Documents the dual-mode cycle system (issue vs refactor), concurrency
model, worktree isolation, and guidance for modifying the service.
Also adds trigger service files to the file structure convention.
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement Codex CLI agent deployment on Oracle Cloud Infrastructure.
Installs @openai/codex via npm, configures OpenRouter API integration
via OPENAI_BASE_URL proxy.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement Kilo Code agent deployment on Vast.ai. Installs via npm
and configures OpenRouter provider type with API key.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Implement Kilo Code agent deployment on Oracle Cloud Infrastructure.
Sets KILO_PROVIDER_TYPE=openrouter and KILO_OPEN_ROUTER_API_KEY env vars.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Implement Cline agent script for Oracle Cloud Infrastructure.
Installs cline via npm, configures OpenRouter API keys,
and launches interactive cline session.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Issue triggers now spawn lightweight 2-agent runs (15-min timeout) in
isolated worktrees, while refactor cycles continue independently with
the full 6-agent team (30-min timeout). Duplicate issue runs are
rejected with 409.
- trigger-server.ts: pass SPAWN_ISSUE/SPAWN_REASON env vars to script,
add issue dedup (409), include issue in health/trigger responses
- refactor.sh: dual-mode (issue vs refactor) with isolated worktrees,
mode-specific prompts and timeouts, scoped cleanup
- start-refactor.sh: set MAX_CONCURRENT=3 (gitignored, local only)
- refactor.yml: handle 409 alongside existing 429
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement NanoClaw agent deployment on Oracle Cloud Infrastructure.
Installs tsx and clones nanoclaw repo, configures .env with Anthropic
API key proxied through OpenRouter, launches WhatsApp QR auth flow.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement Plandex agent deployment on Vast.ai. Installs via official
install script and verifies installation before launching.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Implement NanoClaw (WhatsApp AI agent) deployment on Vast.ai GPU instances.
Sources vastai/lib/common.sh, installs tsx and clones nanoclaw repo,
creates .env with Anthropic API key, and launches with npm run dev.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement Amazon Q CLI agent script for Oracle Cloud Infrastructure.
Installs Amazon Q via official installer, configures OpenRouter API keys,
and launches interactive q chat session.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement OpenClaw agent deployment on Oracle Cloud Infrastructure.
Uses OCI CLI for provisioning, installs openclaw via bun, configures
OpenRouter API integration with gateway+TUI launch.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement OpenClaw deployment on Vast.ai GPU instances.
Sources vastai/lib/common.sh, installs openclaw via bun,
configures OpenRouter API with model selection, starts
gateway in background and launches TUI.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement OpenCode agent deployment on Vast.ai. Uses opencode_install_cmd
from shared/common.sh for installation and injects OpenRouter API key.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Implement Gemini CLI agent script for Oracle Cloud Infrastructure.
Installs @google/gemini-cli via npm, configures OpenRouter API keys,
and launches interactive gemini session.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fixes#137 - The description incorrectly stated OpenClaw was "OpenRouter's
agent framework". OpenClaw is a personal AI assistant, not created by
OpenRouter.
Agent: team-lead
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Extract _generate_csrf_state() from try_oauth_flow() (8-line conditional -> 1-line call)
- Deduplicate retry loop: extract _cloud_api_retry_loop() shared by generic_cloud_api() and generic_cloud_api_custom_auth() (removed 26 duplicated lines)
- Extract OAuth HTML into bash variables with shared CSS, reducing inline string complexity in start_oauth_server()
Net reduction: 11 lines, eliminates copy-paste duplication in the API retry logic.
Agent: complexity-hunter
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fixes#132 - Some terminals can't render the unicode characters used by
@clack/prompts for bullets, selectors, and box drawing. This adds a
unicode detection module that runs before @clack/prompts is imported,
forcing ASCII mode when:
- SPAWN_NO_UNICODE=1 or SPAWN_ASCII=1 is set (explicit override)
- TERM is "dumb" or unset (common in basic terminals)
Also adds a troubleshooting hint in the help text.
Agent: ux-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Discovery cycles run 1-2h+, 2h was too aggressive. 4h gives headroom
while still catching truly hung processes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tests the actual exported cmdRun and cmdAgentInfo functions (not inline
replicas) for their process.exit error paths: identifier validation
(injection, path traversal, length), unknown agent/cloud handling,
unimplemented combination suggestions, prompt security validation,
and empty input handling.
Agent: test-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds Vast.ai as a new cloud provider (GPU marketplace with per-hour pricing).
Implements vastai/lib/common.sh with provider primitives using the vastai CLI,
and adds 3 initial agent scripts (claude, aider, codex). Remaining 11 agents
added as "missing" matrix entries.
Agent: cloud-scout
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Add OCI as a new cloud provider using the OCI CLI for compute instance
provisioning. Includes lib/common.sh with full lifecycle management
(create, SSH, cloud-init, destroy) and auto-creates VCN/subnet if needed.
Implements claude, aider, and goose agent scripts. Supports Always Free
tier shapes (VM.Standard.E2.1.Micro) and flex shapes.
Agent: cloud-scout
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All 14 agents are now implemented on all 21 clouds.
Previously the OVH column showed gaps and Kilo Code
showed only Sprite — now every cell is checked.
Agent: team-lead
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tests the actual exported command functions end-to-end using mock.module
for @clack/prompts and loadManifest(true) to force cache refresh with
mocked fetch data. Covers matrix display, agent/cloud listing, agent
info output, and help text content verification.
Agent: test-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Haiku 4.5 <noreply@anthropic.com>
MODAL_SANDBOX_ID and sandbox name were interpolated directly into
Python code strings, allowing potential code injection. Now all
user-controlled values are passed via environment variables and
read with os.environ in Python.
Changes:
- create_server: pass name/image via _MODAL_NAME/_MODAL_IMAGE env vars,
use getattr() for image lookup, add sandbox name validation
- run_server: pass sandbox ID and command via env vars
- interactive_session: pass sandbox ID and command via env vars
- destroy_server: pass sandbox ID via env var
- Add validate_sandbox_id() to enforce sb-<alphanumeric> format
- upload_file: remove printf '%q' escaping (base64 is safe)
Agent: security-auditor
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement ovh/cline.sh and ovh/gptme.sh using OVH
primitives. Both scripts provision an OVHcloud instance,
install the agent, inject OpenRouter credentials, and
launch an interactive session.
Agent: gap-filler
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- OAuth failures now explain WHY they failed (timeout, port conflict,
no runtime, network) and suggest specific fixes
- Add duration hints to long-running operations (SSH wait: 30-90s,
OAuth: 10-30s) so users know what to expect
- validateImplementation shows exact `spawn <agent> <cloud>` commands
users can run instead of just listing cloud names
- SSH wait failure suggests checking cloud provider dashboard
Agent: ux-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Civo: Extract build_create_instance_body() for JSON body construction
and wait_for_civo_instance() for the status polling loop, reducing
create_server() from 113 to 53 lines.
Kamatera: Extract validate_kamatera_params() for input validation and
build_kamatera_server_body() for JSON body construction, reducing
create_server() from 107 to 62 lines.
Agent: complexity-hunter
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement ovh/goose.sh and ovh/interpreter.sh using OVH
primitives. Both scripts provision an OVHcloud instance,
install the agent, inject OpenRouter credentials, and
launch an interactive session.
Agent: gap-filler-2
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement ovh/opencode.sh and ovh/plandex.sh using OVH
primitives. Both scripts provision an OVHcloud instance,
install the agent, inject OpenRouter credentials, and
launch an interactive session.
Agent: gap-filler-5
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement ovh/gemini.sh and ovh/amazonq.sh using OVH
primitives. Both scripts provision an OVHcloud instance,
install the agent, inject OpenRouter credentials, and
launch an interactive session.
Agent: gap-filler-3
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement ovh/openclaw.sh and ovh/nanoclaw.sh using OVH
primitives from lib/common.sh. Both scripts provision an
OVHcloud instance, install the agent, inject OpenRouter
credentials, and launch an interactive session.
Agent: gap-filler-1
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Default RUN_TIMEOUT_MS increased to 7200000 (2h) based on observed
team cycle durations of 1-2 hours
- SKILL.md now documents the data-driven tuning approach: start high
(6-12h), collect log data, then tune down to 2x longest observed cycle
- Updated health/trigger response docs and workflow template with
429-tolerant curl pattern
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The prompt-based 15-minute time budget was advisory only — cycles could
run for hours (9.5h observed on Feb 9). Now:
- refactor.sh wraps `claude -p` in `timeout 1200` (20 min) with SIGTERM
then SIGKILL after 60s grace. Distinguishes timeout vs failure in logs.
- trigger-server.ts adds a 60-second interval timer that proactively
reaps stale runs instead of only checking on incoming requests.
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add legend to `spawn list` matrix output (+ implemented, - not yet available)
- Show cloud identifier keys in `spawn <agent>` info output for easy copy-paste
- Add CLI shortcut hint in interactive mode after selection
- Add agent descriptions to `spawn agents` output
- Add agent counts to `spawn clouds` output for consistency
- Fix misleading "Updating" spinner in `spawn update` (it only checks)
- Add `spawn help` to help text command listing
- Improve footer hints in agents/clouds output with actionable commands
Agent: ux-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Before checking concurrency, the trigger server now:
- Checks if tracked processes are actually alive (kill -0)
- Reaps dead processes that exited without cleanup
- Kills runs that exceed RUN_TIMEOUT_MS (default 30min)
Health endpoint now reports per-run details (pid, age, reason).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When MAX_CONCURRENT=1 and a cycle is in progress, the trigger server
returns 429. This is expected behavior, not an error — the previous
curl -f treated it as failure (exit code 22).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tests the extractFlagValue generic function and the full CLI flag
extraction pipeline (--prompt/-p and --prompt-file). Existing tests
in index-parsing.test.ts and index-edge-cases.test.ts use simplified
re-implementations; these tests cover the exact behavior including
error messages, process.exit on missing values, startsWith("-") guard,
sequential two-pass extraction, and edge cases with flag-like values.
Agent: test-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
