@chankov/agent-fleet 0.0.1 → 0.0.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude/commands/doctor-agent-fleet.md +1 -1
- package/.claude/commands/setup-agent-fleet.md +4 -4
- package/.opencode/commands/af-doctor-agent-fleet.md +2 -0
- package/.opencode/commands/af-setup-agent-fleet.md +1 -1
- package/.pi/agents/model-profiles.yaml +12 -12
- package/.pi/agents/peers.yaml +26 -22
- package/.pi/agents/teams.yaml +2 -2
- package/.pi/harnesses/agent-hub/README.md +57 -4
- package/.pi/harnesses/agent-hub/index.ts +236 -80
- package/.pi/harnesses/agent-hub/research-retention.js +34 -0
- package/.pi/harnesses/ask-user-remote/README.md +8 -0
- package/.pi/harnesses/ask-user-remote/index.ts +41 -1
- package/.pi/harnesses/coms/README.md +11 -0
- package/.pi/prompts/doctor-agent-fleet.md +1 -1
- package/.pi/prompts/setup-agent-fleet.md +4 -4
- package/README.md +133 -354
- package/agents/architect.md +4 -2
- package/agents/bowser.md +2 -1
- package/agents/builder.md +3 -2
- package/agents/code-reviewer.md +7 -7
- package/agents/deep-researcher.md +3 -3
- package/agents/documenter.md +3 -1
- package/agents/orchestrator.md +5 -3
- package/agents/plan-reviewer.md +5 -5
- package/agents/planner.md +7 -7
- package/agents/releaser.md +3 -1
- package/agents/researcher.md +3 -3
- package/agents/security-auditor.md +7 -7
- package/agents/test-engineer.md +5 -5
- package/agents/web-debugger.md +3 -3
- package/agents/web-performance-auditor.md +3 -3
- package/bin/snapshot-version.js +17 -1
- package/codex/CONDUCTOR.md +148 -0
- package/docs/ARCHITECTURE.md +165 -0
- package/docs/agent-fleet-setup.md +1 -0
- package/docs/claude-code-coms-bridge.md +10 -0
- package/docs/codex-remote-conductor.md +170 -0
- package/docs/coms-hermes-bridge.md +121 -0
- package/docs/getting-started.md +14 -0
- package/docs/npm-install.md +2 -0
- package/docs/pi-extensions.md +16 -0
- package/docs/pi-setup.md +2 -0
- package/hermes/README.md +48 -0
- package/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/justfile +132 -15
- package/package.json +10 -3
- package/scripts/codex-conductor.ts +41 -0
- package/scripts/codex-remote-control.ts +167 -0
- package/scripts/coms-cli.ts +311 -199
- package/scripts/coms-hermes-bridge.ts +8 -4
- package/scripts/lib/codex-conductor.ts +88 -0
- package/scripts/lib/codex-remote-control.ts +480 -0
- package/scripts/lib/coms-envelope.ts +51 -6
- package/scripts/lib/herdr-layout.ts +35 -7
- package/scripts/lib/hermes-bridge-core.ts +4 -4
- package/scripts/lib/spawn-stagger.ts +101 -0
- package/scripts/lib/team-project.ts +112 -3
- package/scripts/lib/team-snapshot.ts +3 -2
- package/scripts/team-snapshot.ts +23 -6
- package/scripts/team-up.ts +106 -18
- package/skills/guided-workspace-setup/SKILL.md +123 -97
- package/skills/guided-workspace-setup/companion-manifest.json +33 -0
- package/skills/peer-coms/SKILL.md +9 -0
- package/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
package/agents/architect.md
CHANGED
|
@@ -1,11 +1,13 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: architect
|
|
3
3
|
description: System architect — owns design decisions and migration strategy; answers design questions with concrete, justified recommendations.
|
|
4
|
-
model: openai-codex/gpt-5.
|
|
4
|
+
model: openai-codex/gpt-5.6-sol
|
|
5
5
|
models:
|
|
6
|
+
- openai-codex/gpt-5.6-terra
|
|
7
|
+
- openai-codex/gpt-5.6-luna
|
|
6
8
|
- ollama/nemotron-3-ultra:cloud
|
|
7
9
|
- ollama/glm-5.2:cloud
|
|
8
|
-
thinking:
|
|
10
|
+
thinking: high
|
|
9
11
|
---
|
|
10
12
|
|
|
11
13
|
# Architect (coms peer)
|
package/agents/bowser.md
CHANGED
|
@@ -2,8 +2,9 @@
|
|
|
2
2
|
name: bowser
|
|
3
3
|
description: Headless browser automation agent using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, or web scraping. Supports parallel instances. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel, bowser.
|
|
4
4
|
tools: read,bash
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-luna
|
|
6
6
|
models:
|
|
7
|
+
- openai-codex/gpt-5.6-terra
|
|
7
8
|
- ollama/minimax-m3:cloud
|
|
8
9
|
- ollama/nemotron-3-ultra:cloud
|
|
9
10
|
color: orange
|
package/agents/builder.md
CHANGED
|
@@ -2,9 +2,10 @@
|
|
|
2
2
|
name: builder
|
|
3
3
|
description: Implementation and code generation — lands changes in small verifiable increments. Use for implementing features, fixes, and refactors once the task is defined.
|
|
4
4
|
tools: read,write,edit,bash,grep,find,ls
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-terra
|
|
6
6
|
models:
|
|
7
|
-
- openai-codex/gpt-5.
|
|
7
|
+
- openai-codex/gpt-5.6-sol
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
8
9
|
- openai-codex/gpt-5.3-codex-spark
|
|
9
10
|
- ollama/minimax-m3:cloud
|
|
10
11
|
- ollama/kimi-k2.7-code:cloud
|
package/agents/code-reviewer.md
CHANGED
|
@@ -2,11 +2,11 @@
|
|
|
2
2
|
name: code-reviewer
|
|
3
3
|
description: Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
|
|
4
4
|
tools: read,bash,grep,find,ls
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-terra
|
|
6
6
|
models:
|
|
7
7
|
- github-copilot/claude-opus-4.8
|
|
8
|
-
- openai-codex/gpt-5.
|
|
9
|
-
- openai-codex/gpt-5.
|
|
8
|
+
- openai-codex/gpt-5.6-sol
|
|
9
|
+
- openai-codex/gpt-5.6-luna
|
|
10
10
|
- github-copilot/claude-sonnet-4.6
|
|
11
11
|
- github-copilot/claude-haiku-4.5
|
|
12
12
|
- ollama/nemotron-3-ultra:cloud
|
|
@@ -17,16 +17,16 @@ thinking: high
|
|
|
17
17
|
delegate_depth: 1
|
|
18
18
|
subagents:
|
|
19
19
|
preflight:
|
|
20
|
-
model: openai-codex/gpt-5.
|
|
20
|
+
model: openai-codex/gpt-5.6-luna
|
|
21
21
|
tools: read,grep,find,ls
|
|
22
22
|
quality:
|
|
23
|
-
model: openai-codex/gpt-5.
|
|
23
|
+
model: openai-codex/gpt-5.6-terra
|
|
24
24
|
tools: read,grep,find,ls
|
|
25
25
|
perf:
|
|
26
|
-
model: openai-codex/gpt-5.
|
|
26
|
+
model: openai-codex/gpt-5.6-terra
|
|
27
27
|
tools: read,grep,find,ls
|
|
28
28
|
docs:
|
|
29
|
-
model: openai-codex/gpt-5.
|
|
29
|
+
model: openai-codex/gpt-5.6-luna
|
|
30
30
|
tools: read,grep,find,ls
|
|
31
31
|
---
|
|
32
32
|
|
|
@@ -3,10 +3,10 @@ name: deep-researcher
|
|
|
3
3
|
description: Read-only deep reconnaissance for hard, ambiguous, or high-stakes questions — traces cross-cutting call paths, maps unfamiliar subsystems, and synthesizes findings across many files with file:line citations. Never edits or runs commands.
|
|
4
4
|
tools: read,grep,find,ls
|
|
5
5
|
kind: research
|
|
6
|
-
model: openai-codex/gpt-5.
|
|
6
|
+
model: openai-codex/gpt-5.6-sol
|
|
7
7
|
models:
|
|
8
|
-
- openai-codex/gpt-5.
|
|
9
|
-
- openai-codex/gpt-5.
|
|
8
|
+
- openai-codex/gpt-5.6-terra
|
|
9
|
+
- openai-codex/gpt-5.6-luna
|
|
10
10
|
- ollama/nemotron-3-ultra:cloud
|
|
11
11
|
- ollama/glm-5.2:cloud
|
|
12
12
|
thinking: high
|
package/agents/documenter.md
CHANGED
|
@@ -2,8 +2,10 @@
|
|
|
2
2
|
name: documenter
|
|
3
3
|
description: Documentation and README generation
|
|
4
4
|
tools: read,write,edit,grep,find,ls
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-terra
|
|
6
6
|
models:
|
|
7
|
+
- openai-codex/gpt-5.6-luna
|
|
8
|
+
- openai-codex/gpt-5.3-codex-spark
|
|
7
9
|
- ollama/glm-5.2:cloud
|
|
8
10
|
- ollama/nemotron-3-ultra:cloud
|
|
9
11
|
thinking: minimal
|
package/agents/orchestrator.md
CHANGED
|
@@ -2,8 +2,10 @@
|
|
|
2
2
|
name: orchestrator
|
|
3
3
|
description: Verification-Contract orchestrator — plans, builds, and verifies in small slices, owns the acceptance assertions, and requires runtime proof before "done"; biased to correctness and reversibility, confirms before risky steps.
|
|
4
4
|
kind: orchestrator
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-sol
|
|
6
6
|
models:
|
|
7
|
+
- openai-codex/gpt-5.6-terra
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
7
9
|
- ollama/minimax-m3:cloud
|
|
8
10
|
- ollama/nemotron-3-ultra:cloud
|
|
9
11
|
thinking: xhigh
|
|
@@ -30,8 +32,8 @@ Before any non-trivial work, read `skills/orchestration-verification/SKILL.md`
|
|
|
30
32
|
- **Recon before action.** When a request touches unfamiliar code, dispatch a researcher to map the terrain before dispatching a builder.
|
|
31
33
|
- **Plan explicitly.** For anything beyond a trivial change, dispatch a planner (and a plan reviewer if the team has one) before any implementation. Relay document artifacts by path: plans, reviews, inventories, critiques, and evidence reports should be written under the real session path `.pi/agent-sessions/artifacts/<kind>/<agentKey>-run<N>.md` and passed downstream as artifact-relative `artifacts/<kind>/<agentKey>-run<N>.md` paths (while preserving planner PLAN_FILE behavior). Downstream dispatches should receive those paths through `artifacts: [...]` instead of pasted document bodies.
|
|
32
34
|
- **Gate work through skills.** Before implementation or risky work, require skill discovery via `skills/using-agent-skills/SKILL.md`; unclear requirements go through spec/planning skills first, implementation tasks need plan/review gates, and security-sensitive work includes `security-and-hardening`. Name the selected skills in specialist tasks and ask each specialist to report which skills they followed plus verification evidence. Skills are active workflows, not passive docs.
|
|
33
|
-
- **Light research for simple reads.** For low-risk, read-only recon — simple counts, grep/search, docs reading, quick summaries — use `spawn_research(persona: "researcher")` (
|
|
34
|
-
- **Deep research for hard reconnaissance.** For ambiguous, cross-cutting, or high-stakes investigation — the parity inventory above, tracing tricky call paths, mapping unfamiliar subsystems, security-relevant reads, or weighing many files before a big change — use `spawn_research(persona: "deep-researcher")` (`gpt-5.
|
|
35
|
+
- **Light research for simple reads.** For low-risk, read-only recon — simple counts, grep/search, docs reading, quick summaries — use `spawn_research(persona: "researcher")` (`openai-codex/gpt-5.6-luna` with low thinking for simple, low-risk read-only recon).
|
|
36
|
+
- **Deep research for hard reconnaissance.** For ambiguous, cross-cutting, or high-stakes investigation — the parity inventory above, tracing tricky call paths, mapping unfamiliar subsystems, security-relevant reads, or weighing many files before a big change — use `spawn_research(persona: "deep-researcher")` (`openai-codex/gpt-5.6-sol` with high thinking). When evidence is thin, prefer a deep pass over guessing.
|
|
35
37
|
- **Escalate non-research complexity by persona.** For architecture planning, complex debugging, security audits, large refactors, or deep code review, dispatch the appropriate specialist — `dispatch_agent` takes no model argument, so routing IS persona selection.
|
|
36
38
|
- **Personas carry their own model.** Both research personas bring their own model/thinking; any `model` argument is ignored when a `persona` is set. Pick the persona that fits the task — don't pass raw model strings.
|
|
37
39
|
- **Use advisory dispatch scope for builders.** When dispatching a builder for a planned implementation task, derive `scope: [...]` from that task's file list/path inventory so side-changes are surfaced. Skip `scope` for exploratory, planning, or reconnaissance work where the file set is not known. Scope violations are advisory only: the hub reports `details.scopeViolations` and a warning, but never auto-reverts, auto-escalates, or blocks progress. Concurrent writable dispatches have approximate attribution; treat overlap warnings as "inspect the diff" rather than proof of which agent changed which file.
|
package/agents/plan-reviewer.md
CHANGED
|
@@ -2,20 +2,20 @@
|
|
|
2
2
|
name: plan-reviewer
|
|
3
3
|
description: Plan critic — reviews, challenges, and validates implementation plans
|
|
4
4
|
tools: read,grep,find,ls
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-sol
|
|
6
6
|
models:
|
|
7
|
-
- openai-codex/gpt-5.
|
|
8
|
-
- openai-codex/gpt-5.
|
|
7
|
+
- openai-codex/gpt-5.6-terra
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
9
9
|
- ollama/nemotron-3-ultra:cloud
|
|
10
10
|
- ollama/glm-5.2:cloud
|
|
11
11
|
thinking: high
|
|
12
12
|
delegate_depth: 1
|
|
13
13
|
subagents:
|
|
14
14
|
feasibility:
|
|
15
|
-
model: openai-codex/gpt-5.
|
|
15
|
+
model: openai-codex/gpt-5.6-terra
|
|
16
16
|
tools: read,grep,find,ls
|
|
17
17
|
deps:
|
|
18
|
-
model: openai-codex/gpt-5.
|
|
18
|
+
model: openai-codex/gpt-5.6-luna
|
|
19
19
|
tools: read,grep,find,ls
|
|
20
20
|
---
|
|
21
21
|
You are a plan reviewer agent. Your job is to critically evaluate implementation plans.
|
package/agents/planner.md
CHANGED
|
@@ -2,23 +2,23 @@
|
|
|
2
2
|
name: planner
|
|
3
3
|
description: Architecture and implementation planning — produces a written PLAN file with dependency-ordered tasks and acceptance criteria. Use when work spans multiple files or needs a task breakdown before building.
|
|
4
4
|
tools: read,grep,find,ls,bash,write
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-sol
|
|
6
6
|
models:
|
|
7
|
-
- openai-codex/gpt-5.
|
|
8
|
-
- openai-codex/gpt-5.
|
|
7
|
+
- openai-codex/gpt-5.6-terra
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
9
9
|
- ollama/nemotron-3-ultra:cloud
|
|
10
10
|
- ollama/glm-5.2:cloud
|
|
11
|
-
thinking:
|
|
11
|
+
thinking: high
|
|
12
12
|
delegate_depth: 1
|
|
13
13
|
subagents:
|
|
14
14
|
scout:
|
|
15
|
-
model: openai-codex/gpt-5.
|
|
15
|
+
model: openai-codex/gpt-5.6-luna
|
|
16
16
|
tools: read,grep,find,ls
|
|
17
17
|
rules:
|
|
18
|
-
model: openai-codex/gpt-5.
|
|
18
|
+
model: openai-codex/gpt-5.6-luna
|
|
19
19
|
tools: read,grep,find,ls
|
|
20
20
|
risk:
|
|
21
|
-
model: openai-codex/gpt-5.
|
|
21
|
+
model: openai-codex/gpt-5.6-terra
|
|
22
22
|
tools: read,grep,find,ls
|
|
23
23
|
---
|
|
24
24
|
You are a planner agent. Analyze requirements and produce a clear, actionable implementation plan, delivered as a written plan document.
|
package/agents/releaser.md
CHANGED
|
@@ -2,8 +2,10 @@
|
|
|
2
2
|
name: releaser
|
|
3
3
|
description: Release owner — cuts versions and ships; runs the changeset → version-bump → tag flow on request.
|
|
4
4
|
color: #059669
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-terra
|
|
6
6
|
models:
|
|
7
|
+
- openai-codex/gpt-5.6-sol
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
7
9
|
- ollama/glm-5.2:cloud
|
|
8
10
|
- ollama/nemotron-3-ultra:cloud
|
|
9
11
|
thinking: low
|
package/agents/researcher.md
CHANGED
|
@@ -3,10 +3,10 @@ name: researcher
|
|
|
3
3
|
description: Read-only reconnaissance — searches code, reads files and docs, and reports findings with file:line citations. Never edits or runs commands.
|
|
4
4
|
tools: read,grep,find,ls
|
|
5
5
|
kind: research
|
|
6
|
-
model: openai-codex/gpt-5.
|
|
6
|
+
model: openai-codex/gpt-5.6-luna
|
|
7
7
|
models:
|
|
8
|
-
- openai-codex/gpt-5.
|
|
9
|
-
- openai-codex/gpt-5.
|
|
8
|
+
- openai-codex/gpt-5.6-sol
|
|
9
|
+
- openai-codex/gpt-5.6-terra
|
|
10
10
|
- ollama/nemotron-3-ultra:cloud
|
|
11
11
|
- ollama/minimax-m3:cloud
|
|
12
12
|
thinking: low
|
|
@@ -2,23 +2,23 @@
|
|
|
2
2
|
name: security-auditor
|
|
3
3
|
description: Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
|
|
4
4
|
tools: read,bash,grep,find,ls
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-sol
|
|
6
6
|
models:
|
|
7
|
-
- openai-codex/gpt-5.
|
|
8
|
-
- openai-codex/gpt-5.
|
|
7
|
+
- openai-codex/gpt-5.6-terra
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
9
9
|
- ollama/nemotron-3-ultra:cloud
|
|
10
10
|
- ollama/glm-5.2:cloud
|
|
11
|
-
thinking:
|
|
11
|
+
thinking: high
|
|
12
12
|
delegate_depth: 1
|
|
13
13
|
subagents:
|
|
14
14
|
recon:
|
|
15
|
-
model: openai-codex/gpt-5.
|
|
15
|
+
model: openai-codex/gpt-5.6-luna
|
|
16
16
|
tools: read,grep,find,ls
|
|
17
17
|
input-sweep:
|
|
18
|
-
model: openai-codex/gpt-5.
|
|
18
|
+
model: openai-codex/gpt-5.6-terra
|
|
19
19
|
tools: read,grep,find,ls
|
|
20
20
|
secrets-sweep:
|
|
21
|
-
model: openai-codex/gpt-5.
|
|
21
|
+
model: openai-codex/gpt-5.6-luna
|
|
22
22
|
tools: read,grep,find,ls
|
|
23
23
|
---
|
|
24
24
|
|
package/agents/test-engineer.md
CHANGED
|
@@ -2,10 +2,10 @@
|
|
|
2
2
|
name: test-engineer
|
|
3
3
|
description: QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
|
|
4
4
|
tools: read,write,edit,bash,grep,find,ls
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-terra
|
|
6
6
|
models:
|
|
7
|
-
- openai-codex/gpt-5.
|
|
8
|
-
- openai-codex/gpt-5.
|
|
7
|
+
- openai-codex/gpt-5.6-sol
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
9
9
|
- ollama/kimi-k2.7-code:cloud
|
|
10
10
|
- ollama/glm-5.2:cloud
|
|
11
11
|
- ollama/nemotron-3-ultra:cloud
|
|
@@ -13,10 +13,10 @@ thinking: medium
|
|
|
13
13
|
delegate_depth: 1
|
|
14
14
|
subagents:
|
|
15
15
|
coverage-scout:
|
|
16
|
-
model: openai-codex/gpt-5.
|
|
16
|
+
model: openai-codex/gpt-5.6-luna
|
|
17
17
|
tools: read,grep,find,ls
|
|
18
18
|
conventions:
|
|
19
|
-
model: openai-codex/gpt-5.
|
|
19
|
+
model: openai-codex/gpt-5.6-luna
|
|
20
20
|
tools: read,grep,find,ls
|
|
21
21
|
---
|
|
22
22
|
|
package/agents/web-debugger.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: web-debugger
|
|
3
3
|
description: Interactive headful Chrome debugging via Chrome DevTools MCP — live DOM snapshots, console, network, and performance traces. Use when you need runtime-UI verification in a real browser, network/console inspection, or performance profiling with a human in the loop. Runs as a coms peer that loads the chrome-devtools-mcp extension. Keywords - chrome, devtools, headful, debug, network, console, performance, runtime-ui, profiling.
|
|
4
|
-
model: openai-codex/gpt-5.
|
|
4
|
+
model: openai-codex/gpt-5.6-terra
|
|
5
5
|
models:
|
|
6
|
-
- openai-codex/gpt-5.
|
|
7
|
-
- openai-codex/gpt-5.
|
|
6
|
+
- openai-codex/gpt-5.6-sol
|
|
7
|
+
- openai-codex/gpt-5.6-luna
|
|
8
8
|
- ollama/glm-5.2:cloud
|
|
9
9
|
color: cyan
|
|
10
10
|
skills:
|
|
@@ -2,10 +2,10 @@
|
|
|
2
2
|
name: web-performance-auditor
|
|
3
3
|
description: Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
|
|
4
4
|
tools: read,bash,grep,find,ls
|
|
5
|
-
model: openai-codex/gpt-5.
|
|
5
|
+
model: openai-codex/gpt-5.6-terra
|
|
6
6
|
models:
|
|
7
|
-
- openai-codex/gpt-5.
|
|
8
|
-
- openai-codex/gpt-5.
|
|
7
|
+
- openai-codex/gpt-5.6-sol
|
|
8
|
+
- openai-codex/gpt-5.6-luna
|
|
9
9
|
- ollama/nemotron-3-ultra:cloud
|
|
10
10
|
- ollama/glm-5.2:cloud
|
|
11
11
|
thinking: high
|
package/bin/snapshot-version.js
CHANGED
|
@@ -27,6 +27,9 @@ const ARTIFACT_PATHS = [
|
|
|
27
27
|
"skills",
|
|
28
28
|
"vendor/agent-skills-upstream",
|
|
29
29
|
"agents",
|
|
30
|
+
"codex",
|
|
31
|
+
"hermes",
|
|
32
|
+
"systemd",
|
|
30
33
|
".claude/commands",
|
|
31
34
|
".claude/orchestrate-teams.yaml",
|
|
32
35
|
".opencode/commands",
|
|
@@ -46,6 +49,19 @@ const ARTIFACT_PATHS = [
|
|
|
46
49
|
// per-version copy for the upgrade three-way diff (retired-harness recipes
|
|
47
50
|
// pruned, new-harness recipes added on refresh).
|
|
48
51
|
"justfile",
|
|
52
|
+
// Snapshot only documentation shipped at the package root. Copying the
|
|
53
|
+
// whole directory would put non-installed docs into the three-way base.
|
|
54
|
+
"docs/agent-fleet-setup.md",
|
|
55
|
+
"docs/ARCHITECTURE.md",
|
|
56
|
+
"docs/codex-remote-conductor.md",
|
|
57
|
+
"docs/claude-code-coms-bridge.md",
|
|
58
|
+
"docs/coms-hermes-bridge.md",
|
|
59
|
+
"docs/pi-extensions.md",
|
|
60
|
+
"docs/npm-install.md",
|
|
61
|
+
"docs/skill-anatomy.md",
|
|
62
|
+
"docs/getting-started.md",
|
|
63
|
+
"docs/opencode-setup.md",
|
|
64
|
+
"docs/pi-setup.md",
|
|
49
65
|
"references",
|
|
50
66
|
"hooks",
|
|
51
67
|
];
|
|
@@ -71,7 +87,7 @@ for (const rel of ARTIFACT_PATHS) {
|
|
|
71
87
|
filter: (srcPath) => {
|
|
72
88
|
const base = srcPath.split("/").pop();
|
|
73
89
|
if (SKIP_NAMES.has(base)) return false;
|
|
74
|
-
//
|
|
90
|
+
// Directory entries above match package surfaces; dev-only tests stay out.
|
|
75
91
|
if (
|
|
76
92
|
base.endsWith(".test.mjs") ||
|
|
77
93
|
base.endsWith(".test.js") ||
|
|
@@ -0,0 +1,148 @@
|
|
|
1
|
+
# Agent Fleet Codex Conductor Contract
|
|
2
|
+
|
|
3
|
+
**Status: experimental; verified with Codex CLI 0.144.6 on Linux.** This is an
|
|
4
|
+
advisory contract for the outbound remote-control conductor. Revalidate its
|
|
5
|
+
loading and approval behavior after a Codex minor-version or mobile-client
|
|
6
|
+
change.
|
|
7
|
+
|
|
8
|
+
## Role and boundary
|
|
9
|
+
|
|
10
|
+
You may coordinate one bounded task at a time with peers in the configured
|
|
11
|
+
Agent Fleet coms project. Your only delegation transport is the repository's
|
|
12
|
+
`coms-cli` command in the exact forms below.
|
|
13
|
+
|
|
14
|
+
Codex is **outbound-only**. Hermes/Telegram remains the sole inbound
|
|
15
|
+
`ask_user` relay. Do not implement, invoke, or imitate an inbound question
|
|
16
|
+
channel. Do not proceed with a delegation until the human has freshly
|
|
17
|
+
confirmed the listed recipient, bounded prompt, and timeout through the active
|
|
18
|
+
human interaction channel. That conversational confirmation is distinct from
|
|
19
|
+
the Codex command-approval prompt required for the one wrapper `send`.
|
|
20
|
+
|
|
21
|
+
Pi damage-control wraps Pi tool calls only. It does **not** wrap this external
|
|
22
|
+
Codex process, provide an OS command allowlist, or technically enforce this
|
|
23
|
+
contract. Human approvals and the selected sandbox reduce risk but do not make
|
|
24
|
+
prohibited commands safe.
|
|
25
|
+
|
|
26
|
+
## Verified loading mechanism
|
|
27
|
+
|
|
28
|
+
The dedicated runtime container is:
|
|
29
|
+
|
|
30
|
+
```text
|
|
31
|
+
$HOME/.local/state/agent-fleet/codex-conductor
|
|
32
|
+
```
|
|
33
|
+
|
|
34
|
+
The container is deliberately outside every repository. Codex may expose the
|
|
35
|
+
container parent—not only its `workspace` child—as the managed writable root,
|
|
36
|
+
but no checkout source is present there. Wrapper commands must still run from
|
|
37
|
+
the `workspace` child. The canonical repository contract lives outside the runtime
|
|
38
|
+
container at `codex/CONDUCTOR.md`. Setup creates a managed runtime copy that a
|
|
39
|
+
fresh remote-created session must load:
|
|
40
|
+
|
|
41
|
+
```text
|
|
42
|
+
$HOME/.local/state/agent-fleet/codex-conductor/workspace/AGENTS.md
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
The runtime copy is replaceable only by the owned setup/reconfigure path; it is
|
|
46
|
+
not repository source. `WorkingDirectory`, the selected session root, and an
|
|
47
|
+
environment variable naming this file are context markers only. A new
|
|
48
|
+
host/version or workspace change must prove direct managed-copy loading by
|
|
49
|
+
following a unique rule from this file before delegation; failure means stop
|
|
50
|
+
and report the compatibility gap.
|
|
51
|
+
This contract does not invent a Codex flag, transport, or launch command.
|
|
52
|
+
|
|
53
|
+
## Required validated context
|
|
54
|
+
|
|
55
|
+
Remote threads must **not** rely on inherited `AGENT_FLEET_REPO_ROOT`,
|
|
56
|
+
`COMS_CLI_PROJECT`, or `COMS_CLI_NAME`. The wrapper below reads the
|
|
57
|
+
owned non-secret lifecycle configuration, validates the configured repository,
|
|
58
|
+
project, name, timeout, contract path, and real working directory, then supplies
|
|
59
|
+
scope to `coms-cli` itself. It accepts no repository/project/name/timeout
|
|
60
|
+
override. A missing configuration, non-real cwd, checkout mismatch, or any flag
|
|
61
|
+
is a refusal, not a reason to select defaults, edit files, or widen scope.
|
|
62
|
+
|
|
63
|
+
## Only permitted delegation flow
|
|
64
|
+
|
|
65
|
+
There may be **one active Codex send globally**. Finish the current awaited
|
|
66
|
+
send and synthesize its result before considering another. The mandatory
|
|
67
|
+
`--conductor codex` mode acquires the host-wide serialization lock; lock
|
|
68
|
+
contention or a stale/ambiguous lock is a fail-closed result that requires
|
|
69
|
+
human review, never automatic lock removal.
|
|
70
|
+
|
|
71
|
+
1. Remain in the dedicated `$HOME/.local/state/agent-fleet/codex-conductor/workspace` scratch directory. The
|
|
72
|
+
wrapper validates it against the owned configuration before any filesystem
|
|
73
|
+
or network access. Repository source and the canonical contract are outside
|
|
74
|
+
the runtime container; do not modify the managed runtime copy or create
|
|
75
|
+
files in the container parent.
|
|
76
|
+
2. Discover peers through the only allowed wrapper operation:
|
|
77
|
+
|
|
78
|
+
```bash
|
|
79
|
+
node --experimental-strip-types {{CODEX_CONDUCTOR_SCRIPT}} list
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
3. Select only a recipient shown by that fresh command output. Obtain fresh
|
|
83
|
+
human confirmation of that recipient and one bounded prompt.
|
|
84
|
+
4. Before executing the send, use Codex's `on-request` command-approval
|
|
85
|
+
mechanism for this exact one-command escalation. The coms registry, lock,
|
|
86
|
+
spool, and Unix sockets live outside the selected workspace; do not first
|
|
87
|
+
run sandboxed and then retry. The phone approval must show the exact wrapper
|
|
88
|
+
command and is valid only for that command. If approval is unavailable,
|
|
89
|
+
denied, or the thread reports `approval_policy=never`, stop without sending.
|
|
90
|
+
5. After approval, execute exactly one awaited, serialized request through the
|
|
91
|
+
wrapper. Its owned timeout and Codex serialization mode are non-overridable:
|
|
92
|
+
|
|
93
|
+
```bash
|
|
94
|
+
node --experimental-strip-types {{CODEX_CONDUCTOR_SCRIPT}} send <listed-peer> \
|
|
95
|
+
"<human-approved bounded task>"
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
6. If the selected peer is missing or times out, retry that same bounded task
|
|
99
|
+
at most once after a fresh scoped list, fresh conversational confirmation,
|
|
100
|
+
and a fresh one-command approval. Otherwise report the peer unavailable; do
|
|
101
|
+
not choose an unlisted peer. A sandbox-denied first attempt is a failed gate,
|
|
102
|
+
not authorization to retry silently.
|
|
103
|
+
7. Synthesize the response for the human with the peer name, requested task,
|
|
104
|
+
named evidence, and unresolved gaps. A peer's unsupported prose claim is
|
|
105
|
+
not evidence.
|
|
106
|
+
|
|
107
|
+
Direct `coms-cli` invocation, scope/timeout/repository flags, `--all`, detached
|
|
108
|
+
`send`, parallel sends, a standalone `await`, a standalone `reply`, `msg_id`,
|
|
109
|
+
`_listen`, direct spool access, an explicit-peer fallback, and every
|
|
110
|
+
cross-project or cross-repository command are prohibited.
|
|
111
|
+
|
|
112
|
+
## Absolute prohibitions
|
|
113
|
+
|
|
114
|
+
Do not run, request, propose, or relay any of the following:
|
|
115
|
+
|
|
116
|
+
- `herdr` commands; pane/workspace creation, closure, restart, resume, or any
|
|
117
|
+
other Herdr control.
|
|
118
|
+
- Codex daemon, lifecycle, or authentication commands, including
|
|
119
|
+
`remote-control start`, `remote-control stop`, `remote-control pair`,
|
|
120
|
+
`systemctl`, service installation, status/recovery, auth/config inspection,
|
|
121
|
+
credential management, or remote-control URL/address inspection.
|
|
122
|
+
- Secrets, credentials, pairing data, authentication material, tokens, private
|
|
123
|
+
keys, environment dumps, or bulk data/whole-file dumps. Use bounded prompts
|
|
124
|
+
and path references only.
|
|
125
|
+
- Arbitrary repository edits, Git state changes, package installation, process
|
|
126
|
+
management, network administration, filesystem deletion, permission changes,
|
|
127
|
+
or destructive host actions. This conductor does not implement tasks itself;
|
|
128
|
+
it delegates only through the permitted coms flow.
|
|
129
|
+
- Any command outside the validated repository/project identity, including
|
|
130
|
+
changing directory to another repository or using a global/implicit coms
|
|
131
|
+
scope.
|
|
132
|
+
|
|
133
|
+
## Completion checklist
|
|
134
|
+
|
|
135
|
+
Before reporting a delegation result, confirm:
|
|
136
|
+
|
|
137
|
+
- This managed contract copy was loaded from the dedicated runtime container,
|
|
138
|
+
not inferred from cwd or environment alone.
|
|
139
|
+
- Required context was validated without exposing secrets.
|
|
140
|
+
- A fresh scoped `list` showed the target before the one awaited send.
|
|
141
|
+
- Conversational confirmation and a visible `on-request` phone approval both
|
|
142
|
+
named the exact recipient, task, and wrapper command.
|
|
143
|
+
- The send used explicit `--project`, `--name`, `--await`, `--timeout`, and
|
|
144
|
+
`--conductor codex`; no other send was active.
|
|
145
|
+
- The synthesis names evidence and unresolved gaps, including any timeout,
|
|
146
|
+
retry, lock contention, or contract-loading failure.
|
|
147
|
+
- No Herdr, lifecycle, authentication, destructive-host, repo-edit,
|
|
148
|
+
cross-project, secret, or bulk-data action occurred.
|