date.now() has low resolution. Closes #578 Co-Authored-By: Claude <noreply@anthropic.com> Agent: cli/issue-solver Squad: cli Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com>
Adds test/commands/run.test.ts covering the exported runCommand and runSquadCommand functions with 22 unit tests across 5 describe blocks: - no squads directory (3 tests) - --cloud flag handling (5 tests) - target not found error paths (5 tests) - preflight provider CLI check (3 tests) - slash syntax parsing (2 tests) - runSquadCommand delegation (3 tests) All tests mock fs, child_process, and all lib modules. Uses SQUADS_SKIP_CHECKS=1 to bypass preflight where needed. Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
#566 (#591) Closes #566 Covers: - hasUnresolvedEscalation: blocked/needs-human label detection, fail-open on gh errors - scoreSquads: PAUSED signal (score=0) for blocked squads, normal scoring for clean squads - classifyRunOutcome: failed/skipped/completed paths - checkCooldown: cooldown enforcement and expiry - defaultState: initial state structure The escalation pause logic was already implemented in squad-loop.ts. This PR adds the missing test coverage to lock in the behavior. Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
…culateSquadCostProjections, and plan detection (#592) - formatCostBar: 7 tests — boundary values, clamping, rounding, width - calculateROIMetrics: 9 tests — cost per goal/commit/PR, ROI multiplier, projections, null handling - calculateSquadCostProjections: 5 tests — null/empty input, multi-squad projections, weekly/monthly ratios - detectPlan/getPlanType/isMaxPlan/getPlanDescription: 17 tests — all env signal paths, priority ordering, descriptions Closes #556 Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
* feat(run): inject SYSTEM.md as immutable Layer 1 in agent prompt - Add loadSystemProtocol() to run-context.ts — reads .agents/SYSTEM.md - Inject SYSTEM.md first in prompt, marked as [IMMUTABLE — NEVER OVERRIDE] - Skip loadApprovalInstructions() and loadPostExecution() when SYSTEM.md loaded - Mark both deprecated functions with @deprecated JSDoc - Graceful fallback: if no SYSTEM.md, legacy config files still used Closes #585 Co-Authored-By: Claude <noreply@anthropic.com> * refactor(run-context): extract readAgentsFile helper, fix abstraction boundary - Extract readAgentsFile() to eliminate boilerplate across 3 loaders - loadSystemProtocol() returns raw content; caller wraps with [IMMUTABLE] markers - loadApprovalInstructions() uses shared helper (removes duplicate find+read+warn) - loadPostExecution() uses shared helper (removes duplicate find+read+warn) - Add verbose log when SYSTEM.md absent (was silent) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
* feat(context): phase-ordered execution with role-based context cascade Implement the full context overhaul for autonomous agent orchestration: - Role-based context (scanner/worker/lead/coo) with token budgets and section gating — scanners get 3 sections, leads get all 10 - Topological phase ordering via depends_on in SQUAD.md frontmatter (Kahn's algorithm, cycle detection, wildcard support) - --phased flag for autopilot: sequential phases, parallel within - Context injection into conversation mode (workflow.ts) - CLAUDECODE env var properly stripped via destructuring (not empty string) - Backward-compatible: priorities.md falls back to goals.md, --phased is opt-in - Pre-commit hook: remove false positives for documented file conventions - README updated with "How Agents Think" context philosophy section - All 1608 tests pass Co-Authored-By: Claude <noreply@anthropic.com> * feat(eval): default post-run COO evaluation after every squad run After any squad or agent execution, the COO (company-lead) automatically evaluates outputs against priorities and directives. Generates feedback.md and active-work.md per squad. Cross-squad assessment for multi-squad runs. - Single squad: `squads run engineering` → eval engineering - Single agent: `squads run engineering/issue-solver` → eval engineering - Autopilot cycle: eval all dispatched squads after each cycle - Skip recursion: company squad runs don't trigger self-evaluation - Opt-out: `--no-eval` flag to skip evaluation Co-Authored-By: Claude <noreply@anthropic.com> * feat(eval): trajectory-aware evaluation with history tracking The COO evaluation now: - Reads previous feedback.md FIRST as baseline (not blank-slate) - Measures direction (improving/stable/declining), not just position - Maintains a history table (last 10 grades) so trajectory is visible - Uses 7-day GitHub window (not 24h) for meaningful trend analysis - Cross-squad review written to cross-squad-review.md - Explicit: "C improving from F > B declining from A" Co-Authored-By: Claude <noreply@anthropic.com> * fix(eval): inject --task directive into runAgent prompt The task option was only wired into conversation mode, not single-agent execution. COO evaluation task was being silently dropped. Now injected as a TASK DIRECTIVE section that overrides default agent behavior. Co-Authored-By: Claude <noreply@anthropic.com> * docs(readme): rewrite intro with architectural vision Position Squads as OS-native alternative to framework-based agent tools. Lead with the three architectural pillars: native LLM CLIs as runtime, filesystem as memory, GitHub as message bus. Co-Authored-By: Claude <noreply@anthropic.com> * fix(run): cleanup worktrees after agent execution Worktrees were created per execution but never removed, accumulating 120+ stale directories. Now cleanup runs in all execution paths: foreground, background, detached, and non-Anthropic providers. Co-Authored-By: Claude <noreply@anthropic.com> * fix: remove hardcoded localhost URLs and Docker references from CLI Source changes: - Replace process.env.SQUADS_BRIDGE_URL || 'http://localhost:8088' with getEnv().bridge_url in sync.ts and autonomy.ts - Replace "Is the bridge running?" and "squads stack up" messages with "squads login" guidance Test updates (27 tests across 6 files): - env-config: default environment is now 'prod', local env has empty URLs - services: checkServiceAvailable uses fetch health checks, not Docker - local: new service interface (url instead of port/healthUrl/configPath) - setup-checks: Docker is optional (always returns 'ok') - templates/memory: match new interfaces and env requirements Co-Authored-By: Claude <noreply@anthropic.com> * fix(lint): use const for non-reassigned Set binding in computePhases Co-Authored-By: Claude <noreply@anthropic.com> * fix: remove Docker/infrastructure leaks from all source files Complete cleanup of internal infrastructure references from OSS CLI: - services.ts: remove Docker container checks, use fetch-based health - local.ts: remove port/healthUrl/configPath, use simple URL-based status - env-config.ts: default to 'prod' environment, local env uses empty URLs - setup-checks.ts: Docker is optional (always returns 'ok') - health.ts, memory.ts, deploy.ts, costs.ts: graceful degradation - cli.ts, approval.ts, context-feed.ts, cost.ts, history.ts, trigger.ts, stack-config.ts, telemetry.ts: minor cleanup Co-Authored-By: Claude <noreply@anthropic.com> * fix(test): set SQUADS_BRIDGE_URL in memory search/extract tests Tests for memorySearchCommand and memoryExtractCommand need bridge URL set to avoid early return from getBridgeUrl() empty check. Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
- Fix ReferenceError: provider is not defined in executeWithClaude - Add missing outcomes.ts, insights.ts, stats.ts from develop - Every squads run crashed on v0.7.0, D1 retention effectively 0% Co-authored-by: Jorge Vidaurre <jorge@agents-squads.com> Co-authored-by: Claude <noreply@anthropic.com>
The pre-commit hook contained client names, personal emails, and financial terms in plaintext — on a public repo. Moved blocked patterns to .husky/.blocked-patterns (gitignored, local-only). Hook reads from external file if present, skips PII check if not. Co-Authored-By: Claude <noreply@anthropic.com>
Hook contained client names and personal data on a public repo. Commenting out entirely until proper local-only solution is in place. Co-Authored-By: Claude <noreply@anthropic.com>
Symlink was accidentally committed. Already in .gitignore. Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Promote develop to main. 74 commits, 10 PRs merged today.