el-j/nexus-orchestrator — Submit AI Task

Submit a code-generation task to a nexus-orchestrator daemon and poll for completion. Optionally downloads and starts a local daemon. Integrates with el-j/agency-agents for specialist agent identities (single agent, named swarm, or whole category).

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
instructionTask instruction text sent to the LLM. Mutually exclusive with task_file — use one or the other. no""
task_filePath to a task file (.md / .txt) whose content is used as the instruction. Useful for multi-line prompts stored as repository files. no""
project_pathAbsolute project root for per-project session memory isolation. Defaults to $GITHUB_WORKSPACE (the checked-out repository root). no""
target_fileRelative path of the file the LLM should write or update (e.g. "src/utils/helpers.go"). Optional — omit for plan/analysis tasks. no""
context_filesComma-separated list of relative file paths to include as read context alongside the instruction (e.g. "go.mod,internal/core/domain/task.go"). no""
commandTask command type: "plan" (orchestration / documentation) or "execute" (code implementation). Default: execute. noexecute
modelLLM model override sent with the task (e.g. "gpt-4o", "claude-3-5-sonnet-20241022", "llama3"). no""
providerProvider hint for routing the task (e.g. "openai", "anthropic", "ollama", "lmstudio"). no""
agentLoad a single specialist agent from el-j/agency-agents by slug or name. Examples: "engineering-backend-architect", "backend-architect", "Frontend Developer". Mutually exclusive with agents / agent_category. The agent's system prompt is automatically prepended to the instruction. no""
agentsComma-separated list of agent slugs/names for swarm mode (e.g. "engineering-backend-architect,engineering-frontend-developer"). A combined orchestrator prompt is generated from all agents. Mutually exclusive with agent / agent_category. no""
agent_categoryLoad ALL agents from a specific category from el-j/agency-agents (e.g. "engineering", "design", "testing"). A combined swarm prompt is generated. Mutually exclusive with agent / agents. no""
agent_refGit ref (branch, tag, or SHA) of el-j/agency-agents to fetch identities from. Default: "main". nomain
system_promptRaw agent system prompt prepended to the instruction. Takes precedence over agent / agents / agent_category when set. Use this to chain with el-j/agency-agents manually: - uses: el-j/agency-agents@main id: ag with: agent: backend-architect - uses: el-j/nexus-orchestrator@v1 with: system_prompt: ${{ steps.ag.outputs.system_prompt }} instruction: 'Refactor auth to use JWT' no""
daemon_urlHTTP base URL of a running nexus-daemon. Used only when start_daemon is "false". nohttp://127.0.0.1:63987
start_daemonDownload and start a local nexus-daemon for the duration of this job. Set to "false" to connect to an existing remote daemon via daemon_url. notrue
nexus_versionnexus-orchestrator release version to install (e.g. "v0.2.0"; defaults to "latest"). nolatest
timeout_secondsMaximum seconds to wait for the task to reach a terminal status before the step fails. no300
openai_api_keyOpenAI API key — enables GPT models on the local daemon.no""
openai_modelOpenAI model override (default: gpt-4o-mini). Requires openai_api_key.no""
anthropic_api_keyAnthropic API key — enables Claude models on the local daemon.no""
anthropic_modelAnthropic model override (default: claude-3-5-sonnet-20241022). Requires anthropic_api_key. no""
github_copilot_tokenGitHub Copilot token — enables GPT-4o via Copilot on the local daemon.no""
github_copilot_modelCopilot model override (default: gpt-4o). Requires github_copilot_token.no""
namedescription
task_idUUID of the submitted task.
statusFinal task status: COMPLETED, FAILED, CANCELLED, or TOO_LARGE.
logsLLM output and execution logs for the completed task.