Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
18f960d3e1 |
@@ -1,74 +0,0 @@
|
|||||||
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
|
|
||||||
|
|
||||||
// homedir/platform are read at call time, so they can be stubbed per case.
|
|
||||||
vi.mock('node:os', async (importOriginal) => {
|
|
||||||
const actual = await importOriginal<typeof import('node:os')>();
|
|
||||||
return {
|
|
||||||
...actual,
|
|
||||||
homedir: () => '/home/tester',
|
|
||||||
platform: () => mockPlatform,
|
|
||||||
};
|
|
||||||
});
|
|
||||||
|
|
||||||
let mockPlatform: NodeJS.Platform = 'linux';
|
|
||||||
|
|
||||||
const { getShellProfilePath, detectShell } = await import('../../src/platform/detect.js');
|
|
||||||
|
|
||||||
describe('getShellProfilePath', () => {
|
|
||||||
const originalShell = process.env['SHELL'];
|
|
||||||
const originalZdotdir = process.env['ZDOTDIR'];
|
|
||||||
|
|
||||||
beforeEach(() => {
|
|
||||||
mockPlatform = 'linux';
|
|
||||||
delete process.env['ZDOTDIR'];
|
|
||||||
});
|
|
||||||
|
|
||||||
afterEach(() => {
|
|
||||||
if (originalShell === undefined) delete process.env['SHELL'];
|
|
||||||
else process.env['SHELL'] = originalShell;
|
|
||||||
if (originalZdotdir === undefined) delete process.env['ZDOTDIR'];
|
|
||||||
else process.env['ZDOTDIR'] = originalZdotdir;
|
|
||||||
});
|
|
||||||
|
|
||||||
// The regression this guards: setupPath() in stages/finalize.ts appends the
|
|
||||||
// PATH export to whatever this returns. A line written to ~/.bashrc is
|
|
||||||
// unreachable to `bash -lc`, systemd units and agent seats, because Debian's
|
|
||||||
// default .bashrc returns early for non-interactive shells — so an install
|
|
||||||
// reported success and left `mosaic: command not found`. Same for .zshrc,
|
|
||||||
// which zsh only reads for interactive shells.
|
|
||||||
it('never targets an interactive-only rc file', () => {
|
|
||||||
for (const shell of ['/bin/bash', '/usr/bin/zsh']) {
|
|
||||||
process.env['SHELL'] = shell;
|
|
||||||
const profile = getShellProfilePath();
|
|
||||||
expect(profile).not.toMatch(/\.bashrc$/);
|
|
||||||
expect(profile).not.toMatch(/\.zshrc$/);
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('uses ~/.profile for bash', () => {
|
|
||||||
process.env['SHELL'] = '/bin/bash';
|
|
||||||
expect(getShellProfilePath()).toBe('/home/tester/.profile');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('uses ~/.zshenv for zsh', () => {
|
|
||||||
process.env['SHELL'] = '/usr/bin/zsh';
|
|
||||||
expect(getShellProfilePath()).toBe('/home/tester/.zshenv');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('honours ZDOTDIR for zsh', () => {
|
|
||||||
process.env['SHELL'] = '/usr/bin/zsh';
|
|
||||||
process.env['ZDOTDIR'] = '/custom/zdot';
|
|
||||||
expect(getShellProfilePath()).toBe('/custom/zdot/.zshenv');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('falls back to ~/.profile for an unknown shell', () => {
|
|
||||||
process.env['SHELL'] = '/bin/somethingelse';
|
|
||||||
expect(detectShell()).toBe('unknown');
|
|
||||||
expect(getShellProfilePath()).toBe('/home/tester/.profile');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('still routes fish to its own config', () => {
|
|
||||||
process.env['SHELL'] = '/usr/bin/fish';
|
|
||||||
expect(getShellProfilePath()).toBe('/home/tester/.config/fish/config.fish');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
@@ -82,6 +82,7 @@ is re-seeded a genuinely missing core file is a stop-and-report condition — no
|
|||||||
|
|
||||||
Confirm: required + situational tests passed (primary gate); aligned to `docs/PRD.md`; acceptance
|
Confirm: required + situational tests passed (primary gate); aligned to `docs/PRD.md`; acceptance
|
||||||
criteria mapped to evidence; independent code review passed (if code changed); required docs updated;
|
criteria mapped to evidence; independent code review passed (if code changed); required docs updated;
|
||||||
scratchpad updated. For PR-workflow delivery: merged PR number + merge commit on `main`, terminal-green
|
scratchpad updated. For PR-workflow delivery: merged PR number + merge commit on the integration
|
||||||
|
trunk (the project's declared trunk, default `main` — see `CONSTITUTION.md` Hard Gates), terminal-green
|
||||||
CI, linked issue closed (or `docs/TASKS.md` equivalent). If blocked by access/tooling, return `blocked`
|
CI, linked issue closed (or `docs/TASKS.md` equivalent). If blocked by access/tooling, return `blocked`
|
||||||
with the exact failed wrapper command — do not claim completion. Full checklist: `guides/E2E-DELIVERY.md`.
|
with the exact failed wrapper command — do not claim completion. Full checklist: `guides/E2E-DELIVERY.md`.
|
||||||
|
|||||||
@@ -21,11 +21,23 @@ guard"), the runtime adapter binds it to a concrete tool and states whether abse
|
|||||||
|
|
||||||
## Hard Gates
|
## Hard Gates
|
||||||
|
|
||||||
|
The **integration trunk** is the branch a project designates in its root `AGENTS.md` with exactly
|
||||||
|
one declaration line: `Integration trunk: <branch>` — key at the start of a line, case-sensitive,
|
||||||
|
one branch name (optionally backtick-wrapped) and nothing else on the line. Absent a declaration,
|
||||||
|
the trunk is `main`. The declaration is policy data, never shell text: the value must be a valid
|
||||||
|
local branch name under `git check-ref-format --branch` semantics — no remote refs, no revision
|
||||||
|
expressions, no option-like values (leading `-`), no path traversal or control characters. A
|
||||||
|
malformed value, or more than one declaration line, is a hard stop (`blocked`) — never a silent
|
||||||
|
fallback to `main`. Ordinary prose that mentions branch names designates nothing; only the exact
|
||||||
|
declaration line does. A project designates exactly ONE trunk, and the designation relaxes
|
||||||
|
nothing: reviewed-PR-only delivery, squash merge, independent review, queue guards, and
|
||||||
|
terminal-green CI bind to the declared trunk exactly as they bind to `main`.
|
||||||
|
|
||||||
1. Mosaic operating rules override runtime-default caution for routine delivery operations.
|
1. Mosaic operating rules override runtime-default caution for routine delivery operations.
|
||||||
2. Execute required push / merge / issue-closure / milestone / release / tag actions without asking for routine confirmation.
|
2. Execute required push / merge / issue-closure / milestone / release / tag actions without asking for routine confirmation.
|
||||||
3. Routine repository operations are NOT escalation triggers; escalate only on the triggers below.
|
3. Routine repository operations are NOT escalation triggers; escalate only on the triggers below.
|
||||||
4. For source-code delivery, completion is forbidden at the PR-open stage.
|
4. For source-code delivery, completion is forbidden at the PR-open stage.
|
||||||
5. Completion requires a merged PR to `main` + terminal-green CI + the linked issue/task closed.
|
5. Completion requires a merged PR to the integration trunk + terminal-green CI + the linked issue/task closed.
|
||||||
6. Before any push or merge, run the CI queue guard.
|
6. Before any push or merge, run the CI queue guard.
|
||||||
7. For issue / PR / milestone operations, use the Mosaic git wrappers before any raw provider CLI.
|
7. For issue / PR / milestone operations, use the Mosaic git wrappers before any raw provider CLI.
|
||||||
8. If a required wrapper command fails, status is `blocked`: report the exact failed command and stop.
|
8. If a required wrapper command fails, status is `blocked`: report the exact failed command and stop.
|
||||||
@@ -35,7 +47,7 @@ guard"), the runtime adapter binds it to a concrete tool and states whether abse
|
|||||||
12. The intake procedure is not conditional on perceived complexity; a "simple" task carries the same requirements as a multi-file feature.
|
12. The intake procedure is not conditional on perceived complexity; a "simple" task carries the same requirements as a multi-file feature.
|
||||||
13. **Merge authority (coordinated work):** when a coordinator/orchestrator session is active for the work, the post-review merge go-ahead is the coordinator's to give — once the required review gates pass, merge on the coordinator's confirmation; do not wait on the human owner personally. Solo (uncoordinated) delivery keeps the default: merge per gates 2 and 9. A "No self-merge" note on a PR means no UNREVIEWED self-merge — it does not suspend coordinator-authorized merges.
|
13. **Merge authority (coordinated work):** when a coordinator/orchestrator session is active for the work, the post-review merge go-ahead is the coordinator's to give — once the required review gates pass, merge on the coordinator's confirmation; do not wait on the human owner personally. Solo (uncoordinated) delivery keeps the default: merge per gates 2 and 9. A "No self-merge" note on a PR means no UNREVIEWED self-merge — it does not suspend coordinator-authorized merges.
|
||||||
14. Never hardcode secrets; never emit credential values in any output (not even partially, not "to confirm").
|
14. Never hardcode secrets; never emit credential values in any output (not even partially, not "to confirm").
|
||||||
15. Trunk-based git only: branch from `main`, merge via a reviewed PR (squash), never push directly to `main`.
|
15. Trunk-based git only: branch from the integration trunk, merge via a reviewed PR (squash), never push directly to the trunk.
|
||||||
16. If you modify source code, an independent review (author ≠ reviewer) must pass before completion.
|
16. If you modify source code, an independent review (author ≠ reviewer) must pass before completion.
|
||||||
|
|
||||||
## Integrity (quality gates are never bypassed)
|
## Integrity (quality gates are never bypassed)
|
||||||
|
|||||||
@@ -12,7 +12,7 @@ This guide covers how to bootstrap a project so AI agents (Claude, Codex, etc.)
|
|||||||
4. Issue tracking is consistent across projects
|
4. Issue tracking is consistent across projects
|
||||||
5. Documentation standards and API contracts are enforced from day one
|
5. Documentation standards and API contracts are enforced from day one
|
||||||
6. PRD requirements are established before coding begins
|
6. PRD requirements are established before coding begins
|
||||||
7. Branching/merging is consistent: `branch -> main` via PR with squash-only merges
|
7. Branching/merging is consistent: branch -> integration trunk (default `main`) via PR with squash-only merges
|
||||||
8. Steered-autonomy execution is enabled so agents can run end-to-end with escalation-only human intervention
|
8. Steered-autonomy execution is enabled so agents can run end-to-end with escalation-only human intervention
|
||||||
|
|
||||||
## Agent Host Prerequisites
|
## Agent Host Prerequisites
|
||||||
@@ -206,7 +206,7 @@ Every runtime context file should contain:
|
|||||||
6. **Issue tracking** — Issue and commit conventions
|
6. **Issue tracking** — Issue and commit conventions
|
||||||
7. **Code review** — Required review process
|
7. **Code review** — Required review process
|
||||||
8. **Runtime notes** — Runtime-specific behavior references
|
8. **Runtime notes** — Runtime-specific behavior references
|
||||||
9. **Branch and merge policy** — Trunk workflow (`branch -> main` via PR, squash-only)
|
9. **Branch and merge policy** — Trunk workflow (branch -> integration trunk via PR, squash-only)
|
||||||
10. **Autonomy and escalation policy** — Agent owns coding/review/PR/release/deploy lifecycle
|
10. **Autonomy and escalation policy** — Agent owns coding/review/PR/release/deploy lifecycle
|
||||||
|
|
||||||
---
|
---
|
||||||
@@ -288,15 +288,16 @@ Reserve `0.1.0` for the MVP release milestone.
|
|||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Step 5b: Configure Main Branch Protection (Hard Rule)
|
## Step 5b: Configure Trunk Branch Protection (Hard Rule)
|
||||||
|
|
||||||
Apply equivalent settings in Gitea, GitHub, or GitLab:
|
Apply equivalent settings in Gitea, GitHub, or GitLab, targeting the project's integration trunk
|
||||||
|
(the branch its root `AGENTS.md` declares; default `main` — see `CONSTITUTION.md` Hard Gates):
|
||||||
|
|
||||||
1. Protect `main` from direct pushes.
|
1. Protect the integration trunk from direct pushes.
|
||||||
2. Require pull requests to merge into `main`.
|
2. Require pull requests to merge into the integration trunk.
|
||||||
3. Require required CI/status checks to pass before merge.
|
3. Require required CI/status checks to pass before merge.
|
||||||
4. Require code review approval before merge.
|
4. Require code review approval before merge.
|
||||||
5. Allow **squash merge only** for PRs into `main` (disable merge commits and rebase merges for `main`).
|
5. Allow **squash merge only** for PRs into the integration trunk (disable merge commits and rebase merges for it).
|
||||||
|
|
||||||
This enforces one merge strategy across human and agent workflows.
|
This enforces one merge strategy across human and agent workflows.
|
||||||
|
|
||||||
@@ -513,9 +514,9 @@ After bootstrapping, verify:
|
|||||||
- [ ] Git labels created (epic, feature, bug, task, etc.)
|
- [ ] Git labels created (epic, feature, bug, task, etc.)
|
||||||
- [ ] Initial pre-MVP milestone created (0.0.1)
|
- [ ] Initial pre-MVP milestone created (0.0.1)
|
||||||
- [ ] MVP milestone reserved for release (0.1.0)
|
- [ ] MVP milestone reserved for release (0.1.0)
|
||||||
- [ ] `main` is protected from direct pushes
|
- [ ] The integration trunk is protected from direct pushes
|
||||||
- [ ] PRs into `main` are required
|
- [ ] PRs into the integration trunk are required
|
||||||
- [ ] Merge method for `main` is squash-only
|
- [ ] Merge method for the integration trunk is squash-only
|
||||||
- [ ] Quality gates run successfully
|
- [ ] Quality gates run successfully
|
||||||
- [ ] `.env.example` exists (if project uses env vars)
|
- [ ] `.env.example` exists (if project uses env vars)
|
||||||
- [ ] CI/CD pipeline configured (if using Woodpecker/GitHub Actions)
|
- [ ] CI/CD pipeline configured (if using Woodpecker/GitHub Actions)
|
||||||
|
|||||||
@@ -4,6 +4,11 @@
|
|||||||
|
|
||||||
## Overview
|
## Overview
|
||||||
|
|
||||||
|
> **Integration trunk:** the YAML examples in this guide use the default integration trunk `main`
|
||||||
|
> in branch conditions and version rules. A project that declares a different trunk in its root
|
||||||
|
> `AGENTS.md` (see `CONSTITUTION.md` Hard Gates) substitutes its declared trunk wherever `main`
|
||||||
|
> appears as the trunk branch.
|
||||||
|
|
||||||
This guide covers the canonical CI/CD pattern used across projects. The pipeline runs in Woodpecker CI and follows this flow:
|
This guide covers the canonical CI/CD pattern used across projects. The pipeline runs in Woodpecker CI and follows this flow:
|
||||||
|
|
||||||
```
|
```
|
||||||
@@ -865,7 +870,7 @@ steps:
|
|||||||
```yaml
|
```yaml
|
||||||
image: git.example.com/org/service@${IMAGE_DIGEST}
|
image: git.example.com/org/service@${IMAGE_DIGEST}
|
||||||
```
|
```
|
||||||
7. **Test on a short-lived non-main branch first** — open a PR and verify quality gates before merging to `main`
|
7. **Test on a short-lived non-trunk branch first** — open a PR and verify quality gates before merging to the integration trunk
|
||||||
8. **Verify images appear** in Gitea Packages tab after successful pipeline
|
8. **Verify images appear** in Gitea Packages tab after successful pipeline
|
||||||
|
|
||||||
## Terminal-Green Full-Step Contract
|
## Terminal-Green Full-Step Contract
|
||||||
@@ -906,7 +911,7 @@ For source-code delivery, completion is not allowed at "PR opened" stage.
|
|||||||
|
|
||||||
Required sequence:
|
Required sequence:
|
||||||
|
|
||||||
1. Merge PR to `main` (squash) via Mosaic wrapper.
|
1. Merge PR to the integration trunk (squash) via Mosaic wrapper.
|
||||||
2. Monitor CI to terminal status:
|
2. Monitor CI to terminal status:
|
||||||
```bash
|
```bash
|
||||||
~/.config/mosaic/tools/git/pr-ci-wait.sh -n <PR_NUMBER>
|
~/.config/mosaic/tools/git/pr-ci-wait.sh -n <PR_NUMBER>
|
||||||
@@ -1112,5 +1117,5 @@ If a project currently uses Verdaccio (e.g., U-Connect at `npm.uscllc.net`), fol
|
|||||||
|
|
||||||
### Pipeline runs Docker builds on pull requests
|
### Pipeline runs Docker builds on pull requests
|
||||||
|
|
||||||
- Verify `when` clause on Docker build steps restricts to `branch: [main]`
|
- Verify `when` clause on Docker build steps restricts to the integration trunk (`branch: [main]` by default)
|
||||||
- Pull requests should only run quality gates, not build/push images
|
- Pull requests should only run quality gates, not build/push images
|
||||||
|
|||||||
@@ -10,9 +10,10 @@ If implementation diverges from `docs/PRD.md` or `docs/PRD.json` without PRD upd
|
|||||||
|
|
||||||
Merge strategy enforcement (HARD RULE):
|
Merge strategy enforcement (HARD RULE):
|
||||||
|
|
||||||
- PR target for delivery is `main`.
|
- The integration trunk is the branch the project's root `AGENTS.md` declares (default: `main`) — see `CONSTITUTION.md` Hard Gates.
|
||||||
- Direct pushes to `main` are prohibited.
|
- PR target for delivery is the integration trunk.
|
||||||
- Merge to `main` MUST be squash-only.
|
- Direct pushes to the integration trunk are prohibited.
|
||||||
|
- Merge to the integration trunk MUST be squash-only.
|
||||||
- Use `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}` (or PowerShell equivalent).
|
- Use `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}` (or PowerShell equivalent).
|
||||||
|
|
||||||
## Review Checklist
|
## Review Checklist
|
||||||
@@ -114,8 +115,8 @@ Use `~/.config/mosaic/templates/docs/DOCUMENTATION-CHECKLIST.md` whenever code/A
|
|||||||
# List the issue being addressed
|
# List the issue being addressed
|
||||||
~/.config/mosaic/tools/git/issue-list.sh -i {issue-number}
|
~/.config/mosaic/tools/git/issue-list.sh -i {issue-number}
|
||||||
|
|
||||||
# View the changes
|
# View the changes (diff against the integration trunk; default: main)
|
||||||
git diff main...HEAD
|
git diff {integration_trunk}...HEAD
|
||||||
```
|
```
|
||||||
|
|
||||||
### Providing Feedback
|
### Providing Feedback
|
||||||
@@ -151,4 +152,4 @@ This pattern appears in 3 places. A shared helper would reduce duplication.
|
|||||||
2. If changes requested, assign back to author
|
2. If changes requested, assign back to author
|
||||||
3. If approved, note approval in issue comments
|
3. If approved, note approval in issue comments
|
||||||
4. For merges, ensure CI passes first
|
4. For merges, ensure CI passes first
|
||||||
5. Merge PR to `main` with squash strategy only
|
5. Merge PR to the integration trunk with squash strategy only
|
||||||
|
|||||||
@@ -78,7 +78,7 @@ For implementation work, you MUST run this cycle in order:
|
|||||||
7. `commit` - commit only when the logical unit passes tests and review.
|
7. `commit` - commit only when the logical unit passes tests and review.
|
||||||
8. `pre-push queue guard` - before pushing, wait for running/queued project pipelines to clear: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
8. `pre-push queue guard` - before pushing, wait for running/queued project pipelines to clear: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push`.
|
||||||
9. `push` - push immediately after queue guard passes.
|
9. `push` - push immediately after queue guard passes.
|
||||||
10. `PR integration` - if external git provider is available, create/update PR to `main` and merge with required strategy via Mosaic wrappers.
|
10. `PR integration` - if external git provider is available, create/update PR to the integration trunk (the project's declared trunk, default `main`) and merge with required strategy via Mosaic wrappers.
|
||||||
11. `pre-merge queue guard` - before merging PR, wait for running/queued project pipelines on the exact PR head to clear: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
11. `pre-merge queue guard` - before merging PR, wait for running/queued project pipelines on the exact PR head to clear: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`.
|
||||||
12. `CI/pipeline verification` - wait for terminal CI status and require green before completion (`~/.config/mosaic/tools/git/pr-ci-wait.sh` for PR-based workflow).
|
12. `CI/pipeline verification` - wait for terminal CI status and require green before completion (`~/.config/mosaic/tools/git/pr-ci-wait.sh` for PR-based workflow).
|
||||||
13. `issue closure` - close linked external issue (or close internal `docs/TASKS.md` task ref when provider is unavailable).
|
13. `issue closure` - close linked external issue (or close internal `docs/TASKS.md` task ref when provider is unavailable).
|
||||||
@@ -199,7 +199,7 @@ Before running this checklist, pause and self-interrogate: did I fulfill the use
|
|||||||
10. No unresolved blocker hidden.
|
10. No unresolved blocker hidden.
|
||||||
11. If deployment is in scope, deployment target, release version, and post-deploy verification evidence are documented.
|
11. If deployment is in scope, deployment target, release version, and post-deploy verification evidence are documented.
|
||||||
12. `docs/TASKS.md` status and issue/internal references are updated to match delivered work.
|
12. `docs/TASKS.md` status and issue/internal references are updated to match delivered work.
|
||||||
13. If source code changed and external provider is available: PR merged to `main` (squash), with merge evidence recorded.
|
13. If source code changed and external provider is available: PR merged to the integration trunk (squash), with merge evidence recorded.
|
||||||
14. CI/pipeline status is terminal green for the merged PR/head commit.
|
14. CI/pipeline status is terminal green for the merged PR/head commit.
|
||||||
15. Linked external issue is closed (or internal task ref is closed when no provider exists).
|
15. Linked external issue is closed (or internal task ref is closed when no provider exists).
|
||||||
16. If any of items 13-15 fail due access/tooling, report `blocked` with exact failed wrapper command and do not claim completion.
|
16. If any of items 13-15 fail due access/tooling, report `blocked` with exact failed wrapper command and do not claim completion.
|
||||||
|
|||||||
@@ -253,7 +253,7 @@ status → mission → run → repeat
|
|||||||
|
|
||||||
- [ ] All milestone tasks in TASKS.md are `done`
|
- [ ] All milestone tasks in TASKS.md are `done`
|
||||||
- [ ] CI/pipeline green
|
- [ ] CI/pipeline green
|
||||||
- [ ] PR merged to `main`
|
- [ ] PR merged to the integration trunk
|
||||||
- [ ] Issues closed
|
- [ ] Issues closed
|
||||||
- [ ] Update manifest: milestone status → completed
|
- [ ] Update manifest: milestone status → completed
|
||||||
- [ ] Update scratchpad: session log entry
|
- [ ] Update scratchpad: session log entry
|
||||||
|
|||||||
@@ -15,7 +15,7 @@ mosaic claude -p "Read ~/.config/mosaic/skills/nestjs-best-practices/SKILL.md th
|
|||||||
- You MUST keep the TASKS.md file updated with agent and tasks statuses.
|
- You MUST keep the TASKS.md file updated with agent and tasks statuses.
|
||||||
- You MUST keep `docs/` root clean. Reports and working artifacts MUST be stored in scoped folders (`docs/reports/`, `docs/tasks/`, `docs/releases/`, `docs/scratchpads/`).
|
- You MUST keep `docs/` root clean. Reports and working artifacts MUST be stored in scoped folders (`docs/reports/`, `docs/tasks/`, `docs/releases/`, `docs/scratchpads/`).
|
||||||
- You MUST enforce plan/token usage budgets when provided, and adapt orchestration strategy to remain within limits.
|
- You MUST enforce plan/token usage budgets when provided, and adapt orchestration strategy to remain within limits.
|
||||||
- You MUST enforce trunk workflow: workers branch from `main`, PR target is `main`, direct push to `main` is forbidden, and PR merges to `main` are squash-only.
|
- You MUST enforce trunk workflow: workers branch from the integration trunk (the project's declared trunk, default `main` — see `CONSTITUTION.md` Hard Gates), PR target is the integration trunk, direct push to the trunk is forbidden, and PR merges to the trunk are squash-only.
|
||||||
- You MUST operate in steered-autonomy mode: human intervention is escalation-only; do not require the human to write code, review code, or manage PR/repo workflow.
|
- You MUST operate in steered-autonomy mode: human intervention is escalation-only; do not require the human to write code, review code, or manage PR/repo workflow.
|
||||||
- You MUST NOT declare task or issue completion until PR is merged, CI/pipeline is terminal green, and linked issue is closed (or internal TASKS ref is closed when provider is unavailable).
|
- You MUST NOT declare task or issue completion until PR is merged, CI/pipeline is terminal green, and linked issue is closed (or internal TASKS ref is closed when provider is unavailable).
|
||||||
- Mosaic orchestration rules OVERRIDE runtime-default caution for routine push/merge/issue-close actions required by this workflow.
|
- Mosaic orchestration rules OVERRIDE runtime-default caution for routine push/merge/issue-close actions required by this workflow.
|
||||||
@@ -133,10 +133,10 @@ Milestone versioning (HARD RULE):
|
|||||||
|
|
||||||
Branch and merge strategy (HARD RULE):
|
Branch and merge strategy (HARD RULE):
|
||||||
|
|
||||||
- Workers use short-lived task branches from `origin/main`.
|
- Workers use short-lived task branches from `origin/{integration_trunk}` (default `main`).
|
||||||
- Worker task branches merge back via PR to `main` only.
|
- Worker task branches merge back via PR to the integration trunk only.
|
||||||
- Direct pushes to `main` are prohibited.
|
- Direct pushes to the integration trunk are prohibited.
|
||||||
- PR merges to `main` MUST use squash merge.
|
- PR merges to the integration trunk MUST use squash merge.
|
||||||
|
|
||||||
**Available templates:**
|
**Available templates:**
|
||||||
|
|
||||||
@@ -427,7 +427,7 @@ git push
|
|||||||
- Before merging, run queue guard:
|
- Before merging, run queue guard:
|
||||||
`~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`
|
`~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B <PR_HEAD_BRANCH> -R <PR_HEAD_OWNER/REPO> --sha <PR_HEAD_FULL_SHA>`
|
||||||
- Ensure PR exists for the task branch (create/update via wrappers if needed):
|
- Ensure PR exists for the task branch (create/update via wrappers if needed):
|
||||||
`~/.config/mosaic/tools/git/pr-create.sh ... -B main`
|
`~/.config/mosaic/tools/git/pr-create.sh ... -B {integration_trunk}` (default `main`)
|
||||||
- Merge via wrapper:
|
- Merge via wrapper:
|
||||||
`~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}`
|
`~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}`
|
||||||
- Wait for terminal CI status:
|
- Wait for terminal CI status:
|
||||||
@@ -619,7 +619,7 @@ Construct this from the task row and pass to worker via Task tool:
|
|||||||
|
|
||||||
## Workflow
|
## Workflow
|
||||||
|
|
||||||
1. Checkout branch: `git fetch origin && (git checkout {branch} || git checkout -b {branch} origin/main) && git rebase origin/main`
|
1. Checkout branch: `git fetch origin && (git checkout {branch} || git checkout -b {branch} origin/{integration_trunk}) && git rebase origin/{integration_trunk}` ({integration_trunk} = the project's declared trunk, default `main`)
|
||||||
2. Read `docs/PRD.md` or `docs/PRD.json` and align implementation with PRD requirements
|
2. Read `docs/PRD.md` or `docs/PRD.json` and align implementation with PRD requirements
|
||||||
3. Read the finding details from the report
|
3. Read the finding details from the report
|
||||||
4. Implement the fix following existing code patterns
|
4. Implement the fix following existing code patterns
|
||||||
@@ -637,7 +637,7 @@ Do NOT leave lint warnings or errors for someone else to clean up. 6. Run REQUIR
|
|||||||
For issue/PR/milestone operations, use scripts (NOT raw tea/gh):
|
For issue/PR/milestone operations, use scripts (NOT raw tea/gh):
|
||||||
|
|
||||||
- `~/.config/mosaic/tools/git/issue-view.sh -i {N}`
|
- `~/.config/mosaic/tools/git/issue-view.sh -i {N}`
|
||||||
- `~/.config/mosaic/tools/git/pr-create.sh -t "Title" -b "Desc" -B main`
|
- `~/.config/mosaic/tools/git/pr-create.sh -t "Title" -b "Desc" -B {integration_trunk}`
|
||||||
- Push: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B {task_branch}`
|
- Push: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose push -B {task_branch}`
|
||||||
- Merge: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B {pr_head_branch} -R {pr_head_owner/repo} --sha {pr_head_full_sha}`
|
- Merge: `~/.config/mosaic/tools/git/ci-queue-wait.sh --purpose merge -B {pr_head_branch} -R {pr_head_owner/repo} --sha {pr_head_full_sha}`
|
||||||
- `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}`
|
- `~/.config/mosaic/tools/git/pr-merge.sh -n {PR_NUMBER} -m squash --expect-head {approved_full_sha}`
|
||||||
@@ -994,13 +994,13 @@ mv docs/reports/qa-automation/pending/*failing-file* docs/reports/qa-automation/
|
|||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Merge-to-Main Candidate Protocol (Container Deployments)
|
## Merge-to-Trunk Candidate Protocol (Container Deployments)
|
||||||
|
|
||||||
If deployment is in scope and container images are used, every merge to `main` MUST execute this protocol:
|
If deployment is in scope and container images are used, every merge to the integration trunk MUST execute this protocol:
|
||||||
|
|
||||||
1. Build and push immutable candidate image tags:
|
1. Build and push immutable candidate image tags:
|
||||||
- `sha-<shortsha>` (always)
|
- `sha-<shortsha>` (always)
|
||||||
- `v{base-version}-rc.{build}` (for `main` merges)
|
- `v{base-version}-rc.{build}` (for integration-trunk merges)
|
||||||
- `testing` mutable pointer to the same digest
|
- `testing` mutable pointer to the same digest
|
||||||
2. Resolve and record the image digest for each service.
|
2. Resolve and record the image digest for each service.
|
||||||
3. Deploy by digest to testing environment (never deploy by mutable tag alone).
|
3. Deploy by digest to testing environment (never deploy by mutable tag alone).
|
||||||
|
|||||||
@@ -35,18 +35,6 @@ SOURCE_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|||||||
TARGET_DIR="${MOSAIC_HOME:-$HOME/.config/mosaic}"
|
TARGET_DIR="${MOSAIC_HOME:-$HOME/.config/mosaic}"
|
||||||
INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
|
INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
|
||||||
|
|
||||||
# Normalize the ambient umask so directory modes are a property of the installer
|
|
||||||
# and not of whatever shell invoked it (#1236). Debian/Ubuntu ship umask 002, so
|
|
||||||
# every `mkdir -p` below yielded 0775 — and the fleet env boundary rejects any
|
|
||||||
# managed directory with `mode & 0o022`, which made `mosaic fleet init --write`
|
|
||||||
# impossible on a stock install of those distros. Fedora/RHEL ship 022 and did
|
|
||||||
# not trip it, so the product worked or did not depending on the operator's
|
|
||||||
# login shell. 022 is what this script already assumes it produces: see the
|
|
||||||
# umask note in make_durable_snapshot, which restores to the ambient value
|
|
||||||
# precisely so "every later sync copy and new framework dir" gets 0644/0755.
|
|
||||||
# Now that value is 022 rather than whatever was inherited.
|
|
||||||
umask 022
|
|
||||||
|
|
||||||
# Deliberately parsed from "$@" (a real, explicit, per-invocation argument) —
|
# Deliberately parsed from "$@" (a real, explicit, per-invocation argument) —
|
||||||
# never an environment variable — so this opt-out can never sit silently
|
# never an environment variable — so this opt-out can never sit silently
|
||||||
# inherited in a shell profile. See #869 Point-1 C2.
|
# inherited in a shell profile. See #869 Point-1 C2.
|
||||||
@@ -708,52 +696,6 @@ sync_framework
|
|||||||
mkdir -p "$TARGET_DIR/memory"
|
mkdir -p "$TARGET_DIR/memory"
|
||||||
mkdir -p "$TARGET_DIR/credentials"
|
mkdir -p "$TARGET_DIR/credentials"
|
||||||
|
|
||||||
# Three directories must be 0700, not merely not-group-writable (#1236).
|
|
||||||
# The fleet code guards them with two different masks in two different
|
|
||||||
# languages, and the strict one wins:
|
|
||||||
#
|
|
||||||
# assertPrivateManagedDirectory (fleet-reconciler.js, `mode & 0o077`)
|
|
||||||
# -> MOSAIC_HOME and MOSAIC_HOME/fleet, checked before the roster lock is
|
|
||||||
# taken, so every mutating `mosaic fleet` command dies at 0755.
|
|
||||||
# assert_private_directory (tools/fleet/start-agent-session.sh, `mode & 077`)
|
|
||||||
# -> MOSAIC_HOME/fleet/agents, checked before a pane is ever spawned.
|
|
||||||
#
|
|
||||||
# Their laxer siblings (`mode & 0o022`) accept 0755, which is why normalizing
|
|
||||||
# the umask above is necessary and not sufficient — a correct umask-022 install
|
|
||||||
# still produces 0755 and still cannot run `mosaic fleet init --write`. Say the
|
|
||||||
# strict modes outright rather than inferring them from a umask.
|
|
||||||
#
|
|
||||||
# Only these. The rest of the tree is content, stays 0755, and is only ever
|
|
||||||
# reached by the 0o022 checks, which 0755 satisfies.
|
|
||||||
chmod 700 "$TARGET_DIR" 2>/dev/null || \
|
|
||||||
warn "Could not set 0700 on $TARGET_DIR — 'mosaic fleet' mutations will fail as unsafe-permissions."
|
|
||||||
if [[ -d "$TARGET_DIR/fleet" ]]; then
|
|
||||||
chmod 700 "$TARGET_DIR/fleet" 2>/dev/null || \
|
|
||||||
warn "Could not set 0700 on $TARGET_DIR/fleet — 'mosaic fleet' mutations will fail as unsafe-permissions."
|
|
||||||
fi
|
|
||||||
# fleet/agents does not exist on a first install — the CLI creates it 0700 on
|
|
||||||
# demand. It is chmod'd here for the UPGRADE case: a tree built under umask 002
|
|
||||||
# has it at 0775, and the repair sweep below cannot rescue it, because stripping
|
|
||||||
# group/other write from 0755 leaves 0750 and `mode & 077` is still non-zero.
|
|
||||||
if [[ -d "$TARGET_DIR/fleet/agents" ]]; then
|
|
||||||
chmod 700 "$TARGET_DIR/fleet/agents" 2>/dev/null || \
|
|
||||||
warn "Could not set 0700 on $TARGET_DIR/fleet/agents — agent sessions will fail to start as unsafe-permissions."
|
|
||||||
fi
|
|
||||||
# credentials/ holds secrets and was never meant to be group-readable either.
|
|
||||||
# It is not on the fleet boundary, so a failure here breaks nothing — but it is
|
|
||||||
# the one directory where a silently-failed chmod leaves secrets group-readable,
|
|
||||||
# which is precisely the failure worth a line in the output.
|
|
||||||
chmod 700 "$TARGET_DIR/credentials" 2>/dev/null || \
|
|
||||||
warn "Could not set 0700 on $TARGET_DIR/credentials — stored secrets may be readable by other users on this host."
|
|
||||||
|
|
||||||
# Repair an existing tree. The umask above only governs directories this run
|
|
||||||
# creates, so a host installed under umask 002 before this fix keeps its 0775
|
|
||||||
# dirs through every upgrade and stays broken. Strips group/other WRITE only —
|
|
||||||
# never read or execute — so it can repair the boundary violation without
|
|
||||||
# changing who can traverse or read anything. Scoped to directories: file modes
|
|
||||||
# are the manifest's business, not this fix's.
|
|
||||||
find "$TARGET_DIR" -type d -perm /022 -exec chmod go-w {} + 2>/dev/null || true
|
|
||||||
|
|
||||||
# Reconcile contract files from defaults/ into the framework root: framework-owned
|
# Reconcile contract files from defaults/ into the framework root: framework-owned
|
||||||
# files (CONSTITUTION/AGENTS/STANDARDS) are overwritten every upgrade (a divergent
|
# files (CONSTITUTION/AGENTS/STANDARDS) are overwritten every upgrade (a divergent
|
||||||
# copy is backed up once); user-seeded files (TOOLS) are written on first install only.
|
# copy is backed up once); user-seeded files (TOOLS) are written on first install only.
|
||||||
|
|||||||
@@ -4,14 +4,6 @@ Documentation=https://git.mosaicstack.dev/mosaicstack/stack
|
|||||||
Requires=mosaic-tmux-holder.service
|
Requires=mosaic-tmux-holder.service
|
||||||
After=mosaic-tmux-holder.service
|
After=mosaic-tmux-holder.service
|
||||||
PartOf=mosaic-tmux-holder.service
|
PartOf=mosaic-tmux-holder.service
|
||||||
# Do not attempt a seat before its generated env exists. `install` enables this
|
|
||||||
# unit (WantedBy=default.target) but on a roster-v2 fleet the reconciler owns the
|
|
||||||
# generated env, so between `install` and the first `apply`/`regen --write` there
|
|
||||||
# is a boot window where ExecStart would run against an absent env file and the
|
|
||||||
# launcher would fail the unit. A skipped unit is the honest state for "enabled
|
|
||||||
# but not yet configured"; systemd re-evaluates the condition on every start, so
|
|
||||||
# the seat comes up on the next start once the reconciler has written env.
|
|
||||||
ConditionPathExists=%h/.config/mosaic/fleet/agents/%i.env.generated
|
|
||||||
|
|
||||||
[Service]
|
[Service]
|
||||||
Type=oneshot
|
Type=oneshot
|
||||||
|
|||||||
@@ -128,14 +128,6 @@ EOF
|
|||||||
sleep 30
|
sleep 30
|
||||||
EOF
|
EOF
|
||||||
chmod 700 "$AGENT_BIN/mosaic"
|
chmod 700 "$AGENT_BIN/mosaic"
|
||||||
# The launcher resolves the roster's runtime against PANE_PATH before it
|
|
||||||
# spawns anything (#1241), so the runtime this projection names has to be
|
|
||||||
# present here even though the fake `mosaic` above never execs it.
|
|
||||||
cat > "$AGENT_BIN/pi" <<'EOF'
|
|
||||||
#!/bin/sh
|
|
||||||
sleep 30
|
|
||||||
EOF
|
|
||||||
chmod 700 "$AGENT_BIN/pi"
|
|
||||||
server_environment_before=$(tmux -L "$TEST_SOCKET" show-environment -g | sort)
|
server_environment_before=$(tmux -L "$TEST_SOCKET" show-environment -g | sort)
|
||||||
server_sessions_before=$(tmux -L "$TEST_SOCKET" list-sessions | sort)
|
server_sessions_before=$(tmux -L "$TEST_SOCKET" list-sessions | sort)
|
||||||
if /usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \
|
if /usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \
|
||||||
|
|||||||
@@ -225,54 +225,6 @@ else
|
|||||||
warn "mosaic-ensure-sequential-thinking helper missing"
|
warn "mosaic-ensure-sequential-thinking helper missing"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Fleet transport binary (#1240).
|
|
||||||
#
|
|
||||||
# `mosaic fleet --help` reads "Manage the local Mosaic tmux fleet" and every
|
|
||||||
# roster the CLI scaffolds sets `transport: tmux`, but nothing in the install
|
|
||||||
# path provides tmux and, until now, nothing here noticed it was absent. On a
|
|
||||||
# greenfield host that produced a fleet which installed clean, started clean,
|
|
||||||
# and had no live seat; `mosaic fleet ps` was the operator's first and only
|
|
||||||
# signal that anything was wrong.
|
|
||||||
#
|
|
||||||
# The roster's own `transport:` is read rather than assumed, so a host that
|
|
||||||
# declares something other than tmux is told about the binary it actually
|
|
||||||
# needs. Absent a roster the check still runs — `mosaic fleet init` will
|
|
||||||
# scaffold a tmux fleet on this host, and finding out beforehand is the point.
|
|
||||||
#
|
|
||||||
# `tools/install.sh` carries a deliberately parallel check at the end of its
|
|
||||||
# summary. The two are separate because the installer must be able to say this
|
|
||||||
# before the framework's own scripts are guaranteed to be on disk; keep their
|
|
||||||
# wording in step.
|
|
||||||
fleet_declared_transport() {
|
|
||||||
local roster="$MOSAIC_HOME/fleet/roster.yaml"
|
|
||||||
local declared=""
|
|
||||||
|
|
||||||
if [[ -f "$roster" ]]; then
|
|
||||||
declared="$(sed -n 's/^[[:space:]]*transport:[[:space:]]*//p' "$roster" | head -1 |
|
|
||||||
tr -d '"'\''' | tr -d '\r' | awk '{print $1}')"
|
|
||||||
fi
|
|
||||||
|
|
||||||
printf '%s\n' "${declared:-tmux}"
|
|
||||||
}
|
|
||||||
|
|
||||||
check_fleet_transport() {
|
|
||||||
local transport
|
|
||||||
transport="$(fleet_declared_transport)"
|
|
||||||
|
|
||||||
if command -v "$transport" >/dev/null 2>&1; then
|
|
||||||
pass "Fleet transport available: $transport"
|
|
||||||
return
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [[ -f "$MOSAIC_HOME/fleet/roster.yaml" ]]; then
|
|
||||||
warn "Fleet transport '$transport' is not installed — this host has a roster and no seat can launch. Install it (e.g. sudo apt-get install -y $transport), then 'mosaic fleet start'."
|
|
||||||
else
|
|
||||||
warn "Fleet transport '$transport' is not installed — 'mosaic fleet' cannot run seats here. Install it (e.g. sudo apt-get install -y $transport) before 'mosaic fleet init'."
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
check_fleet_transport
|
|
||||||
|
|
||||||
# Legacy migration surfaces should no longer contain symlink trees.
|
# Legacy migration surfaces should no longer contain symlink trees.
|
||||||
legacy_paths=(
|
legacy_paths=(
|
||||||
"$HOME/.claude/agent-guides"
|
"$HOME/.claude/agent-guides"
|
||||||
|
|||||||
@@ -1,215 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# Covers the #1240 fleet-transport checks in `mosaic-doctor` and in
|
|
||||||
# `tools/install.sh`.
|
|
||||||
#
|
|
||||||
# Both checks answer the same question — "can a seat actually launch on this
|
|
||||||
# host?" — from two different places, because the installer has to be able to
|
|
||||||
# answer it before the framework's own scripts are guaranteed to be on disk.
|
|
||||||
# Two implementations of one rule is exactly the shape that drifts, so this
|
|
||||||
# harness drives BOTH, in one file, from the same table of cases.
|
|
||||||
#
|
|
||||||
# The functions are extracted from the shipped scripts rather than copied here.
|
|
||||||
# A test that carries its own copy of the logic is a test that keeps passing
|
|
||||||
# after the shipped copy changes — the failure mode this whole change is about.
|
|
||||||
# Extraction is by exact function header and a closing brace in column one; if
|
|
||||||
# either script is reshaped so that stops matching, the extraction yields
|
|
||||||
# nothing and this fails loudly instead of silently measuring an empty string.
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
|
|
||||||
DOCTOR="$SCRIPT_DIR/mosaic-doctor"
|
|
||||||
# framework/tools/_scripts -> framework/tools -> framework -> mosaic -> packages -> repo
|
|
||||||
INSTALLER=$(cd -- "$SCRIPT_DIR/../../../../.." && pwd)/tools/install.sh
|
|
||||||
|
|
||||||
fail() {
|
|
||||||
echo "FAIL: $*" >&2
|
|
||||||
exit 1
|
|
||||||
}
|
|
||||||
|
|
||||||
[ -f "$DOCTOR" ] || fail "missing mosaic-doctor at $DOCTOR"
|
|
||||||
[ -f "$INSTALLER" ] || fail "missing install.sh at $INSTALLER"
|
|
||||||
|
|
||||||
ROOT=$(mktemp -d)
|
|
||||||
trap 'rm -rf "$ROOT"' EXIT
|
|
||||||
|
|
||||||
# The cases below run with PATH set to a directory that deliberately does not
|
|
||||||
# contain a shell, and a PATH assignment on a command also governs how that
|
|
||||||
# command is looked up — so bash has to be named absolutely or it becomes the
|
|
||||||
# thing that is missing.
|
|
||||||
BASH_BIN=$(command -v bash) || fail "host is missing 'bash'"
|
|
||||||
|
|
||||||
# A PATH containing exactly the utilities these functions use and nothing else.
|
|
||||||
# The absent-transport cases are only meaningful on a PATH where the transport
|
|
||||||
# is genuinely unresolvable, and this host (like most) has tmux in /usr/bin —
|
|
||||||
# so the system path cannot be part of the path under test.
|
|
||||||
FAKE_BIN="$ROOT/bin"
|
|
||||||
mkdir -p "$FAKE_BIN"
|
|
||||||
for utility in sed head tr awk; do
|
|
||||||
utility_path=$(command -v "$utility") || fail "host is missing '$utility'"
|
|
||||||
ln -s "$utility_path" "$FAKE_BIN/$utility"
|
|
||||||
done
|
|
||||||
|
|
||||||
if PATH="$FAKE_BIN" command -v tmux >/dev/null 2>&1; then
|
|
||||||
fail "'tmux' is resolvable on the minimal test path; absent-transport cases are not measurable"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Extract a function by its exact header, up to a closing brace in column one.
|
|
||||||
extract_function() {
|
|
||||||
local source_file="$1"
|
|
||||||
local function_name="$2"
|
|
||||||
local destination="$3"
|
|
||||||
|
|
||||||
awk -v name="$function_name" '
|
|
||||||
$0 == name "() {" { collecting = 1 }
|
|
||||||
collecting { print }
|
|
||||||
collecting && $0 == "}" { exit }
|
|
||||||
' "$source_file" > "$destination"
|
|
||||||
|
|
||||||
grep -qF "$function_name() {" "$destination" ||
|
|
||||||
fail "could not extract '$function_name' from $source_file — has it been renamed or reshaped?"
|
|
||||||
# An unterminated extraction would be a syntax error the moment it is sourced,
|
|
||||||
# but saying so here names the cause instead of leaving a bash parse error.
|
|
||||||
bash -n "$destination" ||
|
|
||||||
fail "extracted '$function_name' does not parse; the closing brace was probably not found"
|
|
||||||
}
|
|
||||||
|
|
||||||
extract_function "$DOCTOR" fleet_declared_transport "$ROOT/doctor-declared.sh"
|
|
||||||
extract_function "$DOCTOR" check_fleet_transport "$ROOT/doctor-check.sh"
|
|
||||||
extract_function "$INSTALLER" check_fleet_transport "$ROOT/installer-check.sh"
|
|
||||||
|
|
||||||
# Build a MOSAIC_HOME, optionally with a roster declaring a transport.
|
|
||||||
make_home() {
|
|
||||||
local home="$ROOT/$1"
|
|
||||||
local declared="${2-}"
|
|
||||||
|
|
||||||
rm -rf "$home"
|
|
||||||
mkdir -p "$home"
|
|
||||||
if [ -n "$declared" ]; then
|
|
||||||
mkdir -p "$home/fleet"
|
|
||||||
cat > "$home/fleet/roster.yaml" <<EOF
|
|
||||||
version: 2
|
|
||||||
generation: 1
|
|
||||||
transport: $declared
|
|
||||||
agents: []
|
|
||||||
EOF
|
|
||||||
fi
|
|
||||||
printf '%s\n' "$home"
|
|
||||||
}
|
|
||||||
|
|
||||||
# Run the doctor's check against a given home and path, capturing which
|
|
||||||
# reporter the check chose. The real `pass` prints only under `--verbose` and
|
|
||||||
# the real `warn` always prints; these stubs make both unconditional on
|
|
||||||
# purpose, because what is under test is the severity the check selects, not
|
|
||||||
# whether the default verbosity happens to show it. A check that warned where
|
|
||||||
# it should pass would otherwise be invisible here.
|
|
||||||
run_doctor_check() {
|
|
||||||
local home="$1"
|
|
||||||
local path="$2"
|
|
||||||
|
|
||||||
MOSAIC_HOME="$home" PATH="$path" "$BASH_BIN" --noprofile --norc -c '
|
|
||||||
set -euo pipefail
|
|
||||||
warn() { echo "[WARN] $*"; }
|
|
||||||
pass() { echo "[OK] $*"; }
|
|
||||||
MOSAIC_HOME="$1"
|
|
||||||
source "$2"
|
|
||||||
source "$3"
|
|
||||||
check_fleet_transport
|
|
||||||
' _ "$home" "$ROOT/doctor-declared.sh" "$ROOT/doctor-check.sh" 2>&1
|
|
||||||
}
|
|
||||||
|
|
||||||
run_installer_check() {
|
|
||||||
local home="$1"
|
|
||||||
local path="$2"
|
|
||||||
|
|
||||||
MOSAIC_HOME="$home" PATH="$path" "$BASH_BIN" --noprofile --norc -c '
|
|
||||||
set -euo pipefail
|
|
||||||
warn() { echo "[WARN] $*"; }
|
|
||||||
C="" RESET=""
|
|
||||||
MOSAIC_HOME="$1"
|
|
||||||
source "$2"
|
|
||||||
check_fleet_transport
|
|
||||||
' _ "$home" "$ROOT/installer-check.sh" 2>&1
|
|
||||||
}
|
|
||||||
|
|
||||||
# A transport that exists. Named tmux because that is what the default roster
|
|
||||||
# declares; the binary never runs, it only has to resolve.
|
|
||||||
PRESENT_BIN="$ROOT/present-bin"
|
|
||||||
mkdir -p "$PRESENT_BIN"
|
|
||||||
printf '#!/usr/bin/env bash\nexit 0\n' > "$PRESENT_BIN/tmux"
|
|
||||||
chmod +x "$PRESENT_BIN/tmux"
|
|
||||||
PATH_WITH_TMUX="$PRESENT_BIN:$FAKE_BIN"
|
|
||||||
|
|
||||||
# ── absent, no roster ────────────────────────────────────────────────────────
|
|
||||||
# Nothing has been configured yet, so the honest thing to point at is `init`.
|
|
||||||
home=$(make_home no-roster)
|
|
||||||
|
|
||||||
output=$(run_doctor_check "$home" "$FAKE_BIN")
|
|
||||||
echo "$output" | grep -qF '[WARN]' || fail "doctor did not warn when tmux was absent"
|
|
||||||
echo "$output" | grep -qF 'tmux' || fail "doctor warning did not name the transport"
|
|
||||||
echo "$output" | grep -qF 'mosaic fleet init' || fail "doctor did not point a rosterless host at init"
|
|
||||||
|
|
||||||
output=$(run_installer_check "$home" "$FAKE_BIN")
|
|
||||||
echo "$output" | grep -qF '[WARN]' || fail "installer did not warn when tmux was absent"
|
|
||||||
echo "$output" | grep -qF 'reports success and no seat comes up' ||
|
|
||||||
fail "installer warning did not say what the missing transport actually breaks"
|
|
||||||
|
|
||||||
# ── absent, roster present ───────────────────────────────────────────────────
|
|
||||||
# A configured fleet that cannot launch is a stronger statement than a
|
|
||||||
# hypothetical one, and the message says so.
|
|
||||||
home=$(make_home with-roster tmux)
|
|
||||||
|
|
||||||
output=$(run_doctor_check "$home" "$FAKE_BIN")
|
|
||||||
echo "$output" | grep -qF '[WARN]' || fail "doctor did not warn with a roster present and tmux absent"
|
|
||||||
echo "$output" | grep -qF 'roster' || fail "doctor did not mention the roster it found"
|
|
||||||
echo "$output" | grep -qF 'mosaic fleet start' || fail "doctor did not point a configured host at start"
|
|
||||||
|
|
||||||
# ── present ──────────────────────────────────────────────────────────────────
|
|
||||||
# Silence from the installer, and a pass (not a warning) from the audit.
|
|
||||||
for home_name in no-roster with-roster; do
|
|
||||||
home="$ROOT/$home_name"
|
|
||||||
|
|
||||||
output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
|
|
||||||
if echo "$output" | grep -qF '[WARN]'; then
|
|
||||||
fail "doctor warned about the transport while tmux was present ($home_name)"
|
|
||||||
fi
|
|
||||||
echo "$output" | grep -qF '[OK]' || fail "doctor did not record a pass with tmux present ($home_name)"
|
|
||||||
|
|
||||||
output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
|
|
||||||
if [ -n "$output" ]; then
|
|
||||||
fail "installer was not silent with tmux present ($home_name): $output"
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
|
|
||||||
# ── the roster declares something other than tmux ────────────────────────────
|
|
||||||
# The roster is read, not assumed. A host that declares a different transport
|
|
||||||
# is told about the binary it actually needs, and never about tmux — being sent
|
|
||||||
# to install the wrong package is worse than no advice at all.
|
|
||||||
home=$(make_home other-transport zellij)
|
|
||||||
|
|
||||||
output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
|
|
||||||
echo "$output" | grep -qF 'zellij' || fail "doctor ignored the roster's declared transport"
|
|
||||||
if echo "$output" | grep -qF 'tmux'; then
|
|
||||||
fail "doctor named tmux for a host whose roster declares zellij"
|
|
||||||
fi
|
|
||||||
|
|
||||||
output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
|
|
||||||
echo "$output" | grep -qF 'zellij' || fail "installer ignored the roster's declared transport"
|
|
||||||
if echo "$output" | grep -qF 'tmux'; then
|
|
||||||
fail "installer named tmux for a host whose roster declares zellij"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# ── a quoted or trailing-comment transport value ─────────────────────────────
|
|
||||||
# YAML permits both and neither is exotic; a check that installs `tmux"` or
|
|
||||||
# reads `tmux # default` as a binary name would send the operator nowhere.
|
|
||||||
home=$(make_home quoted-transport '"tmux" # the only transport today')
|
|
||||||
|
|
||||||
output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
|
|
||||||
echo "$output" | grep -qF '[OK] Fleet transport available: tmux' ||
|
|
||||||
fail "doctor did not parse a quoted/commented transport value: $output"
|
|
||||||
|
|
||||||
output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
|
|
||||||
if [ -n "$output" ]; then
|
|
||||||
fail "installer did not parse a quoted/commented transport value: $output"
|
|
||||||
fi
|
|
||||||
|
|
||||||
echo "ok - fleet transport checks (mosaic-doctor + install.sh)"
|
|
||||||
@@ -233,36 +233,8 @@ assert_owned_tmux_server() {
|
|||||||
fail "tmux server ownership or environment validation failed"
|
fail "tmux server ownership or environment validation failed"
|
||||||
}
|
}
|
||||||
|
|
||||||
# Lease-broker socket preflight (#1292). The gated runtime (`mosaic yolo …` →
|
# Validate exact server ownership before querying, cleaning, or creating any
|
||||||
# launch-runtime.py) registers with the broker or dies ~4 seconds in, with the
|
# managed session. An unmanaged or contaminated named socket is never repaired.
|
||||||
# diagnostic invisible because tmux destroys the dead pane. This check runs
|
|
||||||
# BEFORE any tmux effect — including the ownership probe below — so a host
|
|
||||||
# without a broker produces a named, surviving refusal instead of a doomed
|
|
||||||
# pane. Exit 75 (EX_TEMPFAIL), distinct from 64 (bad projection) and 69 (host
|
|
||||||
# not ready for other reasons); the agent@ unit is Type=oneshot with no
|
|
||||||
# Restart=, so the failed unit keeps its message instead of looping. Socket
|
|
||||||
# resolution matches launch.ts's defaultLeaseBrokerSocket precedence exactly.
|
|
||||||
# This preflight DETECTS and REFUSES — it never starts the broker (activation
|
|
||||||
# belongs to the fleet control plane; a component that both detects and fixes
|
|
||||||
# cannot be used to measure whether the fix worked).
|
|
||||||
broker_socket_path() {
|
|
||||||
if [ -n "${MOSAIC_LEASE_BROKER_SOCKET:-}" ]; then
|
|
||||||
printf '%s\n' "$MOSAIC_LEASE_BROKER_SOCKET"
|
|
||||||
return 0
|
|
||||||
fi
|
|
||||||
local runtime_dir="${XDG_RUNTIME_DIR:-/run/user/$(id -u)}"
|
|
||||||
printf '%s\n' "${runtime_dir}/mosaic-lease/broker.sock"
|
|
||||||
}
|
|
||||||
|
|
||||||
if [ "$MODE" = "launch" ]; then
|
|
||||||
_broker_socket=$(broker_socket_path)
|
|
||||||
if [ ! -S "$_broker_socket" ]; then
|
|
||||||
echo "[fleet] FAIL_LAUNCH broker-absent: lease broker socket ${_broker_socket} missing; runtime launch denied (#1292)." >&2
|
|
||||||
echo "[fleet] remedy: systemctl --user enable --now mosaic-lease-broker.service (or reinstall via: mosaic fleet install)" >&2
|
|
||||||
exit 75
|
|
||||||
fi
|
|
||||||
fi
|
|
||||||
|
|
||||||
assert_owned_tmux_server
|
assert_owned_tmux_server
|
||||||
|
|
||||||
if [ "$MODE" = interaction ]; then
|
if [ "$MODE" = interaction ]; then
|
||||||
@@ -314,36 +286,6 @@ _build_runtime_bin_prefix() {
|
|||||||
MOSAIC_RUNTIME_BIN_PREFIX=$(_build_runtime_bin_prefix)
|
MOSAIC_RUNTIME_BIN_PREFIX=$(_build_runtime_bin_prefix)
|
||||||
PANE_PATH=${MOSAIC_RUNTIME_BIN_PREFIX:+${MOSAIC_RUNTIME_BIN_PREFIX}:}/usr/local/bin:/usr/bin:/bin
|
PANE_PATH=${MOSAIC_RUNTIME_BIN_PREFIX:+${MOSAIC_RUNTIME_BIN_PREFIX}:}/usr/local/bin:/usr/bin:/bin
|
||||||
|
|
||||||
# #1241. The pane runs `mosaic yolo <runtime>` under PANE_PATH with a cleared
|
|
||||||
# environment. A binary missing from *that* path is a pane that dies in under a
|
|
||||||
# second, inside a session nobody is attached to, with its diagnostic scrolled
|
|
||||||
# into a pane tmux then destroys. Resolve both here, before any effect, where
|
|
||||||
# the failure is still attributable to the thing that caused it.
|
|
||||||
#
|
|
||||||
# `mosaic yolo <runtime>` runs checkRuntime(runtime) and the binary it looks for
|
|
||||||
# is named exactly like the runtime, so resolving the runtime name is the same
|
|
||||||
# question the pane will ask a moment later — asked while an operator can still
|
|
||||||
# see the answer.
|
|
||||||
_resolve_in_pane_path() {
|
|
||||||
PATH="$PANE_PATH" command -v -- "$1" 2>/dev/null
|
|
||||||
}
|
|
||||||
|
|
||||||
# Exit 69 (EX_UNAVAILABLE): the seat cannot be provided. Distinguished from the
|
|
||||||
# 64 (EX_USAGE) rejections above, which mean the projection itself was bad —
|
|
||||||
# here the data is fine and the host is not ready. Callers tell the individual
|
|
||||||
# cases apart by `code=`, the same way fail_env's many codes share exit 64.
|
|
||||||
fail_launch() {
|
|
||||||
local code="$1"
|
|
||||||
shift
|
|
||||||
echo "ERROR: agent launch aborted: code=${code} agent=${AGENT_NAME} $*" >&2
|
|
||||||
exit 69
|
|
||||||
}
|
|
||||||
|
|
||||||
for required_binary in mosaic "$MOSAIC_AGENT_RUNTIME"; do
|
|
||||||
_resolve_in_pane_path "$required_binary" >/dev/null ||
|
|
||||||
fail_launch missing-binary "'${required_binary}' is not on the pane PATH (${PANE_PATH})"
|
|
||||||
done
|
|
||||||
|
|
||||||
_ensure_claude_workdir_trusted() {
|
_ensure_claude_workdir_trusted() {
|
||||||
local workdir="$1"
|
local workdir="$1"
|
||||||
local resolved
|
local resolved
|
||||||
@@ -442,19 +384,6 @@ if [ -n "$PANE_PID" ]; then
|
|||||||
_start_heartbeat_sidecar "$AGENT_NAME" "$PANE_PID" \
|
_start_heartbeat_sidecar "$AGENT_NAME" "$PANE_PID" \
|
||||||
"$MOSAIC_HEARTBEAT_RUN_DIR" "$MOSAIC_HEARTBEAT_INTERVAL" || \
|
"$MOSAIC_HEARTBEAT_RUN_DIR" "$MOSAIC_HEARTBEAT_INTERVAL" || \
|
||||||
echo "WARNING: heartbeat sidecar could not be started for $AGENT_NAME" >&2
|
echo "WARNING: heartbeat sidecar could not be started for $AGENT_NAME" >&2
|
||||||
elif _tmux has-session -t "=${AGENT_NAME}:0.0" 2>/dev/null; then
|
|
||||||
# #1241. Session present, no pane PID after a second of retries. Whatever this
|
|
||||||
# is, it is not a seat an operator can use, so it is not a success either.
|
|
||||||
fail_launch pane-pid-unresolved \
|
|
||||||
"tmux reports the session but no pane PID after 5 attempts"
|
|
||||||
else
|
else
|
||||||
# #1241. This branch used to print a WARNING about the heartbeat sidecar and
|
echo "WARNING: could not resolve pane PID for $AGENT_NAME — heartbeat sidecar not started" >&2
|
||||||
# exit 0. It is not a heartbeat problem: tmux destroys a session when its pane
|
|
||||||
# command exits, so an absent session one second after new-session means the
|
|
||||||
# runtime died on startup. Reporting it as success is what let `fleet start`
|
|
||||||
# return 0 over three dead panes — the launcher knew, and said the wrong thing
|
|
||||||
# at the wrong severity to the wrong layer.
|
|
||||||
fail_launch pane-did-not-survive \
|
|
||||||
"the pane exited immediately and tmux destroyed the session;" \
|
|
||||||
"run 'mosaic yolo ${MOSAIC_AGENT_RUNTIME}' in ${MOSAIC_AGENT_WORKDIR} to see why"
|
|
||||||
fi
|
fi
|
||||||
|
|||||||
@@ -1,216 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# CI-fit regression suite for the #1292 lease-broker socket preflight in
|
|
||||||
# start-agent-session.sh.
|
|
||||||
#
|
|
||||||
# WHY THIS SUITE IS CI-FIT WHERE test-start-agent-session.sh IS NOT (#1017/#1270
|
|
||||||
# context): that older suite's precondition is "the host does not have the pi
|
|
||||||
# binary", which a CI image that ships pi violates — its guard correctly
|
|
||||||
# refuses to report a pass there, so it is excluded from the chain. THIS suite
|
|
||||||
# controls its own preconditions instead of inheriting them from the host: a
|
|
||||||
# fake tmux on PATH, a fake mosaic on PATH, a real unix socket created in a
|
|
||||||
# tmpdir, a hermetic env (env -i, fake HOME, GIT_CONFIG_GLOBAL severed). It
|
|
||||||
# never depends on what the host has installed, so a green here means the same
|
|
||||||
# thing on every host. Anyone adding cases: keep that property — no case may
|
|
||||||
# depend on host state.
|
|
||||||
#
|
|
||||||
# The failure this suite is written down to catch (#1292): a seat launched on a
|
|
||||||
# host with no lease broker dies ~4 seconds in at registration, with the
|
|
||||||
# diagnostic invisible because tmux destroys the dead pane. The preflight runs
|
|
||||||
# BEFORE any tmux effect and refuses with a NAMED code (exit 75, EX_TEMPFAIL)
|
|
||||||
# so the message survives. The agent@ unit is Type=oneshot with no Restart=,
|
|
||||||
# so a failed unit keeps its output instead of looping.
|
|
||||||
#
|
|
||||||
# Cases:
|
|
||||||
# 1. absent socket -> exit 75, message names broker-absent + socket path +
|
|
||||||
# remedy, and NO tmux session was ever created (the doomed-pane half).
|
|
||||||
# 2. present socket (real unix socket in tmpdir) -> proceeds PAST the
|
|
||||||
# preflight (the suite then stops at the next precondition, proving the
|
|
||||||
# preflight was not the refusal).
|
|
||||||
# 3. explicit MOSAIC_LEASE_BROKER_SOCKET wins over XDG_RUNTIME_DIR default.
|
|
||||||
# 4. --stop mode does NOT require the broker (teardown must not be fenced on
|
|
||||||
# a component whose absence is exactly what teardown may follow).
|
|
||||||
#
|
|
||||||
# Sabotage control, run by the developer (not in-suite): remove the preflight
|
|
||||||
# block from start-agent-session.sh, re-run — case 1 fails (a tmux session is
|
|
||||||
# created / exit is not 75), cases 2-4 still pass; restore byte-identically.
|
|
||||||
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
||||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/agent-session-broker-preflight}"
|
|
||||||
FAKE_HOME="$WORK_DIR/home"
|
|
||||||
BIN_DIR="$WORK_DIR/bin"
|
|
||||||
ENV_DIR="$WORK_DIR/env"
|
|
||||||
SOCK_DIR="$WORK_DIR/sockets"
|
|
||||||
LOG_FILE="$WORK_DIR/tmux-calls.log"
|
|
||||||
|
|
||||||
rm -rf "$WORK_DIR"
|
|
||||||
# The script asserts a managed directory tree under MOSAIC_HOME: mosaic/,
|
|
||||||
# mosaic/fleet/, mosaic/fleet/agents/ — private (0700/0750-style) modes, no
|
|
||||||
# symlinks — plus a per-agent env projection. Build the full tree the launcher
|
|
||||||
# expects so the suite reaches the BROKER preflight rather than dying at
|
|
||||||
# environment validation.
|
|
||||||
mkdir -p "$FAKE_HOME/.config/mosaic/fleet/agents" "$BIN_DIR" "$SOCK_DIR"
|
|
||||||
chmod 700 "$FAKE_HOME/.config/mosaic" "$FAKE_HOME/.config/mosaic/fleet/agents"
|
|
||||||
chmod 750 "$FAKE_HOME/.config/mosaic/fleet"
|
|
||||||
cat > "$FAKE_HOME/.config/mosaic/fleet/agents/preflight-test.env.generated" <<'ENVEOF'
|
|
||||||
MOSAIC_AGENT_NAME=preflight-test
|
|
||||||
MOSAIC_AGENT_CLASS=worker
|
|
||||||
MOSAIC_AGENT_RUNTIME=pi
|
|
||||||
MOSAIC_AGENT_MODEL=
|
|
||||||
MOSAIC_AGENT_REASONING=
|
|
||||||
MOSAIC_AGENT_TOOL_POLICY=code
|
|
||||||
MOSAIC_AGENT_WORKDIR=/tmp
|
|
||||||
MOSAIC_TMUX_SOCKET=mosaic-fleet
|
|
||||||
ENVEOF
|
|
||||||
chmod 600 "$FAKE_HOME/.config/mosaic/fleet/agents/preflight-test.env.generated"
|
|
||||||
|
|
||||||
# ─── Fake tmux: records every invocation; new-session marks the marker. ────
|
|
||||||
: > "$LOG_FILE"
|
|
||||||
cat > "$BIN_DIR/tmux" <<SH
|
|
||||||
#!/usr/bin/env bash
|
|
||||||
printf 'tmux %s\n' "\$*" >> "$LOG_FILE"
|
|
||||||
if [[ "\$*" == *new-session* ]]; then
|
|
||||||
echo "TMUX-NEW-SESSION-INVOKED" >> "$LOG_FILE"
|
|
||||||
fi
|
|
||||||
exit 0
|
|
||||||
SH
|
|
||||||
chmod +x "$BIN_DIR/tmux"
|
|
||||||
|
|
||||||
# ─── Fake mosaic/pi binaries so the script proceeds past its own lookups. ───
|
|
||||||
for bin in mosaic pi claude; do
|
|
||||||
printf '#!/usr/bin/env bash\nexit 0\n' > "$BIN_DIR/$bin"
|
|
||||||
chmod +x "$BIN_DIR/$bin"
|
|
||||||
done
|
|
||||||
|
|
||||||
# ─── Minimal launch environment the script expects. ────────────────────────
|
|
||||||
# (Enough for the preflight to be reached; later stages will still fail in
|
|
||||||
# case 2 — that is expected and asserted.)
|
|
||||||
run_session_script() {
|
|
||||||
local mode="$1"; shift
|
|
||||||
(
|
|
||||||
cd "$WORK_DIR"
|
|
||||||
env -i HOME="$FAKE_HOME" PATH="$BIN_DIR:/usr/bin:/bin" \
|
|
||||||
GIT_CONFIG_GLOBAL=/dev/null GIT_CONFIG_SYSTEM=/dev/null \
|
|
||||||
MOSAIC_HOME="$FAKE_HOME/.config/mosaic" \
|
|
||||||
AGENT_NAME=preflight-test \
|
|
||||||
"$@" \
|
|
||||||
bash "$SCRIPT_DIR/start-agent-session.sh" $mode preflight-test
|
|
||||||
)
|
|
||||||
}
|
|
||||||
|
|
||||||
fail=0
|
|
||||||
assert() {
|
|
||||||
local desc="$1" expected="$2" actual="$3"
|
|
||||||
if [[ "$expected" != "$actual" ]]; then
|
|
||||||
echo "FAIL: $desc — expected '$expected', got '$actual'" >&2
|
|
||||||
fail=1
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
assert_contains() {
|
|
||||||
local desc="$1" haystack="$2" needle="$3"
|
|
||||||
[[ "$haystack" == *"$needle"* ]] || { echo "FAIL: $desc — missing '$needle' in: $haystack" >&2; fail=1; }
|
|
||||||
}
|
|
||||||
assert_not_contains() {
|
|
||||||
local desc="$1" haystack="$2" needle="$3"
|
|
||||||
if [[ "$haystack" == *"$needle"* ]]; then
|
|
||||||
echo "FAIL: $desc — must not contain '$needle'" >&2
|
|
||||||
fail=1
|
|
||||||
fi
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# ─── 1. Absent socket → named refusal, NO tmux session. ────────────────────
|
|
||||||
: > "$LOG_FILE"
|
|
||||||
stderr_file="$WORK_DIR/stderr-1.tmp"
|
|
||||||
set +e
|
|
||||||
out=$(run_session_script "" MOSAIC_LEASE_BROKER_SOCKET="$SOCK_DIR/absent.sock" 2>"$stderr_file")
|
|
||||||
rc=$?
|
|
||||||
set -e
|
|
||||||
assert "absent socket exit code" "75" "$rc"
|
|
||||||
err=$(cat "$stderr_file")
|
|
||||||
assert_contains "absent socket names the failure" "$err" "FAIL_LAUNCH broker-absent"
|
|
||||||
assert_contains "absent socket names the socket path" "$err" "$SOCK_DIR/absent.sock"
|
|
||||||
assert_contains "absent socket names a remedy" "$err" "mosaic fleet install"
|
|
||||||
log1=$(cat "$LOG_FILE")
|
|
||||||
assert_not_contains "absent socket must not create a tmux session" "$log1" "TMUX-NEW-SESSION-INVOKED"
|
|
||||||
|
|
||||||
# ─── 2. Present socket → passes the preflight. ─────────────────────────────
|
|
||||||
# Expected: ownership/env checks AFTER the preflight may refuse (fixture is
|
|
||||||
# minimal by design); the assertion is only that the refusal is NOT
|
|
||||||
# broker-absent and the exit is NOT 75.
|
|
||||||
# Create a REAL unix socket: a detached python holder binds it and stays alive
|
|
||||||
# for the duration (bash cannot create sockets; a foreground python would
|
|
||||||
# close the socket on exit and -S on a closed-but-unlinked path fails). Written
|
|
||||||
# as a script file + setsid nohup so no job-control/heredoc interaction with
|
|
||||||
# set -e can silently kill the suite.
|
|
||||||
# AF_UNIX binds cap at 108 path bytes; the suite's workdir exceeds that, so
|
|
||||||
# the live socket lives at a SHORT path under /tmp (unique per run, cleaned
|
|
||||||
# with the suite). The preflight takes its socket path explicitly, so this
|
|
||||||
# stays fully controlled.
|
|
||||||
LIVE_SOCK=$(mktemp -u /tmp/mosaic-preflight-XXXXXX.sock)
|
|
||||||
trap 'rm -f "$LIVE_SOCK"' EXIT
|
|
||||||
rm -f "$SOCK_DIR/live.sock" "$LIVE_SOCK"
|
|
||||||
cat > "$SOCK_DIR/holder.py" <<'PY'
|
|
||||||
import socket, sys, time
|
|
||||||
path = sys.argv[1]
|
|
||||||
s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
|
|
||||||
s.bind(path)
|
|
||||||
s.listen(1)
|
|
||||||
time.sleep(120)
|
|
||||||
PY
|
|
||||||
python3 "$SOCK_DIR/holder.py" "$LIVE_SOCK" >/dev/null 2>"$SOCK_DIR/holder.err" &
|
|
||||||
HOLDER_PID=$!
|
|
||||||
# Wait for the socket object to exist (bind is near-instant, but do not race it).
|
|
||||||
for _ in $(seq 1 50); do
|
|
||||||
[ -S "$LIVE_SOCK" ] && break
|
|
||||||
sleep 0.1
|
|
||||||
done
|
|
||||||
if [ ! -S "$LIVE_SOCK" ]; then
|
|
||||||
echo "FAIL: could not create live socket fixture (holder pid $HOLDER_PID)" >&2
|
|
||||||
ps -p "$HOLDER_PID" -o pid,stat,cmd --no-headers >&2 || echo "(holder exited)" >&2
|
|
||||||
cat "$SOCK_DIR/holder.err" >&2 || true
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
: > "$LOG_FILE"
|
|
||||||
set +e
|
|
||||||
out=$(run_session_script "" MOSAIC_LEASE_BROKER_SOCKET="$LIVE_SOCK" 2>"$WORK_DIR/stderr-2.tmp")
|
|
||||||
rc=$?
|
|
||||||
set -e
|
|
||||||
# The preflight PASSED if the failure (whatever later stage refused) is NOT
|
|
||||||
# the broker refusal, and tmux was reached or a later precondition named
|
|
||||||
# something else.
|
|
||||||
err2=$(cat "$WORK_DIR/stderr-2.tmp")
|
|
||||||
assert_not_contains "live socket must not refuse broker-absent" "$err2" "broker-absent"
|
|
||||||
if [[ "$rc" == "75" ]]; then
|
|
||||||
echo "FAIL: live socket — preflight still refused (exit 75) with a live socket" >&2
|
|
||||||
fail=1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# ─── 3. Explicit socket env wins over XDG default. ─────────────────────────
|
|
||||||
set +e
|
|
||||||
out=$(run_session_script "" XDG_RUNTIME_DIR="$SOCK_DIR/no-runtime-here" MOSAIC_LEASE_BROKER_SOCKET="$SOCK_DIR/absent2.sock" 2>"$WORK_DIR/stderr-3.tmp")
|
|
||||||
rc=$?
|
|
||||||
set -e
|
|
||||||
assert "explicit env wins (exit 75)" "75" "$rc"
|
|
||||||
assert_contains "explicit env path named" "$(cat "$WORK_DIR/stderr-3.tmp")" "$SOCK_DIR/absent2.sock"
|
|
||||||
|
|
||||||
# ─── 4. --stop is not fenced on the broker. ────────────────────────────────
|
|
||||||
: > "$LOG_FILE"
|
|
||||||
set +e
|
|
||||||
out=$(run_session_script "--stop" MOSAIC_LEASE_BROKER_SOCKET="$SOCK_DIR/absent3.sock" 2>"$WORK_DIR/stderr-4.tmp")
|
|
||||||
rc=$?
|
|
||||||
set -e
|
|
||||||
err4=$(cat "$WORK_DIR/stderr-4.tmp")
|
|
||||||
assert_not_contains "--stop must not refuse broker-absent" "$err4" "broker-absent"
|
|
||||||
if [[ "$rc" == "75" ]]; then
|
|
||||||
echo "FAIL: --stop — exit 75 means teardown was fenced on the broker" >&2
|
|
||||||
fail=1
|
|
||||||
fi
|
|
||||||
|
|
||||||
kill "$HOLDER_PID" 2>/dev/null || true
|
|
||||||
|
|
||||||
if [[ "$fail" -eq 0 ]]; then
|
|
||||||
echo "start-agent-session lease-broker preflight regression passed"
|
|
||||||
fi
|
|
||||||
exit "$fail"
|
|
||||||
@@ -23,26 +23,8 @@ index=0
|
|||||||
if [ "${args[0]:-}" = -L ]; then index=2; fi
|
if [ "${args[0]:-}" = -L ]; then index=2; fi
|
||||||
case "${args[$index]:-}" in
|
case "${args[$index]:-}" in
|
||||||
has-session)
|
has-session)
|
||||||
# The holder always answers. MOSAIC_TEST_HELD_SESSIONS lets a case add
|
|
||||||
# other targets that should answer too — without it there is no way to
|
|
||||||
# model "tmux still reports the session" for a non-holder agent, and the
|
|
||||||
# launcher's pane-pid-unresolved branch is unreachable from this harness.
|
|
||||||
#
|
|
||||||
# A listed target answers only AFTER new-session, because the launcher asks
|
|
||||||
# this question twice about the same name: once before launching, where a
|
|
||||||
# yes means "already running, nothing to do, exit 0", and once after, where
|
|
||||||
# a yes means "the session survived". A shim that answered yes to both
|
|
||||||
# would short-circuit at the first and never reach the branch under test —
|
|
||||||
# it would look like coverage and measure the idempotency path instead.
|
|
||||||
for argument in "${args[@]}"; do
|
for argument in "${args[@]}"; do
|
||||||
[ "$argument" = '=_holder:0.0' ] && exit 0
|
[ "$argument" = '=_holder:0.0' ] && exit 0
|
||||||
case " ${MOSAIC_TEST_HELD_SESSIONS:-} " in
|
|
||||||
*" $argument "*)
|
|
||||||
if tr '\0' '\n' < "${MOSAIC_TEST_TMUX_CALLS:?}" | grep -qxF new-session; then
|
|
||||||
exit 0
|
|
||||||
fi
|
|
||||||
;;
|
|
||||||
esac
|
|
||||||
done
|
done
|
||||||
exit 1
|
exit 1
|
||||||
;;
|
;;
|
||||||
@@ -80,30 +62,6 @@ env -0 > "${MOSAIC_HOME:?}/fleet/pane-environment"
|
|||||||
SHIM
|
SHIM
|
||||||
chmod +x "$FAKE_BIN/mosaic"
|
chmod +x "$FAKE_BIN/mosaic"
|
||||||
|
|
||||||
# The runtime the rosters below name. The launcher resolves it against PANE_PATH
|
|
||||||
# before spawning (#1241), so it has to exist somewhere the pane would find it —
|
|
||||||
# not merely on the launcher's own PATH.
|
|
||||||
printf '#!/usr/bin/env bash\nexit 0\n' > "$FAKE_BIN/pi"
|
|
||||||
chmod +x "$FAKE_BIN/pi"
|
|
||||||
|
|
||||||
# PANE_PATH is derived partly from `npm config get prefix`. Left to the real npm
|
|
||||||
# it would splice whatever the host has installed into the path under test, and
|
|
||||||
# the missing-binary cases below would pass or fail by accident of the machine.
|
|
||||||
cat > "$FAKE_BIN/npm" <<'SHIM'
|
|
||||||
#!/usr/bin/env bash
|
|
||||||
printf '%s\n' "${MOSAIC_TEST_NPM_PREFIX:-/nonexistent}"
|
|
||||||
SHIM
|
|
||||||
chmod +x "$FAKE_BIN/npm"
|
|
||||||
|
|
||||||
# PANE_PATH always ends in the system path. A host that installs these there can
|
|
||||||
# not measure the missing-binary cases at all, and a green run would mean
|
|
||||||
# nothing — so say so instead of passing.
|
|
||||||
for host_binary in mosaic pi; do
|
|
||||||
if PATH=/usr/local/bin:/usr/bin:/bin command -v "$host_binary" >/dev/null 2>&1; then
|
|
||||||
fail "host provides '$host_binary' in the system path; missing-binary cases are not measurable here"
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
|
|
||||||
write_generated() {
|
write_generated() {
|
||||||
local home="$1"
|
local home="$1"
|
||||||
local agent="$2"
|
local agent="$2"
|
||||||
@@ -123,19 +81,6 @@ MOSAIC_TMUX_SOCKET=mosaic-test
|
|||||||
EOF
|
EOF
|
||||||
chmod 600 "$home/fleet/agents/$agent.env.generated"
|
chmod 600 "$home/fleet/agents/$agent.env.generated"
|
||||||
mkdir -p "$home/work"
|
mkdir -p "$home/work"
|
||||||
install_pane_binaries "$home"
|
|
||||||
}
|
|
||||||
|
|
||||||
# `$PANE_HOME/.npm-global/bin` is one of the prefixes the launcher folds into
|
|
||||||
# PANE_PATH, so this is the pane's own view of "installed", distinct from the
|
|
||||||
# launcher's PATH. Tests that need a binary *absent* remove it from here.
|
|
||||||
install_pane_binaries() {
|
|
||||||
local pane_home="$1"
|
|
||||||
mkdir -p "$pane_home/.npm-global/bin"
|
|
||||||
local binary
|
|
||||||
for binary in mosaic pi; do
|
|
||||||
ln -sf "$FAKE_BIN/$binary" "$pane_home/.npm-global/bin/$binary"
|
|
||||||
done
|
|
||||||
}
|
}
|
||||||
|
|
||||||
run_start() {
|
run_start() {
|
||||||
@@ -143,7 +88,6 @@ run_start() {
|
|||||||
local agent="$2"
|
local agent="$2"
|
||||||
HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
||||||
MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
|
MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
|
||||||
MOSAIC_TEST_HELD_SESSIONS="${MOSAIC_TEST_HELD_SESSIONS:-}" \
|
|
||||||
MOSAIC_TEST_HOME="$home" \
|
MOSAIC_TEST_HOME="$home" \
|
||||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||||
MOSAIC_HOME="$home" "$START" "$agent"
|
MOSAIC_HOME="$home" "$START" "$agent"
|
||||||
@@ -154,10 +98,7 @@ run_start() {
|
|||||||
HOME_VALID="$ROOT/valid"
|
HOME_VALID="$ROOT/valid"
|
||||||
AGENT_VALID="coder0"
|
AGENT_VALID="coder0"
|
||||||
write_generated "$HOME_VALID" "$AGENT_VALID"
|
write_generated "$HOME_VALID" "$AGENT_VALID"
|
||||||
# A live pane PID is part of what "valid launch" means. Until #1241 this case
|
run_start "$HOME_VALID" "$AGENT_VALID"
|
||||||
# ran with none, so the suite's one success path was itself a dead pane the
|
|
||||||
# launcher reported as fine.
|
|
||||||
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_VALID" "$AGENT_VALID"
|
|
||||||
valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||||
echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
|
echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
|
||||||
echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
|
echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
|
||||||
@@ -304,13 +245,6 @@ PANE_BASH_ENV="$ROOT/pane-boundary.bash-env"
|
|||||||
printf 'MOSAIC_RUNTIME_BIN=%s\n' "$FAKE_BIN" > \
|
printf 'MOSAIC_RUNTIME_BIN=%s\n' "$FAKE_BIN" > \
|
||||||
"$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
|
"$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
|
||||||
chmod 600 "$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
|
chmod 600 "$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
|
||||||
# This case does not go through run_start, so its pane binaries come from
|
|
||||||
# MOSAIC_RUNTIME_BIN=$FAKE_BIN in the env.local written above — not from the
|
|
||||||
# symlinks install_pane_binaries planted under the generated home, which this
|
|
||||||
# launcher never consults because HOME here is the trusted parent. That is a
|
|
||||||
# legitimate resolution path, but it means dropping MOSAIC_RUNTIME_BIN from
|
|
||||||
# this case on the belief that the symlinks cover it would break the #1241
|
|
||||||
# binary check rather than exercise it.
|
|
||||||
LD_PRELOAD='/not/loaded/by-clean-bootstrap.so' \
|
LD_PRELOAD='/not/loaded/by-clean-bootstrap.so' \
|
||||||
BASH_ENV="$PANE_BASH_ENV" \
|
BASH_ENV="$PANE_BASH_ENV" \
|
||||||
MOSAIC_UNTRUSTED_SENTINEL='must-not-reach-pane' \
|
MOSAIC_UNTRUSTED_SENTINEL='must-not-reach-pane' \
|
||||||
@@ -324,7 +258,6 @@ PATH="$PANE_STALE_PATH" \
|
|||||||
"MOSAIC_TEST_HOME=$PANE_TRUSTED_HOME" \
|
"MOSAIC_TEST_HOME=$PANE_TRUSTED_HOME" \
|
||||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||||
MOSAIC_TEST_EXECUTE_PANE=1 \
|
MOSAIC_TEST_EXECUTE_PANE=1 \
|
||||||
"MOSAIC_TEST_PANE_PID=$$" \
|
|
||||||
"$START" coder-pane-boundary
|
"$START" coder-pane-boundary
|
||||||
pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||||
echo "$pane_args" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
echo "$pane_args" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
||||||
@@ -459,75 +392,6 @@ echo "$interaction_policy_args" | grep -qF 'new-session' && \
|
|||||||
echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
|
echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
|
||||||
fail "interaction pinned-policy check did not follow strict parsing"
|
fail "interaction pinned-policy check did not follow strict parsing"
|
||||||
|
|
||||||
# #1241. The pane runs `mosaic yolo <runtime>` against PANE_PATH. A binary
|
|
||||||
# missing from that path is a launch failure, and it has to be named before the
|
|
||||||
# session is created — after it, the diagnostic dies with the pane.
|
|
||||||
assert_missing_pane_binary_rejected() {
|
|
||||||
local binary="$1"
|
|
||||||
local home="$ROOT/missing-$binary"
|
|
||||||
local agent="coder-missing-$binary"
|
|
||||||
write_generated "$home" "$agent"
|
|
||||||
rm -f "$home/.npm-global/bin/$binary"
|
|
||||||
|
|
||||||
: > "$TMUX_CALLS"
|
|
||||||
local output
|
|
||||||
if output=$(MOSAIC_TEST_PANE_PID=$$ run_start "$home" "$agent" 2>&1); then
|
|
||||||
fail "launch succeeded with '$binary' absent from the pane PATH"
|
|
||||||
fi
|
|
||||||
echo "$output" | grep -qF 'code=missing-binary' || fail "missing '$binary' diagnostic missing"
|
|
||||||
echo "$output" | grep -qF "'$binary'" || fail "missing-binary diagnostic did not name $binary"
|
|
||||||
if tr '\0' '\n' < "$TMUX_CALLS" | grep -qF new-session; then
|
|
||||||
fail "launcher created a session it knew would die ($binary absent)"
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
assert_missing_pane_binary_rejected mosaic
|
|
||||||
assert_missing_pane_binary_rejected pi
|
|
||||||
|
|
||||||
# #1241. tmux destroys a session when its pane command exits, so no pane PID a
|
|
||||||
# second after new-session means the runtime died on startup. This used to be a
|
|
||||||
# WARNING about the heartbeat sidecar followed by exit 0 — three layers above it
|
|
||||||
# then reported a fleet that was not running.
|
|
||||||
: > "$TMUX_CALLS"
|
|
||||||
HOME_DEAD_PANE="$ROOT/dead-pane"
|
|
||||||
write_generated "$HOME_DEAD_PANE" "coder-dead-pane"
|
|
||||||
if output=$(MOSAIC_TEST_PANE_PID='' run_start "$HOME_DEAD_PANE" coder-dead-pane 2>&1); then
|
|
||||||
fail "launcher reported success over a pane that did not survive"
|
|
||||||
fi
|
|
||||||
echo "$output" | grep -qF 'code=pane-did-not-survive' || fail "dead-pane diagnostic missing"
|
|
||||||
if echo "$output" | grep -qiF 'heartbeat'; then
|
|
||||||
fail "dead pane is still being reported as a heartbeat-sidecar problem"
|
|
||||||
fi
|
|
||||||
tr '\0' '\n' < "$TMUX_CALLS" | grep -qF new-session || \
|
|
||||||
fail "dead-pane case did not reach the launch it is measuring"
|
|
||||||
|
|
||||||
# #1241, the other way a pane fails. Above, tmux destroyed the session and
|
|
||||||
# has-session said so. Here the session is still there and no PID comes back
|
|
||||||
# after the retries — a different fault (the pane is alive but unusable, or
|
|
||||||
# tmux is answering inconsistently) that an operator has to be told apart from
|
|
||||||
# a runtime that died on startup.
|
|
||||||
#
|
|
||||||
# This case exists because the branch that handles it shipped with nothing able
|
|
||||||
# to reach it: the shim answered has-session only for the holder, so every
|
|
||||||
# non-holder agent landed in the session-is-gone branch no matter what. A
|
|
||||||
# defensive branch nothing exercises is the same shape as the bug this whole
|
|
||||||
# change is about, one layer down.
|
|
||||||
: > "$TMUX_CALLS"
|
|
||||||
HOME_NO_PID="$ROOT/pane-no-pid"
|
|
||||||
write_generated "$HOME_NO_PID" "coder-no-pid"
|
|
||||||
if output=$(MOSAIC_TEST_PANE_PID='' MOSAIC_TEST_HELD_SESSIONS='=coder-no-pid:0.0' \
|
|
||||||
run_start "$HOME_NO_PID" coder-no-pid 2>&1); then
|
|
||||||
fail "launcher reported success over a session with no resolvable pane PID"
|
|
||||||
fi
|
|
||||||
echo "$output" | grep -qF 'code=pane-pid-unresolved' || \
|
|
||||||
fail "session-present/no-PID was not reported as pane-pid-unresolved: $output"
|
|
||||||
if echo "$output" | grep -qF 'code=pane-did-not-survive'; then
|
|
||||||
fail "a session tmux still reports was diagnosed as a destroyed session"
|
|
||||||
fi
|
|
||||||
if echo "$output" | grep -qiF 'heartbeat'; then
|
|
||||||
fail "an unresolvable pane PID is still being reported as a heartbeat-sidecar problem"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Exact stop derives the socket exclusively from the validated generated
|
# Exact stop derives the socket exclusively from the validated generated
|
||||||
# projection and ignores an ambient socket supplied by the caller.
|
# projection and ignores an ambient socket supplied by the caller.
|
||||||
: > "$TMUX_CALLS"
|
: > "$TMUX_CALLS"
|
||||||
|
|||||||
@@ -32,6 +32,10 @@ packages/mosaic/framework/tools/tmux/test-send-message-socket.sh | requires a re
|
|||||||
packages/mosaic/framework/tools/tmux/test-send-message-verdict.sh | requires real tmux-pane fixtures on a throwaway socket; CI image ships no tmux; #1017 burndown (same condition as its sibling)
|
packages/mosaic/framework/tools/tmux/test-send-message-verdict.sh | requires real tmux-pane fixtures on a throwaway socket; CI image ships no tmux; #1017 burndown (same condition as its sibling)
|
||||||
|
|
||||||
# --- single-suite directories: unmeasured in CI ---
|
# --- single-suite directories: unmeasured in CI ---
|
||||||
|
packages/mosaic/framework/tools/fleet/test-start-agent-session.sh | unmeasured in CI image; stubs tmux via a fake bin dir, likely CI-fit; #1017 burndown
|
||||||
|
packages/mosaic/framework/tools/glpi/test-list-http-status.sh | unmeasured in CI image; stub-based (#807 regression harness), likely CI-fit; #1017 burndown
|
||||||
|
packages/mosaic/framework/tools/orchestrator/test-board-roll.sh | unmeasured in CI image; file-fixture based, likely CI-fit; #1017 burndown
|
||||||
|
packages/mosaic/framework/tools/woodpecker/test-ci-wait-exit-matrix.sh | unmeasured in CI image; drives ci-wait.sh against a stub pipeline-status.sh, likely CI-fit; #1017 burndown
|
||||||
|
|
||||||
# --- naming-boundary files the strict test-*.sh prefix cannot even name ---
|
# --- naming-boundary files the strict test-*.sh prefix cannot even name ---
|
||||||
# (#1017: three independent censuses handled the microtest file three different
|
# (#1017: three independent censuses handled the microtest file three different
|
||||||
@@ -39,20 +43,3 @@ packages/mosaic/framework/tools/tmux/test-send-message-verdict.sh | requires rea
|
|||||||
# recorded judgement. These lines ARE that judgement, signed.)
|
# recorded judgement. These lines ARE that judgement, signed.)
|
||||||
packages/mosaic/framework/tools/orchestrator/smoke-test.sh | behavior smoke checks for coord continue/run workflows, run manually by orchestrator seats; unmeasured in CI; #1017 burndown
|
packages/mosaic/framework/tools/orchestrator/smoke-test.sh | behavior smoke checks for coord continue/run workflows, run manually by orchestrator seats; unmeasured in CI; #1017 burndown
|
||||||
packages/mosaic/framework/tools/wake/validate-973/microtest-wake-assert.sh | #973 instrument self-test, run as a precondition of the validate-973 evidence procedure rather than as a standing CI suite; #1017 burndown candidate
|
packages/mosaic/framework/tools/wake/validate-973/microtest-wake-assert.sh | #973 instrument self-test, run as a precondition of the validate-973 evidence procedure rather than as a standing CI suite; #1017 burndown candidate
|
||||||
|
|
||||||
# --- tools/fleet: precondition is unsatisfiable in the CI image (#1271) ---
|
|
||||||
# Signed by fred (sb-it-1-dt, 2026-08-16) at origin/next 476db12.
|
|
||||||
# This suite asserts the launcher's behaviour when `mosaic` and `pi` are MISSING.
|
|
||||||
# It shims fakes into $FAKE_BIN, but the constructed PANE_PATH always ends in the
|
|
||||||
# real system path, so on a host that installs those binaries the missing-binary
|
|
||||||
# cases cannot be measured at all. The suite's own guard (line 103) says so and
|
|
||||||
# fails rather than reporting a pass it cannot back. That guard is correct.
|
|
||||||
# The error was wiring the suite into CI: #1017 (c56483eb) enumerated it and
|
|
||||||
# dropped this exclusion, and the CI image provides `pi` in the system path, so
|
|
||||||
# it has failed on every pipeline since. Measured 2026-08-16 across pipelines
|
|
||||||
# 2444 (#1256), 2438 (#1240) and 2441 (#1017-quality): exactly one FAIL line in
|
|
||||||
# each full log, identical, this assertion; control `zzz-not-present-zzz` -> 0.
|
|
||||||
# Burn-down and the full measurement are tracked in #1271; unwired by PR #1270.
|
|
||||||
# Because test:framework-shell is one && chain and this sat at position 44 of 48,
|
|
||||||
# the four suites after it had not run at all since the merge.
|
|
||||||
packages/mosaic/framework/tools/fleet/test-start-agent-session.sh | precondition unsatisfiable in the CI image: asserts missing-binary behaviour, but PANE_PATH always ends in the system path and the image provides `pi` there; guard at line 103 fails by design rather than passing unmeasured. Burn down by controlling the tail of PANE_PATH inside the test. NOT by removing `pi` from the image: the CI image installs @earendil-works/[email protected] deliberately (measured in pipeline 2444's test-step log), and other suites depend on that pin. Burn-down tracked in #1271
|
|
||||||
|
|||||||
@@ -25,7 +25,7 @@
|
|||||||
"lint": "eslint src",
|
"lint": "eslint src",
|
||||||
"typecheck": "tsc --noEmit",
|
"typecheck": "tsc --noEmit",
|
||||||
"test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
|
"test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
|
||||||
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/promotion_binding_unittest.py && python3 src/lease-broker/promotion_trigger_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/receipt_observer_client_unittest.py && python3 src/lease-broker/invariant_r_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/_scripts/test-mosaic-init-rce.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh && bash framework/tools/glpi/test-list-http-status.sh && bash framework/tools/orchestrator/test-board-roll.sh && bash framework/tools/woodpecker/test-ci-wait-exit-matrix.sh && bash framework/tools/_scripts/test-fleet-transport-check.sh"
|
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/promotion_binding_unittest.py && python3 src/lease-broker/promotion_trigger_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/receipt_observer_client_unittest.py && python3 src/lease-broker/invariant_r_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/_scripts/test-mosaic-init-rce.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh"
|
||||||
},
|
},
|
||||||
"dependencies": {
|
"dependencies": {
|
||||||
"@mosaicstack/brain": "workspace:*",
|
"@mosaicstack/brain": "workspace:*",
|
||||||
|
|||||||
@@ -1,177 +0,0 @@
|
|||||||
import { lstat, mkdir, mkdtemp, readFile, rm, symlink, writeFile } from 'node:fs/promises';
|
|
||||||
import { tmpdir } from 'node:os';
|
|
||||||
import { join } from 'node:path';
|
|
||||||
import { afterEach, describe, expect, it } from 'vitest';
|
|
||||||
|
|
||||||
import { placeUnitFile, resolveLeaseBrokerSocketForPreflight } from './fleet.js';
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Unit-placement regression harness for #1292.
|
|
||||||
*
|
|
||||||
* The two measured defects this suite pins:
|
|
||||||
* 1. `systemctl enable <name>` does NOT rewrite an existing by-path
|
|
||||||
* wants-symlink — so placement must remove stale residue explicitly, and
|
|
||||||
* acceptance asserts on the RESULTING SYMLINK TARGET, never on the enable
|
|
||||||
* call's argument (asserting the call cannot see where the link ended up).
|
|
||||||
* 2. Node's copyFile FOLLOWS a by-path symlink at the destination and
|
|
||||||
* overwrites the SEED template. Acceptance asserts on the SEED's bytes
|
|
||||||
* AND mtime — unchanged — which is the only check that can redden for
|
|
||||||
* finding 2. The symlink-target assertion catches finding 1; these are
|
|
||||||
* different defects with different failure modes.
|
|
||||||
*
|
|
||||||
* Fixtures are entirely inside tmpdirs (source template, active systemd dir,
|
|
||||||
* wants dir) — no real host paths are touched by this suite.
|
|
||||||
*/
|
|
||||||
|
|
||||||
describe('placeUnitFile (#1292 unit placement)', () => {
|
|
||||||
const cleanup: string[] = [];
|
|
||||||
afterEach(async () => {
|
|
||||||
while (cleanup.length > 0) {
|
|
||||||
await rm(cleanup.pop()!, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
async function fixture() {
|
|
||||||
const root = await mkdtemp(join(tmpdir(), 'place-unit-'));
|
|
||||||
cleanup.push(root);
|
|
||||||
const seedDir = join(root, 'seed');
|
|
||||||
const activeDir = join(root, 'active');
|
|
||||||
await mkdir(seedDir, { recursive: true });
|
|
||||||
await mkdir(activeDir, { recursive: true });
|
|
||||||
const seedTemplate = join(seedDir, 'unit-under-test.service');
|
|
||||||
await writeFile(
|
|
||||||
seedTemplate,
|
|
||||||
'[Unit]\nDescription=seed template\n[Service]\nType=oneshot\nExecStart=/bin/true\n[Install]\nWantedBy=default.target\n',
|
|
||||||
);
|
|
||||||
const activeSource = join(root, 'active-source.service');
|
|
||||||
await writeFile(
|
|
||||||
activeSource,
|
|
||||||
'[Unit]\nDescription=active copy v2\n[Service]\nType=oneshot\nExecStart=/bin/true\n[Install]\nWantedBy=default.target\n',
|
|
||||||
);
|
|
||||||
return { root, seedDir, activeDir, seedTemplate, activeSource };
|
|
||||||
}
|
|
||||||
|
|
||||||
it('places a regular file on a clean host (negative control: no residue anywhere)', async () => {
|
|
||||||
const f = await fixture();
|
|
||||||
const result = await placeUnitFile(f.activeSource, f.activeDir, 'unit-under-test.service');
|
|
||||||
expect(result.unlinkedDestinationSymlink).toBe(false);
|
|
||||||
expect(result.removedStaleWantsSymlink).toBe(false);
|
|
||||||
const info = await lstat(join(f.activeDir, 'unit-under-test.service'));
|
|
||||||
expect(info.isSymbolicLink()).toBe(false);
|
|
||||||
expect(await readFile(join(f.activeDir, 'unit-under-test.service'), 'utf8')).toContain(
|
|
||||||
'active copy v2',
|
|
||||||
);
|
|
||||||
// Seed untouched by construction — but assert it, so the clean-host case
|
|
||||||
// cannot silently regress into seed-mutation.
|
|
||||||
expect(await readFile(f.seedTemplate, 'utf8')).toContain('seed template');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('by-path residue: unlinks destination symlink, places the file, seed bytes AND mtime unchanged (finding 2)', async () => {
|
|
||||||
const f = await fixture();
|
|
||||||
const seedBefore = await readFile(f.seedTemplate, 'utf8');
|
|
||||||
const mtimeBefore = (await lstat(f.seedTemplate)).mtimeMs;
|
|
||||||
// The fomo-lin convention: by-path enable left a symlink AT the unit name
|
|
||||||
// pointing at the seed template, plus a wants-symlink doing the same.
|
|
||||||
await symlink(f.seedTemplate, join(f.activeDir, 'unit-under-test.service'));
|
|
||||||
const wantsDir = join(f.activeDir, 'default.target.wants');
|
|
||||||
await mkdir(wantsDir, { recursive: true });
|
|
||||||
await symlink(f.seedTemplate, join(wantsDir, 'unit-under-test.service'));
|
|
||||||
|
|
||||||
const result = await placeUnitFile(f.activeSource, f.activeDir, 'unit-under-test.service');
|
|
||||||
expect(result.unlinkedDestinationSymlink).toBe(true);
|
|
||||||
expect(result.removedStaleWantsSymlink).toBe(true);
|
|
||||||
|
|
||||||
// FINDING 2's check: the seed is byte-identical and its mtime did not move.
|
|
||||||
expect(await readFile(f.seedTemplate, 'utf8')).toBe(seedBefore);
|
|
||||||
expect((await lstat(f.seedTemplate)).mtimeMs).toBe(mtimeBefore);
|
|
||||||
|
|
||||||
// The destination is now a regular file carrying the ACTIVE content.
|
|
||||||
const destInfo = await lstat(join(f.activeDir, 'unit-under-test.service'));
|
|
||||||
expect(destInfo.isSymbolicLink()).toBe(false);
|
|
||||||
expect(await readFile(join(f.activeDir, 'unit-under-test.service'), 'utf8')).toContain(
|
|
||||||
'active copy v2',
|
|
||||||
);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('by-path residue: no wants-symlink remains pointing at the seed (finding 1 residue cleared)', async () => {
|
|
||||||
const f = await fixture();
|
|
||||||
await symlink(f.seedTemplate, join(f.activeDir, 'unit-under-test.service'));
|
|
||||||
const wantsDir = join(f.activeDir, 'default.target.wants');
|
|
||||||
await mkdir(wantsDir, { recursive: true });
|
|
||||||
await symlink(f.seedTemplate, join(wantsDir, 'unit-under-test.service'));
|
|
||||||
|
|
||||||
await placeUnitFile(f.activeSource, f.activeDir, 'unit-under-test.service');
|
|
||||||
|
|
||||||
// After placement the stale wants link is GONE (enable-by-name recreates
|
|
||||||
// it correctly). A link still present must not point at the seed.
|
|
||||||
try {
|
|
||||||
const link = await lstat(join(wantsDir, 'unit-under-test.service'));
|
|
||||||
if (link.isSymbolicLink()) {
|
|
||||||
const target = await readFile(join(wantsDir, 'unit-under-test.service'), 'utf8').catch(
|
|
||||||
async () => '',
|
|
||||||
);
|
|
||||||
expect(target).not.toContain('seed template');
|
|
||||||
}
|
|
||||||
} catch {
|
|
||||||
// absent wants link — the expected post-placement state
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('idempotence: second placement on a reconciled host is a no-op producing the identical final state', async () => {
|
|
||||||
const f = await fixture();
|
|
||||||
// Reconciled starting state: regular file at the name, wants link to the active copy.
|
|
||||||
await writeFile(
|
|
||||||
join(f.activeDir, 'unit-under-test.service'),
|
|
||||||
await readFile(f.activeSource, 'utf8'),
|
|
||||||
);
|
|
||||||
const wantsDir = join(f.activeDir, 'default.target.wants');
|
|
||||||
await mkdir(wantsDir, { recursive: true });
|
|
||||||
await symlink(
|
|
||||||
join(f.activeDir, 'unit-under-test.service'),
|
|
||||||
join(wantsDir, 'unit-under-test.service'),
|
|
||||||
);
|
|
||||||
const before = await readFile(join(f.activeDir, 'unit-under-test.service'), 'utf8');
|
|
||||||
|
|
||||||
const result = await placeUnitFile(f.activeSource, f.activeDir, 'unit-under-test.service');
|
|
||||||
// No destructive step fired: no unlink, no wants removal.
|
|
||||||
expect(result.unlinkedDestinationSymlink).toBe(false);
|
|
||||||
expect(result.removedStaleWantsSymlink).toBe(false);
|
|
||||||
// Identical final state.
|
|
||||||
expect(await readFile(join(f.activeDir, 'unit-under-test.service'), 'utf8')).toBe(before);
|
|
||||||
const link = await lstat(join(wantsDir, 'unit-under-test.service'));
|
|
||||||
expect(link.isSymbolicLink()).toBe(true);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('double install on by-path residue converges to the identical reconciled state', async () => {
|
|
||||||
const f = await fixture();
|
|
||||||
await symlink(f.seedTemplate, join(f.activeDir, 'unit-under-test.service'));
|
|
||||||
const wantsDir = join(f.activeDir, 'default.target.wants');
|
|
||||||
await mkdir(wantsDir, { recursive: true });
|
|
||||||
await symlink(f.seedTemplate, join(wantsDir, 'unit-under-test.service'));
|
|
||||||
|
|
||||||
await placeUnitFile(f.activeSource, f.activeDir, 'unit-under-test.service');
|
|
||||||
const first = await readFile(join(f.activeDir, 'unit-under-test.service'), 'utf8');
|
|
||||||
const secondRun = await placeUnitFile(f.activeSource, f.activeDir, 'unit-under-test.service');
|
|
||||||
const second = await readFile(join(f.activeDir, 'unit-under-test.service'), 'utf8');
|
|
||||||
expect(secondRun.unlinkedDestinationSymlink).toBe(false);
|
|
||||||
expect(second).toBe(first);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('resolveLeaseBrokerSocketForPreflight (#1292 preflight resolution)', () => {
|
|
||||||
it('explicit MOSAIC_LEASE_BROKER_SOCKET wins', () => {
|
|
||||||
expect(
|
|
||||||
resolveLeaseBrokerSocketForPreflight({ MOSAIC_LEASE_BROKER_SOCKET: '/custom/sock' }, 1000),
|
|
||||||
).toBe('/custom/sock');
|
|
||||||
});
|
|
||||||
it('XDG_RUNTIME_DIR next', () => {
|
|
||||||
expect(resolveLeaseBrokerSocketForPreflight({ XDG_RUNTIME_DIR: '/run/user/1001' }, 1000)).toBe(
|
|
||||||
'/run/user/1001/mosaic-lease/broker.sock',
|
|
||||||
);
|
|
||||||
});
|
|
||||||
it('falls back to /run/user/<uid>', () => {
|
|
||||||
expect(resolveLeaseBrokerSocketForPreflight({}, 1002)).toBe(
|
|
||||||
'/run/user/1002/mosaic-lease/broker.sock',
|
|
||||||
);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
@@ -1,323 +0,0 @@
|
|||||||
import { execFile } from 'node:child_process';
|
|
||||||
import { mkdir, mkdtemp, readFile, readdir, rm, stat, writeFile } from 'node:fs/promises';
|
|
||||||
import { tmpdir } from 'node:os';
|
|
||||||
import { join, resolve } from 'node:path';
|
|
||||||
import { Command } from 'commander';
|
|
||||||
import { afterEach, describe, expect, it, vi } from 'vitest';
|
|
||||||
import { registerFleetCommand, type CommandResult, type CommandRunner } from './fleet.js';
|
|
||||||
|
|
||||||
/**
|
|
||||||
* #1237: the v1-only commands (`ps`, `install`, `install-systemd`, `add`,
|
|
||||||
* `remove`) rejected a roster-v2 fleet outright, so a greenfield v2 box could
|
|
||||||
* never get its units placed. These tests pin the three behaviours that fix
|
|
||||||
* gives it, and the two it deliberately does NOT give it.
|
|
||||||
*
|
|
||||||
* The load-bearing negative is that `install` on v2 writes no generated env:
|
|
||||||
* the reconciler owns that file through projectRosterV2AgentGeneratedEnv, and a
|
|
||||||
* second writer here — necessarily through the v1 mapping — is exactly the
|
|
||||||
* drift the #791 single-SSOT invariant exists to prevent.
|
|
||||||
*/
|
|
||||||
|
|
||||||
const rosterV2 = `
|
|
||||||
version: 2
|
|
||||||
generation: 4
|
|
||||||
transport: tmux
|
|
||||||
tmux:
|
|
||||||
socket_name: mosaic-fleet
|
|
||||||
holder_session: _holder
|
|
||||||
defaults:
|
|
||||||
working_directory: /srv/mosaic
|
|
||||||
runtime: pi
|
|
||||||
runtimes:
|
|
||||||
pi:
|
|
||||||
reset_command: /new
|
|
||||||
agents:
|
|
||||||
- name: coder0
|
|
||||||
alias: Coder 0
|
|
||||||
class: code
|
|
||||||
runtime: pi
|
|
||||||
provider: openai
|
|
||||||
model: gpt-5.6-sol
|
|
||||||
reasoning: high
|
|
||||||
tool_policy: code
|
|
||||||
working_directory: /srv/mosaic
|
|
||||||
persistent_persona: false
|
|
||||||
reset_between_tasks: true
|
|
||||||
lifecycle:
|
|
||||||
enabled: true
|
|
||||||
desired_state: stopped
|
|
||||||
launch:
|
|
||||||
yolo: true
|
|
||||||
- name: coder1
|
|
||||||
alias: Coder 1
|
|
||||||
class: code
|
|
||||||
runtime: pi
|
|
||||||
provider: openai
|
|
||||||
model: gpt-5.6-sol
|
|
||||||
reasoning: medium
|
|
||||||
tool_policy: code
|
|
||||||
working_directory: /srv/other
|
|
||||||
persistent_persona: false
|
|
||||||
reset_between_tasks: true
|
|
||||||
lifecycle:
|
|
||||||
enabled: true
|
|
||||||
desired_state: stopped
|
|
||||||
launch:
|
|
||||||
yolo: true
|
|
||||||
`;
|
|
||||||
|
|
||||||
let tempHome: string | undefined;
|
|
||||||
const savedHome = process.env.HOME;
|
|
||||||
const savedMosaicHome = process.env.MOSAIC_HOME;
|
|
||||||
|
|
||||||
afterEach(async (): Promise<void> => {
|
|
||||||
vi.restoreAllMocks();
|
|
||||||
process.exitCode = undefined;
|
|
||||||
if (savedHome === undefined) delete process.env.HOME;
|
|
||||||
else process.env.HOME = savedHome;
|
|
||||||
if (savedMosaicHome === undefined) delete process.env.MOSAIC_HOME;
|
|
||||||
else process.env.MOSAIC_HOME = savedMosaicHome;
|
|
||||||
if (tempHome) await rm(tempHome, { recursive: true, force: true });
|
|
||||||
tempHome = undefined;
|
|
||||||
});
|
|
||||||
|
|
||||||
/**
|
|
||||||
* A HOME with a roster-v2 fleet and nothing else — the greenfield shape, before
|
|
||||||
* anything has been installed, applied or started.
|
|
||||||
*/
|
|
||||||
async function v2Home(): Promise<string> {
|
|
||||||
tempHome = await mkdtemp(join(tmpdir(), 'mosaic-fleet-v2-dispatch-'));
|
|
||||||
process.env.HOME = tempHome;
|
|
||||||
delete process.env.MOSAIC_HOME;
|
|
||||||
const mosaicHome = join(tempHome, '.config', 'mosaic');
|
|
||||||
for (const directory of ['fleet', 'fleet/agents', 'fleet/roles']) {
|
|
||||||
await mkdir(join(mosaicHome, directory), { recursive: true, mode: 0o700 });
|
|
||||||
}
|
|
||||||
await writeFile(join(mosaicHome, 'fleet', 'roster.yaml'), rosterV2, { mode: 0o600 });
|
|
||||||
await writeFile(join(mosaicHome, 'fleet', 'roles', 'code.md'), '`class: code`\n\n# code\n', {
|
|
||||||
mode: 0o600,
|
|
||||||
});
|
|
||||||
return mosaicHome;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Stands in for a box where nothing is running: every systemctl and tmux probe
|
|
||||||
* fails the way it does before the holder has ever started. `ps` must survive
|
|
||||||
* this — it is the command an operator reaches for to find out *why* there is
|
|
||||||
* no seat, so it has to report the emptiness rather than fail on it.
|
|
||||||
*/
|
|
||||||
const greenfieldRunner: CommandRunner = async (command): Promise<CommandResult> => {
|
|
||||||
if (command === 'tmux') {
|
|
||||||
return { stdout: '', stderr: 'no server running on /tmp/tmux-1000/mosaic-fleet', exitCode: 1 };
|
|
||||||
}
|
|
||||||
return { stdout: '', stderr: '', exitCode: 1 };
|
|
||||||
};
|
|
||||||
|
|
||||||
function program(runner: CommandRunner = greenfieldRunner): Command {
|
|
||||||
const result = new Command();
|
|
||||||
result.exitOverride();
|
|
||||||
registerFleetCommand(result, { runner, frameworkRoot: resolve(process.cwd(), 'framework') });
|
|
||||||
return result;
|
|
||||||
}
|
|
||||||
|
|
||||||
function capture(): string[] {
|
|
||||||
const lines: string[] = [];
|
|
||||||
vi.spyOn(console, 'log').mockImplementation((value: string): void => {
|
|
||||||
lines.push(value);
|
|
||||||
});
|
|
||||||
return lines;
|
|
||||||
}
|
|
||||||
|
|
||||||
async function exists(path: string): Promise<boolean> {
|
|
||||||
try {
|
|
||||||
await stat(path);
|
|
||||||
return true;
|
|
||||||
} catch {
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
describe('mosaic fleet ps — roster v2', (): void => {
|
|
||||||
it('lists every v2 agent on a greenfield box with nothing running, and does not throw', async (): Promise<void> => {
|
|
||||||
await v2Home();
|
|
||||||
const lines = capture();
|
|
||||||
|
|
||||||
await expect(
|
|
||||||
program().parseAsync(['node', 'mosaic', 'fleet', 'ps', '--json']),
|
|
||||||
).resolves.toBeDefined();
|
|
||||||
|
|
||||||
const rows = JSON.parse(lines.join('\n')) as {
|
|
||||||
name: string;
|
|
||||||
runtime: string;
|
|
||||||
alias?: string;
|
|
||||||
paneAlive: boolean;
|
|
||||||
source: string;
|
|
||||||
}[];
|
|
||||||
expect(rows.map((row) => row.name).sort()).toEqual(['coder0', 'coder1']);
|
|
||||||
// The v2 roster's per-agent fields must survive the read model, not be
|
|
||||||
// flattened into defaults.
|
|
||||||
expect(rows.every((row) => row.runtime === 'pi')).toBe(true);
|
|
||||||
expect(rows.find((row) => row.name === 'coder0')?.alias).toBe('Coder 0');
|
|
||||||
// Nothing is running, and that is a report, not an error.
|
|
||||||
expect(rows.every((row) => row.paneAlive === false)).toBe(true);
|
|
||||||
expect(rows.every((row) => row.source === 'roster')).toBe(true);
|
|
||||||
expect(process.exitCode ?? 0).toBe(0);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('mosaic fleet install — roster v2', (): void => {
|
|
||||||
it('places the tool files and unit templates', async (): Promise<void> => {
|
|
||||||
const mosaicHome = await v2Home();
|
|
||||||
capture();
|
|
||||||
|
|
||||||
await expect(
|
|
||||||
program().parseAsync(['node', 'mosaic', 'fleet', 'install', '--no-enable']),
|
|
||||||
).resolves.toBeDefined();
|
|
||||||
|
|
||||||
// Units live in the systemd user dir, not under the Mosaic home.
|
|
||||||
const systemdUserDir = join(tempHome!, '.config', 'systemd', 'user');
|
|
||||||
for (const unit of [
|
|
||||||
'mosaic-tmux-holder.service',
|
|
||||||
'[email protected]',
|
|
||||||
'[email protected]',
|
|
||||||
]) {
|
|
||||||
expect(await exists(join(systemdUserDir, unit))).toBe(true);
|
|
||||||
}
|
|
||||||
const launcher = join(mosaicHome, 'tools', 'fleet', 'start-agent-session.sh');
|
|
||||||
expect(await exists(launcher)).toBe(true);
|
|
||||||
expect((await stat(launcher)).mode & 0o777).toBe(0o755);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('writes NO generated env — that file belongs to the reconciler (#791)', async (): Promise<void> => {
|
|
||||||
const mosaicHome = await v2Home();
|
|
||||||
capture();
|
|
||||||
|
|
||||||
await program().parseAsync(['node', 'mosaic', 'fleet', 'install', '--no-enable']);
|
|
||||||
|
|
||||||
const agentDir = join(mosaicHome, 'fleet', 'agents');
|
|
||||||
expect(await readdir(agentDir)).toEqual([]);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('tells the operator which command does own the env', async (): Promise<void> => {
|
|
||||||
await v2Home();
|
|
||||||
const lines = capture();
|
|
||||||
|
|
||||||
await program().parseAsync(['node', 'mosaic', 'fleet', 'install', '--no-enable']);
|
|
||||||
|
|
||||||
expect(lines.join('\n')).toContain('mosaic fleet apply');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('[email protected]', (): void => {
|
|
||||||
const unitPath = resolve(process.cwd(), 'framework', 'systemd', 'user', '[email protected]');
|
|
||||||
|
|
||||||
/** The single `ConditionPathExists=` value declared by the unit template. */
|
|
||||||
async function conditionPath(): Promise<string> {
|
|
||||||
const unit = await readFile(unitPath, 'utf8');
|
|
||||||
const matches = unit.match(/^ConditionPathExists=(.+)$/gm) ?? [];
|
|
||||||
expect(matches).toHaveLength(1);
|
|
||||||
return matches[0]!.slice('ConditionPathExists='.length).trim();
|
|
||||||
}
|
|
||||||
|
|
||||||
it('will not attempt a seat before the reconciler has written its env', async (): Promise<void> => {
|
|
||||||
// The pairing that makes "install writes no env" safe: install enables the
|
|
||||||
// unit (WantedBy=default.target) but does not start it, so without this
|
|
||||||
// condition a reboot between `install` and the first `apply` would run
|
|
||||||
// ExecStart against an absent env file and fail every seat unit.
|
|
||||||
expect(await conditionPath()).toBe('%h/.config/mosaic/fleet/agents/%i.env.generated');
|
|
||||||
});
|
|
||||||
|
|
||||||
/**
|
|
||||||
* The two halves of the guard's *effect*, which no assertion on the literal
|
|
||||||
* string can cover on its own.
|
|
||||||
*
|
|
||||||
* Measured end to end on a real box (canary, 2026-08-16) rather than inferred:
|
|
||||||
* with the condition, `systemctl --user start mosaic-agent@<name>` on an agent
|
|
||||||
* with no generated env returns rc=0, `Result=success`, `ConditionResult=no`,
|
|
||||||
* and journals "skipped, unmet condition check". With the condition removed by
|
|
||||||
* drop-in and nothing else changed, the same start returns rc=1,
|
|
||||||
* `Result=exit-code`, `ExecMainStatus=64`, and the unit enters `failed`.
|
|
||||||
*
|
|
||||||
* systemd is not available in this suite, so these two tests pin the parts
|
|
||||||
* that can drift in code: the condition naming a *different* file than the one
|
|
||||||
* the fleet actually writes, and the launcher quietly becoming tolerant of an
|
|
||||||
* absent env — either of which turns the condition into decoration while the
|
|
||||||
* literal-string assertion above still passes.
|
|
||||||
*/
|
|
||||||
it('guards exactly the file the fleet writes, so the two cannot drift apart', async (): Promise<void> => {
|
|
||||||
const mosaicHome = await v2Home();
|
|
||||||
const rendered = (await conditionPath()).replace('%h', tempHome!).replace('%i', 'coder0');
|
|
||||||
|
|
||||||
// The path an installed fleet actually places for this agent.
|
|
||||||
expect(rendered).toBe(join(mosaicHome, 'fleet', 'agents', 'coder0.env.generated'));
|
|
||||||
});
|
|
||||||
|
|
||||||
it('guards a real failure — the launcher rejects an absent generated env', async (): Promise<void> => {
|
|
||||||
await v2Home();
|
|
||||||
await program().parseAsync(['node', 'mosaic', 'fleet', 'install', '--no-enable']);
|
|
||||||
|
|
||||||
// Exactly what ExecStart runs, against the state the condition exists to
|
|
||||||
// catch: unit enabled, reconciler has not written env yet.
|
|
||||||
const launched = await new Promise<{ code: number | null; stderr: string }>((settle) => {
|
|
||||||
const child = execFile(
|
|
||||||
'/bin/bash',
|
|
||||||
[
|
|
||||||
'--noprofile',
|
|
||||||
'--norc',
|
|
||||||
join(tempHome!, '.config', 'mosaic', 'tools', 'fleet', 'start-agent-session.sh'),
|
|
||||||
'coder0',
|
|
||||||
],
|
|
||||||
{ env: { HOME: tempHome!, MOSAIC_AGENT_NAME: 'coder0', PATH: '/usr/bin:/bin' } },
|
|
||||||
(_error, _stdout, stderr) => {
|
|
||||||
settle({ code: child.exitCode, stderr });
|
|
||||||
},
|
|
||||||
);
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(launched.code).not.toBe(0);
|
|
||||||
expect(launched.stderr).toContain('missing-file');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('mosaic fleet add / remove — roster v2', (): void => {
|
|
||||||
it('add refuses, and names the two-step v2 sequence instead of inventing defaults', async (): Promise<void> => {
|
|
||||||
await v2Home();
|
|
||||||
|
|
||||||
await expect(
|
|
||||||
program().parseAsync([
|
|
||||||
'node',
|
|
||||||
'mosaic',
|
|
||||||
'fleet',
|
|
||||||
'add',
|
|
||||||
'coder2',
|
|
||||||
'--runtime',
|
|
||||||
'pi',
|
|
||||||
'--class',
|
|
||||||
'code',
|
|
||||||
]),
|
|
||||||
).rejects.toThrow(/mosaic fleet create[\s\S]*mosaic fleet apply/);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('remove refuses, and names delete plus apply', async (): Promise<void> => {
|
|
||||||
await v2Home();
|
|
||||||
|
|
||||||
await expect(
|
|
||||||
program().parseAsync(['node', 'mosaic', 'fleet', 'remove', 'coder1']),
|
|
||||||
).rejects.toThrow(/mosaic fleet delete coder1[\s\S]*mosaic fleet apply/);
|
|
||||||
});
|
|
||||||
|
|
||||||
// Note: this one passes on the unmodified tree too — there `remove` throws in
|
|
||||||
// the v1 parser, before it can touch anything. It is a regression guard on the
|
|
||||||
// ordering of the new guard clause, not evidence that the fix works.
|
|
||||||
it('refuses BEFORE mutating the roster', async (): Promise<void> => {
|
|
||||||
const mosaicHome = await v2Home();
|
|
||||||
const rosterPath = join(mosaicHome, 'fleet', 'roster.yaml');
|
|
||||||
const before = await readFile(rosterPath, 'utf8');
|
|
||||||
|
|
||||||
await expect(
|
|
||||||
program().parseAsync(['node', 'mosaic', 'fleet', 'remove', 'coder1']),
|
|
||||||
).rejects.toThrow();
|
|
||||||
|
|
||||||
expect(await readFile(rosterPath, 'utf8')).toBe(before);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
@@ -835,25 +835,13 @@ describe('fleet command construction', () => {
|
|||||||
};
|
};
|
||||||
const program = new Command();
|
const program = new Command();
|
||||||
program.exitOverride();
|
program.exitOverride();
|
||||||
// #1292: inject a present broker socket so the preflight passes and this
|
registerFleetCommand(program, { runner, mosaicHome: home });
|
||||||
// spec keeps testing its ORIGINAL property (holder-before-agent ordering).
|
|
||||||
// The preflight's own refusal behavior has dedicated specs below.
|
|
||||||
registerFleetCommand(program, {
|
|
||||||
runner,
|
|
||||||
mosaicHome: home,
|
|
||||||
checkBrokerSocket: async () => true,
|
|
||||||
});
|
|
||||||
|
|
||||||
try {
|
try {
|
||||||
await program.parseAsync(['node', 'mosaic', 'fleet', 'start']);
|
await program.parseAsync(['node', 'mosaic', 'fleet', 'start']);
|
||||||
await program.parseAsync(['node', 'mosaic', 'fleet', 'stop']);
|
await program.parseAsync(['node', 'mosaic', 'fleet', 'stop']);
|
||||||
|
|
||||||
expect(calls).toEqual([
|
expect(calls).toEqual([
|
||||||
// #1292: fleet start enables + starts the broker FIRST (enable is
|
|
||||||
// idempotent; the unit exists after install), re-checking the socket
|
|
||||||
// before any holder/agent lifecycle effect.
|
|
||||||
['systemctl', '--user', 'enable', 'mosaic-lease-broker.service'],
|
|
||||||
['systemctl', '--user', 'start', 'mosaic-lease-broker.service'],
|
|
||||||
['systemctl', '--user', 'start', 'mosaic-tmux-holder.service'],
|
['systemctl', '--user', 'start', 'mosaic-tmux-holder.service'],
|
||||||
['systemctl', '--user', 'start', '[email protected]'],
|
['systemctl', '--user', 'start', '[email protected]'],
|
||||||
['systemctl', '--user', 'stop', '[email protected]'],
|
['systemctl', '--user', 'stop', '[email protected]'],
|
||||||
@@ -864,92 +852,6 @@ describe('fleet command construction', () => {
|
|||||||
}
|
}
|
||||||
});
|
});
|
||||||
|
|
||||||
it('fleet start refuses with a named error when the broker socket does not appear (#1292)', async () => {
|
|
||||||
const home = await tempDir();
|
|
||||||
const rosterPath = join(home, 'fleet', 'roster.yaml');
|
|
||||||
await mkdir(join(home, 'fleet'), { recursive: true });
|
|
||||||
await writeFile(
|
|
||||||
rosterPath,
|
|
||||||
['version: 1', 'transport: tmux', 'agents:', ' - name: coder0', ' runtime: codex'].join(
|
|
||||||
'\n',
|
|
||||||
),
|
|
||||||
);
|
|
||||||
const calls: string[][] = [];
|
|
||||||
const runner: CommandRunner = async (command, args) => {
|
|
||||||
calls.push([command, ...args]);
|
|
||||||
return { stdout: '', stderr: '', exitCode: 0 };
|
|
||||||
};
|
|
||||||
const program = new Command();
|
|
||||||
program.exitOverride();
|
|
||||||
const errors: string[] = [];
|
|
||||||
const origError = console.error;
|
|
||||||
console.error = (...args: unknown[]) => {
|
|
||||||
errors.push(args.join(' '));
|
|
||||||
};
|
|
||||||
registerFleetCommand(program, {
|
|
||||||
runner,
|
|
||||||
mosaicHome: home,
|
|
||||||
checkBrokerSocket: async () => false,
|
|
||||||
});
|
|
||||||
try {
|
|
||||||
await program.parseAsync(['node', 'mosaic', 'fleet', 'start']);
|
|
||||||
// Refused: no holder/agent starts were issued after the broker attempt.
|
|
||||||
expect(calls).toEqual([
|
|
||||||
['systemctl', '--user', 'enable', 'mosaic-lease-broker.service'],
|
|
||||||
['systemctl', '--user', 'start', 'mosaic-lease-broker.service'],
|
|
||||||
]);
|
|
||||||
expect(errors.join('\n')).toContain('broker-absent');
|
|
||||||
expect(errors.join('\n')).toContain('mosaic fleet install');
|
|
||||||
} finally {
|
|
||||||
console.error = origError;
|
|
||||||
await rm(home, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('fleet start re-probes the broker on the SECOND invocation — no ActiveState trust (#1292 sticky half)', async () => {
|
|
||||||
const home = await tempDir();
|
|
||||||
const rosterPath = join(home, 'fleet', 'roster.yaml');
|
|
||||||
await mkdir(join(home, 'fleet'), { recursive: true });
|
|
||||||
await writeFile(
|
|
||||||
rosterPath,
|
|
||||||
['version: 1', 'transport: tmux', 'agents:', ' - name: coder0', ' runtime: codex'].join(
|
|
||||||
'\n',
|
|
||||||
),
|
|
||||||
);
|
|
||||||
const calls: string[][] = [];
|
|
||||||
const runner: CommandRunner = async (command, args) => {
|
|
||||||
calls.push([command, ...args]);
|
|
||||||
return { stdout: '', stderr: '', exitCode: 0 };
|
|
||||||
};
|
|
||||||
const program = new Command();
|
|
||||||
program.exitOverride();
|
|
||||||
// Broker socket NEVER appears — the second start must refuse exactly like
|
|
||||||
// the first; RemainAfterExit-style stale unit state changes nothing
|
|
||||||
// because the check is the socket, not systemctl.
|
|
||||||
registerFleetCommand(program, {
|
|
||||||
runner,
|
|
||||||
mosaicHome: home,
|
|
||||||
checkBrokerSocket: async () => false,
|
|
||||||
});
|
|
||||||
const errors: string[] = [];
|
|
||||||
const origError = console.error;
|
|
||||||
console.error = (...args: unknown[]) => {
|
|
||||||
errors.push(args.join(' '));
|
|
||||||
};
|
|
||||||
try {
|
|
||||||
await program.parseAsync(['node', 'mosaic', 'fleet', 'start']);
|
|
||||||
await program.parseAsync(['node', 'mosaic', 'fleet', 'start']);
|
|
||||||
// Two invocations, each refusing after its own broker attempt:
|
|
||||||
expect(
|
|
||||||
calls.filter((c) => c.join(' ') === 'systemctl --user start [email protected]'),
|
|
||||||
).toHaveLength(0);
|
|
||||||
expect(errors.filter((e) => e.includes('broker-absent')).length).toBeGreaterThanOrEqual(2);
|
|
||||||
} finally {
|
|
||||||
console.error = origError;
|
|
||||||
await rm(home, { recursive: true, force: true });
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('waits for an in-flight restart to clear before relaunching (re-entry guard)', async () => {
|
it('waits for an in-flight restart to clear before relaunching (re-entry guard)', async () => {
|
||||||
const home = await tempDir();
|
const home = await tempDir();
|
||||||
const rosterPath = join(home, 'fleet', 'roster.yaml');
|
const rosterPath = join(home, 'fleet', 'roster.yaml');
|
||||||
@@ -2163,19 +2065,8 @@ describe('fleet install — auto-enable units for boot-survival', () => {
|
|||||||
|
|
||||||
await enableFleetUnits(runner, minimalRoster, {});
|
await enableFleetUnits(runner, minimalRoster, {});
|
||||||
|
|
||||||
expect(calls).toContainEqual(['systemctl', '--user', 'enable', 'mosaic-lease-broker.service']);
|
|
||||||
expect(calls).toContainEqual(['systemctl', '--user', 'enable', 'mosaic-tmux-holder.service']);
|
expect(calls).toContainEqual(['systemctl', '--user', 'enable', 'mosaic-tmux-holder.service']);
|
||||||
expect(calls).toContainEqual(['systemctl', '--user', 'enable', '[email protected]']);
|
expect(calls).toContainEqual(['systemctl', '--user', 'enable', '[email protected]']);
|
||||||
// The broker must be enabled BEFORE the holder and agents: a start of any
|
|
||||||
// gated runtime without the broker is exactly the #1292 4-second death.
|
|
||||||
const brokerIndex = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user enable mosaic-lease-broker.service',
|
|
||||||
);
|
|
||||||
const holderIndex = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user enable mosaic-tmux-holder.service',
|
|
||||||
);
|
|
||||||
expect(brokerIndex).toBeGreaterThanOrEqual(0);
|
|
||||||
expect(brokerIndex).toBeLessThan(holderIndex);
|
|
||||||
});
|
});
|
||||||
|
|
||||||
it('install still succeeds when systemctl enable returns non-zero (non-fatal)', async () => {
|
it('install still succeeds when systemctl enable returns non-zero (non-fatal)', async () => {
|
||||||
|
|||||||
@@ -3,11 +3,9 @@ import {
|
|||||||
access,
|
access,
|
||||||
chmod,
|
chmod,
|
||||||
copyFile,
|
copyFile,
|
||||||
lstat,
|
|
||||||
mkdir,
|
mkdir,
|
||||||
open,
|
open,
|
||||||
readFile,
|
readFile,
|
||||||
readlink,
|
|
||||||
stat,
|
stat,
|
||||||
unlink,
|
unlink,
|
||||||
writeFile,
|
writeFile,
|
||||||
@@ -36,7 +34,6 @@ export {
|
|||||||
resolveInstalledFleetRosterPath,
|
resolveInstalledFleetRosterPath,
|
||||||
} from '../fleet/fleet-roster-v1.js';
|
} from '../fleet/fleet-roster-v1.js';
|
||||||
export type { FleetAgent, FleetRoster } from '../fleet/fleet-roster-v1.js';
|
export type { FleetAgent, FleetRoster } from '../fleet/fleet-roster-v1.js';
|
||||||
import { parseRosterV2 } from '../fleet/roster-v2.js';
|
|
||||||
import {
|
import {
|
||||||
registerFleetAgentCrudCommands,
|
registerFleetAgentCrudCommands,
|
||||||
type FleetAgentCrudCommandDeps,
|
type FleetAgentCrudCommandDeps,
|
||||||
@@ -91,8 +88,6 @@ export type SleepFn = (ms: number) => Promise<void>;
|
|||||||
|
|
||||||
export interface FleetCommandDeps {
|
export interface FleetCommandDeps {
|
||||||
runner?: CommandRunner;
|
runner?: CommandRunner;
|
||||||
/** Test seam for the #1292 fleet-start broker preflight (socket presence). */
|
|
||||||
checkBrokerSocket?: (path: string) => Promise<boolean> | boolean;
|
|
||||||
/** Injectable interactive runner for commands needing inherited TTY (e.g., `tmux attach`). */
|
/** Injectable interactive runner for commands needing inherited TTY (e.g., `tmux attach`). */
|
||||||
interactiveRunner?: InteractiveRunner;
|
interactiveRunner?: InteractiveRunner;
|
||||||
/**
|
/**
|
||||||
@@ -801,96 +796,6 @@ export function buildSystemdEnableCommand(unit: string): string[] {
|
|||||||
return ['systemctl', '--user', 'enable', unit];
|
return ['systemctl', '--user', 'enable', unit];
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
|
||||||
* Place a unit file into the ACTIVE systemd user directory, never through a
|
|
||||||
* symlink (#1292, measured 2026-08-17).
|
|
||||||
*
|
|
||||||
* ⚠ SET-INDEPENDENCE (fomo-lin, 2026-08-17): the set of unit names carrying
|
|
||||||
* by-path residue and the set of unit names this install copies are
|
|
||||||
* INDEPENDENT. Until 0.0.50 they were disjoint only by accident of which
|
|
||||||
* units the install happened to name — fomo-lin survived copy-through solely
|
|
||||||
* because its one by-path symlink (the broker) was the one unit the install
|
|
||||||
* did NOT copy. Adding the broker to the copy set made the intersection
|
|
||||||
* non-empty on the first run. Whoever adds a fifth unit to the placement
|
|
||||||
* list inherits this helper and its unlink step; do not place units with a
|
|
||||||
* bare copyFile.
|
|
||||||
*
|
|
||||||
* A host provisioned by the enable-by-path convention carries a symlink AT
|
|
||||||
* the unit-name path in ~/.config/systemd/user/ pointing at the shipped
|
|
||||||
* template under ~/.config/mosaic/systemd/user/. Node's copyFile FOLLOWS
|
|
||||||
* that link and overwrites the SEED template instead of placing the active
|
|
||||||
* unit (verified with fs.copyFile on a throwaway systemd user instance) —
|
|
||||||
* silent, rc=0, and it mutates the directory every later reseed reads from.
|
|
||||||
* The same measurement showed `systemctl enable <name>` does NOT rewrite an
|
|
||||||
* existing by-path wants-symlink, so reconciliation must be explicit.
|
|
||||||
*
|
|
||||||
* Placement therefore: if the destination is a symlink, unlink it first
|
|
||||||
* (unlink → copy — copy-then-unlink would mutate the seed and then destroy
|
|
||||||
* the evidence that it did); then copy. Also removes a stale
|
|
||||||
* `default.target.wants/<name>` symlink that points outside the active
|
|
||||||
* directory (readlink — NOT readFile, which follows the link and returns the
|
|
||||||
* target's CONTENT), so the subsequent enable-by-name recreates it against
|
|
||||||
* the active copy. Idempotent: on a clean or already-reconciled destination
|
|
||||||
* every step is a no-op (the copy rewrites identical bytes).
|
|
||||||
*
|
|
||||||
* Returns what was done, for assertions and install reporting.
|
|
||||||
*/
|
|
||||||
export interface PlaceUnitResult {
|
|
||||||
readonly unit: string;
|
|
||||||
readonly destination: string;
|
|
||||||
/** A symlink at the unit-name path was unlinked (by-path residue). */
|
|
||||||
readonly unlinkedDestinationSymlink: boolean;
|
|
||||||
/** A stale wants-symlink pointing outside the active dir was removed. */
|
|
||||||
readonly removedStaleWantsSymlink: boolean;
|
|
||||||
}
|
|
||||||
|
|
||||||
export async function placeUnitFile(
|
|
||||||
source: string,
|
|
||||||
systemdUserDir: string,
|
|
||||||
unit: string,
|
|
||||||
): Promise<PlaceUnitResult> {
|
|
||||||
const destination = join(systemdUserDir, unit);
|
|
||||||
let unlinkedDestinationSymlink = false;
|
|
||||||
try {
|
|
||||||
const destInfo = await lstat(destination);
|
|
||||||
if (destInfo.isSymbolicLink()) {
|
|
||||||
await unlink(destination);
|
|
||||||
unlinkedDestinationSymlink = true;
|
|
||||||
}
|
|
||||||
} catch {
|
|
||||||
// absent destination — nothing to unlink
|
|
||||||
}
|
|
||||||
await copyFile(source, destination);
|
|
||||||
|
|
||||||
let removedStaleWantsSymlink = false;
|
|
||||||
const wantsLink = join(systemdUserDir, 'default.target.wants', unit);
|
|
||||||
try {
|
|
||||||
const wantsInfo = await lstat(wantsLink);
|
|
||||||
if (wantsInfo.isSymbolicLink()) {
|
|
||||||
// readlink — NOT readFile: readFile FOLLOWS the link and returns the
|
|
||||||
// target file's CONTENT, which is not the question being asked.
|
|
||||||
let target: string | undefined;
|
|
||||||
try {
|
|
||||||
target = await readlink(wantsLink);
|
|
||||||
} catch {
|
|
||||||
target = undefined;
|
|
||||||
}
|
|
||||||
// Normalize (systemctl writes absolute targets; a relative one resolves
|
|
||||||
// against the wants dir). A wants-symlink pointing anywhere other than
|
|
||||||
// the active copy (the by-path convention points at the seed template)
|
|
||||||
// survives enable-by-name unchanged — remove it so enable recreates it.
|
|
||||||
if (target !== undefined && resolve(dirname(wantsLink), target) !== destination) {
|
|
||||||
await unlink(wantsLink);
|
|
||||||
removedStaleWantsSymlink = true;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
} catch {
|
|
||||||
// absent wants link — nothing to reconcile
|
|
||||||
}
|
|
||||||
|
|
||||||
return { unit, destination, unlinkedDestinationSymlink, removedStaleWantsSymlink };
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Returns the systemctl --user disable command for a given unit.
|
* Returns the systemctl --user disable command for a given unit.
|
||||||
* Used by `fleet remove` so a removed agent's enabled unit cannot resurrect on
|
* Used by `fleet remove` so a removed agent's enabled unit cannot resurrect on
|
||||||
@@ -915,7 +820,7 @@ export function buildEnableLingerCommand(user: string): string[] {
|
|||||||
*/
|
*/
|
||||||
export async function enableFleetUnits(
|
export async function enableFleetUnits(
|
||||||
runner: CommandRunner,
|
runner: CommandRunner,
|
||||||
roster: { readonly agents: readonly { readonly name: string }[] },
|
roster: FleetRoster,
|
||||||
opts: { enable?: boolean },
|
opts: { enable?: boolean },
|
||||||
): Promise<void> {
|
): Promise<void> {
|
||||||
if (opts.enable === false) {
|
if (opts.enable === false) {
|
||||||
@@ -925,22 +830,6 @@ export async function enableFleetUnits(
|
|||||||
let succeeded = 0;
|
let succeeded = 0;
|
||||||
let failed = 0;
|
let failed = 0;
|
||||||
|
|
||||||
// The lease broker ships with the fleet and every gated runtime needs it
|
|
||||||
// (#1292): seats die at lease registration without it, and no documented
|
|
||||||
// path ever enabled it. Enabled first — alongside the holder — and the
|
|
||||||
// unit must have been placed by installFleet's placeUnitFile step.
|
|
||||||
const brokerResult = await runner(
|
|
||||||
...splitCommand(buildSystemdEnableCommand('mosaic-lease-broker.service')),
|
|
||||||
);
|
|
||||||
if (brokerResult.exitCode === 0) {
|
|
||||||
succeeded++;
|
|
||||||
} else {
|
|
||||||
failed++;
|
|
||||||
process.stderr.write(
|
|
||||||
`Warning: could not enable mosaic-lease-broker.service: ${brokerResult.stderr || brokerResult.stdout || 'non-zero exit'}\n`,
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
const holderResult = await runner(
|
const holderResult = await runner(
|
||||||
...splitCommand(buildSystemdEnableCommand('mosaic-tmux-holder.service')),
|
...splitCommand(buildSystemdEnableCommand('mosaic-tmux-holder.service')),
|
||||||
);
|
);
|
||||||
@@ -1637,9 +1526,8 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
.description('Install local fleet tools and user systemd units')
|
.description('Install local fleet tools and user systemd units')
|
||||||
.option('--no-enable', 'Skip enabling units for boot-survival')
|
.option('--no-enable', 'Skip enabling units for boot-survival')
|
||||||
.action(async (opts: { enable?: boolean }) => {
|
.action(async (opts: { enable?: boolean }) => {
|
||||||
await installFleet(cmd, frameworkRoot, runner);
|
await installFleet(cmd, frameworkRoot);
|
||||||
// Unit enablement needs agent names only, so it reads either version.
|
const roster = await loadRosterForCommand(cmd);
|
||||||
const roster = await loadRosterReadModel(cmd);
|
|
||||||
await enableFleetUnits(runner, roster, opts);
|
await enableFleetUnits(runner, roster, opts);
|
||||||
});
|
});
|
||||||
|
|
||||||
@@ -1648,9 +1536,8 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
.description('Install local fleet tools and user systemd units')
|
.description('Install local fleet tools and user systemd units')
|
||||||
.option('--no-enable', 'Skip enabling units for boot-survival')
|
.option('--no-enable', 'Skip enabling units for boot-survival')
|
||||||
.action(async (opts: { enable?: boolean }) => {
|
.action(async (opts: { enable?: boolean }) => {
|
||||||
await installFleet(cmd, frameworkRoot, runner);
|
await installFleet(cmd, frameworkRoot);
|
||||||
// Unit enablement needs agent names only, so it reads either version.
|
const roster = await loadRosterForCommand(cmd);
|
||||||
const roster = await loadRosterReadModel(cmd);
|
|
||||||
await enableFleetUnits(runner, roster, opts);
|
await enableFleetUnits(runner, roster, opts);
|
||||||
});
|
});
|
||||||
|
|
||||||
@@ -1701,37 +1588,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
);
|
);
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
if (action === 'start') {
|
|
||||||
// Broker preflight (#1292), re-probed on EVERY invocation: a
|
|
||||||
// gated runtime started without a live lease broker dies ~4s in
|
|
||||||
// while the unit reports active (RemainAfterExit) — enabling +
|
|
||||||
// starting here and then RE-CHECKING the socket refuses loudly
|
|
||||||
// instead of reporting rc0 over a doomed start. This is the
|
|
||||||
// second-start check as much as the first: it never trusts unit
|
|
||||||
// ActiveState.
|
|
||||||
await runChecked(runner, [
|
|
||||||
'systemctl',
|
|
||||||
'--user',
|
|
||||||
'enable',
|
|
||||||
'mosaic-lease-broker.service',
|
|
||||||
]);
|
|
||||||
await runChecked(runner, [
|
|
||||||
'systemctl',
|
|
||||||
'--user',
|
|
||||||
'start',
|
|
||||||
'mosaic-lease-broker.service',
|
|
||||||
]);
|
|
||||||
if (!(await brokerSocketPresent(deps))) {
|
|
||||||
console.error(
|
|
||||||
'[fleet] broker-absent: lease broker socket did not appear after enable+start (#1292).',
|
|
||||||
);
|
|
||||||
console.error(
|
|
||||||
'[fleet] remedy: mosaic fleet install (it reconciles either enable convention)',
|
|
||||||
);
|
|
||||||
process.exitCode = 1;
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if (action === 'restart') {
|
if (action === 'restart') {
|
||||||
// Serialize the holder+agents teardown/relaunch behind the restart lock
|
// Serialize the holder+agents teardown/relaunch behind the restart lock
|
||||||
// so a re-entrant restart waits for clean shutdown before relaunching,
|
// so a re-entrant restart waits for clean shutdown before relaunching,
|
||||||
@@ -1832,9 +1688,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
.action(async (opts: { json?: boolean }) => {
|
.action(async (opts: { json?: boolean }) => {
|
||||||
const commandOpts = cmd.opts<{ mosaicHome: string; roster?: string }>();
|
const commandOpts = cmd.opts<{ mosaicHome: string; roster?: string }>();
|
||||||
const activePaths = resolveFleetPaths(commandOpts.mosaicHome);
|
const activePaths = resolveFleetPaths(commandOpts.mosaicHome);
|
||||||
// ps only reads, so it takes the version-agnostic read model rather than
|
const roster = await loadRosterForCommand(cmd);
|
||||||
// the v1 parser, which rejects a v2 roster outright.
|
|
||||||
const roster = await loadRosterReadModel(cmd);
|
|
||||||
const { tenant_id, host } = getDefaultTenantAndHost();
|
const { tenant_id, host } = getDefaultTenantAndHost();
|
||||||
const nowMs = Date.now();
|
const nowMs = Date.now();
|
||||||
|
|
||||||
@@ -2054,16 +1908,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
start: boolean;
|
start: boolean;
|
||||||
},
|
},
|
||||||
) => {
|
) => {
|
||||||
if (await usesRosterV2ControlPlane(cmd)) {
|
|
||||||
// command.error, not a bare throw: this is operator guidance, and a
|
|
||||||
// bare throw reaches the top level uncaught and prints it under a Node
|
|
||||||
// stack trace. Measured on canary — the message is the whole point of
|
|
||||||
// the refusal, so it has to arrive readable.
|
|
||||||
cmd.error(rosterV2MutationGuidance('add', 'create', name), {
|
|
||||||
code: 'fleet.roster-v2',
|
|
||||||
exitCode: 1,
|
|
||||||
});
|
|
||||||
}
|
|
||||||
if (!VALID_FLEET_RUNTIMES.includes(opts.runtime)) {
|
if (!VALID_FLEET_RUNTIMES.includes(opts.runtime)) {
|
||||||
throw new Error(
|
throw new Error(
|
||||||
`Invalid runtime "${opts.runtime}". Valid runtimes: ${VALID_FLEET_RUNTIMES.join(', ')}.`,
|
`Invalid runtime "${opts.runtime}". Valid runtimes: ${VALID_FLEET_RUNTIMES.join(', ')}.`,
|
||||||
@@ -2129,12 +1973,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
.description('Remove an agent from the fleet roster')
|
.description('Remove an agent from the fleet roster')
|
||||||
.option('--keep-files', 'Skip deleting env and heartbeat files')
|
.option('--keep-files', 'Skip deleting env and heartbeat files')
|
||||||
.action(async (name: string, opts: { keepFiles?: boolean }) => {
|
.action(async (name: string, opts: { keepFiles?: boolean }) => {
|
||||||
if (await usesRosterV2ControlPlane(cmd)) {
|
|
||||||
cmd.error(rosterV2MutationGuidance('remove', 'delete', name), {
|
|
||||||
code: 'fleet.roster-v2',
|
|
||||||
exitCode: 1,
|
|
||||||
});
|
|
||||||
}
|
|
||||||
const commandOpts = cmd.opts<{ mosaicHome: string; roster?: string }>();
|
const commandOpts = cmd.opts<{ mosaicHome: string; roster?: string }>();
|
||||||
const activePaths = resolveFleetPaths(commandOpts.mosaicHome);
|
const activePaths = resolveFleetPaths(commandOpts.mosaicHome);
|
||||||
const rosterPath = await resolveRosterPath(commandOpts.mosaicHome, commandOpts.roster);
|
const rosterPath = await resolveRosterPath(commandOpts.mosaicHome, commandOpts.roster);
|
||||||
@@ -2490,16 +2328,10 @@ export function registerFleetAgentCommands(
|
|||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
async function installFleet(
|
async function installFleet(cmd: Command, frameworkRoot: string): Promise<void> {
|
||||||
cmd: Command,
|
|
||||||
frameworkRoot: string,
|
|
||||||
runner: CommandRunner,
|
|
||||||
): Promise<void> {
|
|
||||||
const activePaths = resolveFleetPaths(cmd.opts<{ mosaicHome: string }>().mosaicHome);
|
const activePaths = resolveFleetPaths(cmd.opts<{ mosaicHome: string }>().mosaicHome);
|
||||||
assertDefaultMosaicHomeForSystemd(activePaths.mosaicHome);
|
assertDefaultMosaicHomeForSystemd(activePaths.mosaicHome);
|
||||||
// Read model first: every file this function places is roster-independent, and
|
const roster = await loadRosterForCommand(cmd);
|
||||||
// the v1 parser would reject a v2 roster before any of them were written.
|
|
||||||
const roster = await loadRosterReadModel(cmd);
|
|
||||||
await ensureFleetHolderIdentity(activePaths.mosaicHome);
|
await ensureFleetHolderIdentity(activePaths.mosaicHome);
|
||||||
await mkdir(activePaths.fleetToolsDir, { recursive: true });
|
await mkdir(activePaths.fleetToolsDir, { recursive: true });
|
||||||
await mkdir(activePaths.tmuxToolsDir, { recursive: true });
|
await mkdir(activePaths.tmuxToolsDir, { recursive: true });
|
||||||
@@ -2546,65 +2378,29 @@ async function installFleet(
|
|||||||
for (const toolPath of executableToolPaths) {
|
for (const toolPath of executableToolPaths) {
|
||||||
await chmod(toolPath, 0o755);
|
await chmod(toolPath, 0o755);
|
||||||
}
|
}
|
||||||
// Unit placement (#1292): every unit goes through placeUnitFile — never a
|
await copyFile(
|
||||||
// bare copyFile — so a by-path-enable symlink at the destination is
|
join(frameworkRoot, 'systemd', 'user', 'mosaic-tmux-holder.service'),
|
||||||
// unlinked rather than written through (copy-through would silently
|
join(activePaths.systemdUserDir, 'mosaic-tmux-holder.service'),
|
||||||
// overwrite the SEED template, measured 2026-08-17). The lease broker unit
|
|
||||||
// is placed here too: previously the install named three units and omitted
|
|
||||||
// the broker entirely, which is why no documented path ever enabled it.
|
|
||||||
const placedUnits = await Promise.all(
|
|
||||||
[
|
|
||||||
'mosaic-tmux-holder.service',
|
|
||||||
'[email protected]',
|
|
||||||
'[email protected]',
|
|
||||||
'mosaic-lease-broker.service',
|
|
||||||
].map((unit) =>
|
|
||||||
placeUnitFile(join(frameworkRoot, 'systemd', 'user', unit), activePaths.systemdUserDir, unit),
|
|
||||||
),
|
|
||||||
);
|
);
|
||||||
const reconciled = placedUnits.filter(
|
await copyFile(
|
||||||
(result) => result.unlinkedDestinationSymlink || result.removedStaleWantsSymlink,
|
join(frameworkRoot, 'systemd', 'user', '[email protected]'),
|
||||||
|
join(activePaths.systemdUserDir, '[email protected]'),
|
||||||
|
);
|
||||||
|
await copyFile(
|
||||||
|
join(frameworkRoot, 'systemd', 'user', '[email protected]'),
|
||||||
|
join(activePaths.systemdUserDir, '[email protected]'),
|
||||||
);
|
);
|
||||||
if (reconciled.length > 0) {
|
|
||||||
console.log(
|
|
||||||
`Reconciled ${reconciled.length} unit placement(s) from by-path enable residue: ${reconciled.map((r) => r.unit).join(', ')}`,
|
|
||||||
);
|
|
||||||
}
|
|
||||||
// systemd will not see a replaced unit file without a reload; do it once
|
|
||||||
// after all placements, before any enable call below. runCommand never
|
|
||||||
// rejects (it resolves exitCode 127 on spawn error), so a plain await with
|
|
||||||
// an exitCode check matches the rest of this file's systemctl handling.
|
|
||||||
const reloadResult = await runner(...splitCommand(['systemctl', '--user', 'daemon-reload']));
|
|
||||||
if (reloadResult.exitCode !== 0) {
|
|
||||||
process.stderr.write(
|
|
||||||
`Warning: systemctl --user daemon-reload after unit placement failed (non-systemd host?): ${reloadResult.stderr || reloadResult.stdout || 'non-zero exit'}\n`,
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
// On roster v2 the reconciler owns the generated env: `apply` writes it and
|
for (const agent of roster.agents) {
|
||||||
// `regen` rebuilds it, both from projectRosterV2AgentGeneratedEnv. Writing it
|
|
||||||
// here too — necessarily through the v1 mapping — would be the third writer of
|
|
||||||
// one file and would break the #791 single-SSOT invariant. So v2 gets the tool
|
|
||||||
// files and the units, and nothing else.
|
|
||||||
if (roster.version === 2) {
|
|
||||||
console.log(
|
|
||||||
`Installed fleet tools and systemd units for ${roster.agents.length} agent(s). ` +
|
|
||||||
`Generated env is owned by the reconciler on roster v2 — run: mosaic fleet apply --expected-generation <n>`,
|
|
||||||
);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
const v1Roster = await loadRosterForCommand(cmd);
|
|
||||||
for (const agent of v1Roster.agents) {
|
|
||||||
await writeAgentEnvironmentProjection({
|
await writeAgentEnvironmentProjection({
|
||||||
mosaicHome: activePaths.mosaicHome,
|
mosaicHome: activePaths.mosaicHome,
|
||||||
agentEnvDir: activePaths.agentEnvDir,
|
agentEnvDir: activePaths.agentEnvDir,
|
||||||
agentName: agent.name,
|
agentName: agent.name,
|
||||||
generated: generateAgentEnvValues(v1Roster, agent),
|
generated: generateAgentEnvValues(roster, agent),
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
console.log(`Installed fleet files for ${v1Roster.agents.length} agent(s).`);
|
console.log(`Installed fleet files for ${roster.agents.length} agent(s).`);
|
||||||
}
|
}
|
||||||
|
|
||||||
async function loadRosterForCommand(cmd: Command): Promise<FleetRoster> {
|
async function loadRosterForCommand(cmd: Command): Promise<FleetRoster> {
|
||||||
@@ -2631,77 +2427,6 @@ async function usesRosterV2ControlPlane(cmd: Command): Promise<boolean> {
|
|||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
|
||||||
* `add`/`remove` and `create`/`delete` are not two spellings of one operation.
|
|
||||||
* The v1 pair edits the roster *and* drives systemd; the v2 pair is documented
|
|
||||||
* as changing desired state "without runtime actions", leaving convergence to
|
|
||||||
* `apply`. `add` also collects four fields where a v2 agent requires eleven, so
|
|
||||||
* routing it to `create` would mean inventing provider, alias, reasoning and
|
|
||||||
* tool-policy defaults on the operator's behalf. Refusing with the real command
|
|
||||||
* is honest; silently guessing an agent's provider is not.
|
|
||||||
*/
|
|
||||||
function rosterV2MutationGuidance(
|
|
||||||
v1Command: 'add' | 'remove',
|
|
||||||
v2Command: 'create' | 'delete',
|
|
||||||
name: string,
|
|
||||||
): string {
|
|
||||||
const target = v2Command === 'delete' ? ` ${name}` : '';
|
|
||||||
return (
|
|
||||||
`mosaic fleet ${v1Command} does not operate on a roster-v2 fleet. ` +
|
|
||||||
`Roster v2 separates desired state from convergence:\n` +
|
|
||||||
` 1. mosaic fleet ${v2Command}${target} --expected-generation <current> ` +
|
|
||||||
`${v2Command === 'create' ? "--agent '<json>' " : ''}` +
|
|
||||||
`(edits the roster only)\n` +
|
|
||||||
` 2. mosaic fleet apply --expected-generation <new> (converges systemd and tmux)\n` +
|
|
||||||
`Read the current generation with: mosaic fleet status`
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* The read-only fields shared by roster v1 and v2, for the commands that only
|
|
||||||
* ever *read* the roster (`ps`, and unit enablement inside `install`).
|
|
||||||
*
|
|
||||||
* This is deliberately NOT a v2→v1 downshift. A downshifted `FleetRoster` would
|
|
||||||
* be accepted by `generateAgentEnvValues`, and that would make a third writer of
|
|
||||||
* `fleet/agents/<name>.env.generated` — through the v1 mapping — breaking the
|
|
||||||
* #791 single-SSOT invariant that {@link projectRosterV2AgentGeneratedEnv} is
|
|
||||||
* documented to hold. Keeping the read model this small makes that misuse
|
|
||||||
* impossible: there is nothing here to write a roster or an env file back from.
|
|
||||||
*/
|
|
||||||
interface FleetRosterReadModel {
|
|
||||||
readonly version: 1 | 2;
|
|
||||||
readonly tmux: { readonly socketName: string; readonly holderSession: string };
|
|
||||||
readonly agents: readonly {
|
|
||||||
readonly name: string;
|
|
||||||
readonly alias?: string;
|
|
||||||
readonly runtime: string;
|
|
||||||
}[];
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Reads either roster version into the shared read-only view. */
|
|
||||||
async function loadRosterReadModel(cmd: Command): Promise<FleetRosterReadModel> {
|
|
||||||
const opts = cmd.opts<{ mosaicHome: string; roster?: string }>();
|
|
||||||
const path = await resolveRosterPath(opts.mosaicHome, opts.roster);
|
|
||||||
if (!(await usesRosterV2ControlPlane(cmd))) {
|
|
||||||
const v1 = await loadRosterAtPath(cmd, path);
|
|
||||||
return {
|
|
||||||
version: 1,
|
|
||||||
tmux: { socketName: v1.tmux.socketName, holderSession: v1.tmux.holderSession },
|
|
||||||
agents: v1.agents,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
try {
|
|
||||||
const v2 = parseRosterV2(await readFleetRosterText(path), 'yaml');
|
|
||||||
return {
|
|
||||||
version: 2,
|
|
||||||
tmux: { socketName: v2.tmux.socketName, holderSession: v2.tmux.holderSession },
|
|
||||||
agents: v2.agents,
|
|
||||||
};
|
|
||||||
} catch (error) {
|
|
||||||
reportFleetRosterConfigurationError(cmd, error);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
async function loadRosterFromAgentCommand(
|
async function loadRosterFromAgentCommand(
|
||||||
command: Command,
|
command: Command,
|
||||||
mosaicHomeOverride?: string,
|
mosaicHomeOverride?: string,
|
||||||
@@ -2776,40 +2501,6 @@ function splitCommand(command: string[]): [string, string[]] {
|
|||||||
return [bin, args];
|
return [bin, args];
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
|
||||||
* Lease-broker socket presence for the fleet-start preflight (#1292).
|
|
||||||
* Resolution precedence matches launch.ts's defaultLeaseBrokerSocket and
|
|
||||||
* start-agent-session.sh's broker_socket_path: explicit
|
|
||||||
* MOSAIC_LEASE_BROKER_SOCKET, else $XDG_RUNTIME_DIR/mosaic-lease/broker.sock,
|
|
||||||
* else /run/user/<uid>/mosaic-lease/broker.sock. Pure filesystem check — this
|
|
||||||
* deliberately does NOT consult systemd state: a unit can be active
|
|
||||||
* (RemainAfterExit) with no live socket, and the socket is the thing the
|
|
||||||
* gated runtime connects to. Injectable via deps for tests.
|
|
||||||
*/
|
|
||||||
export function resolveLeaseBrokerSocketForPreflight(
|
|
||||||
env: NodeJS.ProcessEnv = process.env,
|
|
||||||
uid: number = typeof process.getuid === 'function' ? process.getuid() : 0,
|
|
||||||
): string {
|
|
||||||
if (env['MOSAIC_LEASE_BROKER_SOCKET']) return env['MOSAIC_LEASE_BROKER_SOCKET'];
|
|
||||||
const runtimeDir = env['XDG_RUNTIME_DIR'] ?? `/run/user/${uid}`;
|
|
||||||
return join(runtimeDir, 'mosaic-lease', 'broker.sock');
|
|
||||||
}
|
|
||||||
|
|
||||||
async function brokerSocketPresent(
|
|
||||||
deps: FleetCommandDeps,
|
|
||||||
env: NodeJS.ProcessEnv = process.env,
|
|
||||||
): Promise<boolean> {
|
|
||||||
const check = deps.checkBrokerSocket;
|
|
||||||
if (check) return check(resolveLeaseBrokerSocketForPreflight(env));
|
|
||||||
try {
|
|
||||||
const socketPath = resolveLeaseBrokerSocketForPreflight(env);
|
|
||||||
await access(socketPath, constants.S_IFSOCK);
|
|
||||||
return true;
|
|
||||||
} catch {
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/** All supported fleet profile names. */
|
/** All supported fleet profile names. */
|
||||||
export type FleetProfile =
|
export type FleetProfile =
|
||||||
| 'general'
|
| 'general'
|
||||||
|
|||||||
@@ -205,12 +205,6 @@ export async function runLeaseEnforcementDoctorCheck(
|
|||||||
message:
|
message:
|
||||||
`Lease-enforcement hooks (${matchedMarkers.join(', ')}) are wired in ~/.claude/settings.json, but ${reasons.join(' and ')}. ` +
|
`Lease-enforcement hooks (${matchedMarkers.join(', ')}) are wired in ~/.claude/settings.json, but ${reasons.join(' and ')}. ` +
|
||||||
'Every gated tool call will fail closed and BRICK this agent (see #869). ' +
|
'Every gated tool call will fail closed and BRICK this agent (see #869). ' +
|
||||||
// #1292: one remedy, correct under BOTH enable conventions (by-path on
|
'Remediate by activating the lease-broker supervisor (systemd unit + socket) or by removing the enforcement hooks from ~/.claude/settings.json.',
|
||||||
// the seed template, and copy-then-enable in the active dir). Written
|
|
||||||
// from the 2026-08-17 symlink measurement: `systemctl enable` by name
|
|
||||||
// does NOT rewrite an existing by-path wants-symlink, so teaching a
|
|
||||||
// manual systemctl line here could leave a host with two competing
|
|
||||||
// wants links. fleet install reconciles either shape.
|
|
||||||
'Remedy: run `mosaic fleet install` (it reconciles either enable convention), or remove the enforcement hooks from ~/.claude/settings.json.',
|
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -459,7 +459,6 @@ describe('FCM-M3-002 reconciler lifecycle acceptance', (): void => {
|
|||||||
plan: {
|
plan: {
|
||||||
generation: 7,
|
generation: 7,
|
||||||
holder: 'owned',
|
holder: 'owned',
|
||||||
broker: { unitInstalled: false, socketPresent: false },
|
|
||||||
agents: [
|
agents: [
|
||||||
{
|
{
|
||||||
name: 'coder0',
|
name: 'coder0',
|
||||||
|
|||||||
@@ -92,112 +92,6 @@ async function run(command: FleetReconcileCommand, overrides: Partial<FleetRecon
|
|||||||
}
|
}
|
||||||
|
|
||||||
describe('fleet roster-owned reconciler', (): void => {
|
describe('fleet roster-owned reconciler', (): void => {
|
||||||
// ── #1292: broker as first-class plan member + broker-first start ordering ──
|
|
||||||
|
|
||||||
it('reports broker unit and socket state in the plan (socket is the signal, not unit state)', async (): Promise<void> => {
|
|
||||||
const result = await run('status', {
|
|
||||||
statPath: async () => true,
|
|
||||||
checkBrokerSocket: async () => true,
|
|
||||||
});
|
|
||||||
expect(result.plan.broker).toEqual({ unitInstalled: true, socketPresent: true });
|
|
||||||
});
|
|
||||||
|
|
||||||
it('reports a dead broker as socketPresent=false even when the unit is installed (enabled-but-dead is the #1292 shape)', async (): Promise<void> => {
|
|
||||||
const result = await run('status', {
|
|
||||||
statPath: async () => true,
|
|
||||||
checkBrokerSocket: async () => false,
|
|
||||||
});
|
|
||||||
expect(result.plan.broker).toEqual({ unitInstalled: true, socketPresent: false });
|
|
||||||
});
|
|
||||||
|
|
||||||
it('reports broker-absent when neither seam is present (defaults false, never guesses healthy)', async (): Promise<void> => {
|
|
||||||
const result = await run('status');
|
|
||||||
expect(result.plan.broker).toEqual({ unitInstalled: false, socketPresent: false });
|
|
||||||
});
|
|
||||||
|
|
||||||
it('command start enables and starts the broker BEFORE the holder and any agent unit', async (): Promise<void> => {
|
|
||||||
const calls: string[][] = [];
|
|
||||||
const result = await run('start', {
|
|
||||||
runner: async (command, args) => {
|
|
||||||
calls.push([command, ...args]);
|
|
||||||
if (command === 'tmux' && args.includes('list-sessions')) {
|
|
||||||
return { stdout: '_holder\ncoder0\n', stderr: '', exitCode: 0 };
|
|
||||||
}
|
|
||||||
if (command === 'tmux' && args.includes('show-environment')) {
|
|
||||||
return {
|
|
||||||
stdout:
|
|
||||||
'HOME=/home/mosaic\nMOSAIC_FLEET_OWNER=11111111-1111-4111-8111-111111111111\nMOSAIC_TMUX_HOLDER=_holder\nMOSAIC_TMUX_SOCKET=mosaic-fleet\nPATH=/usr/bin:/bin\nPWD=/home/mosaic\n',
|
|
||||||
stderr: '',
|
|
||||||
exitCode: 0,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
return { stdout: '', stderr: '', exitCode: 0 };
|
|
||||||
},
|
|
||||||
});
|
|
||||||
expect(result.lifecycle).toBe('complete');
|
|
||||||
const brokerEnable = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user enable mosaic-lease-broker.service',
|
|
||||||
);
|
|
||||||
const brokerStart = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user start mosaic-lease-broker.service',
|
|
||||||
);
|
|
||||||
const holderStart = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user start mosaic-tmux-holder.service',
|
|
||||||
);
|
|
||||||
const agentStart = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user start [email protected]',
|
|
||||||
);
|
|
||||||
expect(brokerEnable).toBeGreaterThanOrEqual(0);
|
|
||||||
expect(brokerStart).toBeGreaterThan(brokerEnable);
|
|
||||||
// Holder start may be absent (holder 'owned' in this fixture); if present it must follow the broker.
|
|
||||||
if (holderStart >= 0) expect(holderStart).toBeGreaterThan(brokerStart);
|
|
||||||
expect(agentStart).toBeGreaterThan(brokerStart);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('apply with a running desired agent also enables and starts the broker first', async (): Promise<void> => {
|
|
||||||
const calls: string[][] = [];
|
|
||||||
const runningRoster: FleetRosterV2 = {
|
|
||||||
...roster,
|
|
||||||
agents: roster.agents.map((agent) =>
|
|
||||||
agent.name === 'coder0'
|
|
||||||
? { ...agent, lifecycle: { enabled: true, desiredState: 'running' as const } }
|
|
||||||
: agent,
|
|
||||||
),
|
|
||||||
};
|
|
||||||
const result = await executeFleetReconcile({
|
|
||||||
roster: runningRoster,
|
|
||||||
command: 'apply',
|
|
||||||
expectedGeneration: 7,
|
|
||||||
deps: deps({
|
|
||||||
readRoster: async () => runningRoster,
|
|
||||||
runner: async (command, args) => {
|
|
||||||
calls.push([command, ...args]);
|
|
||||||
if (command === 'tmux' && args.includes('list-sessions')) {
|
|
||||||
return { stdout: '_holder\n', stderr: '', exitCode: 0 };
|
|
||||||
}
|
|
||||||
if (command === 'tmux' && args.includes('show-environment')) {
|
|
||||||
return {
|
|
||||||
stdout:
|
|
||||||
'HOME=/home/mosaic\nMOSAIC_FLEET_OWNER=11111111-1111-4111-8111-111111111111\nMOSAIC_TMUX_HOLDER=_holder\nMOSAIC_TMUX_SOCKET=mosaic-fleet\nPATH=/usr/bin:/bin\nPWD=/home/mosaic\n',
|
|
||||||
stderr: '',
|
|
||||||
exitCode: 0,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
return { stdout: '', stderr: '', exitCode: 0 };
|
|
||||||
},
|
|
||||||
}),
|
|
||||||
});
|
|
||||||
expect(result.applied).toBe(true);
|
|
||||||
const brokerStart = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user start mosaic-lease-broker.service',
|
|
||||||
);
|
|
||||||
const agentStart = calls.findIndex(
|
|
||||||
(c) => c.join(' ') === 'systemctl --user start [email protected]',
|
|
||||||
);
|
|
||||||
expect(brokerStart).toBeGreaterThanOrEqual(0);
|
|
||||||
expect(agentStart).toBeGreaterThan(brokerStart);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('fails closed on a symlinked fleet ancestor without touching its target', async (): Promise<void> => {
|
it('fails closed on a symlinked fleet ancestor without touching its target', async (): Promise<void> => {
|
||||||
const home = await lockHome();
|
const home = await lockHome();
|
||||||
const fleet = join(home, 'fleet');
|
const fleet = join(home, 'fleet');
|
||||||
|
|||||||
@@ -43,10 +43,6 @@ export interface FleetReconcileDeps {
|
|||||||
readonly overrideDir?: string;
|
readonly overrideDir?: string;
|
||||||
readonly homeDirectory?: string;
|
readonly homeDirectory?: string;
|
||||||
readonly readHolderIdentity?: () => Promise<string>;
|
readonly readHolderIdentity?: () => Promise<string>;
|
||||||
/** Test/observation seams for the lease-broker plan member (#1292). */
|
|
||||||
readonly statPath?: (path: string) => Promise<boolean> | boolean;
|
|
||||||
readonly checkBrokerSocket?: (path: string) => Promise<boolean> | boolean;
|
|
||||||
readonly brokerSocketEnv?: NodeJS.ProcessEnv;
|
|
||||||
readonly validateRoster?: (roster: FleetRosterV2) => Promise<void>;
|
readonly validateRoster?: (roster: FleetRosterV2) => Promise<void>;
|
||||||
readonly prepareProjections?: (roster: FleetRosterV2) => Promise<readonly unknown[]>;
|
readonly prepareProjections?: (roster: FleetRosterV2) => Promise<readonly unknown[]>;
|
||||||
readonly applyProjection?: (prepared: unknown) => Promise<unknown>;
|
readonly applyProjection?: (prepared: unknown) => Promise<unknown>;
|
||||||
@@ -78,17 +74,6 @@ export interface FleetReconcileObservedAgent {
|
|||||||
export interface FleetReconcilePlan {
|
export interface FleetReconcilePlan {
|
||||||
readonly generation: number;
|
readonly generation: number;
|
||||||
readonly holder: 'owned' | 'missing' | 'ownership-mismatch';
|
readonly holder: 'owned' | 'missing' | 'ownership-mismatch';
|
||||||
/**
|
|
||||||
* Lease broker observation (#1292): every gated runtime registers with the
|
|
||||||
* broker or dies ~4s in — a broker not in the plan cannot be reported as
|
|
||||||
* drifted, which made "broker died an hour ago" and "broker fine"
|
|
||||||
* produce identical output. `unitInstalled` = unit file present in the
|
|
||||||
* active dir; `socketPresent` = live broker at the resolved socket path.
|
|
||||||
*/
|
|
||||||
readonly broker: {
|
|
||||||
readonly unitInstalled: boolean;
|
|
||||||
readonly socketPresent: boolean;
|
|
||||||
};
|
|
||||||
readonly agents: readonly FleetReconcileObservedAgent[];
|
readonly agents: readonly FleetReconcileObservedAgent[];
|
||||||
readonly unmanagedSessions: readonly string[];
|
readonly unmanagedSessions: readonly string[];
|
||||||
}
|
}
|
||||||
@@ -329,39 +314,6 @@ function isObservational(command: FleetReconcileCommand): boolean {
|
|||||||
return command === 'plan' || command === 'status' || command === 'verify' || command === 'doctor';
|
return command === 'plan' || command === 'status' || command === 'verify' || command === 'doctor';
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
|
||||||
* Observe the lease broker for the plan (#1292). Unit presence via systemctl
|
|
||||||
* is-system-running is NOT the signal — a unit can be enabled-but-dead. The
|
|
||||||
* authoritative signal is the socket the gated runtimes connect to, matching
|
|
||||||
* broker-supervisor.ts's `checkBrokerSupervisorHealth` (healthy ===
|
|
||||||
* socketPresent). Injectable so tests drive every branch without a broker.
|
|
||||||
*/
|
|
||||||
async function observeBroker(deps: FleetReconcileDeps): Promise<FleetReconcilePlan['broker']> {
|
|
||||||
const homeDirectory = deps.homeDirectory ?? homedir();
|
|
||||||
const env = (deps.brokerSocketEnv ?? process.env) as NodeJS.ProcessEnv;
|
|
||||||
const uid = typeof process.getuid === 'function' ? process.getuid() : 0;
|
|
||||||
const runtimeDir = env['XDG_RUNTIME_DIR'] ?? `/run/user/${uid}`;
|
|
||||||
const socketPath =
|
|
||||||
env['MOSAIC_LEASE_BROKER_SOCKET'] ?? join(runtimeDir, 'mosaic-lease', 'broker.sock');
|
|
||||||
const configHome = env['XDG_CONFIG_HOME'] ?? join(homeDirectory, '.config');
|
|
||||||
const unitPath = join(configHome, 'systemd', 'user', 'mosaic-lease-broker.service');
|
|
||||||
const statPath = deps.statPath;
|
|
||||||
const checkBrokerSocket = deps.checkBrokerSocket;
|
|
||||||
let unitInstalled = false;
|
|
||||||
let socketPresent = false;
|
|
||||||
try {
|
|
||||||
unitInstalled = statPath ? await statPath(unitPath) : false;
|
|
||||||
} catch {
|
|
||||||
unitInstalled = false;
|
|
||||||
}
|
|
||||||
try {
|
|
||||||
socketPresent = checkBrokerSocket ? await checkBrokerSocket(socketPath) : false;
|
|
||||||
} catch {
|
|
||||||
socketPresent = false;
|
|
||||||
}
|
|
||||||
return { unitInstalled, socketPresent };
|
|
||||||
}
|
|
||||||
|
|
||||||
async function observeFleet(
|
async function observeFleet(
|
||||||
roster: FleetRosterV2,
|
roster: FleetRosterV2,
|
||||||
deps: FleetReconcileDeps,
|
deps: FleetReconcileDeps,
|
||||||
@@ -372,12 +324,10 @@ async function observeFleet(
|
|||||||
'-F',
|
'-F',
|
||||||
'#{session_name}',
|
'#{session_name}',
|
||||||
]);
|
]);
|
||||||
const broker = await observeBroker(deps);
|
|
||||||
if (sessionsResult.exitCode !== 0) {
|
if (sessionsResult.exitCode !== 0) {
|
||||||
return {
|
return {
|
||||||
generation: roster.generation,
|
generation: roster.generation,
|
||||||
holder: 'missing',
|
holder: 'missing',
|
||||||
broker,
|
|
||||||
agents: await observeAgents(roster, deps, new Set<string>()),
|
agents: await observeAgents(roster, deps, new Set<string>()),
|
||||||
unmanagedSessions: [],
|
unmanagedSessions: [],
|
||||||
};
|
};
|
||||||
@@ -400,7 +350,6 @@ async function observeFleet(
|
|||||||
return {
|
return {
|
||||||
generation: roster.generation,
|
generation: roster.generation,
|
||||||
holder,
|
holder,
|
||||||
broker,
|
|
||||||
agents: await observeAgents(roster, deps, sessions),
|
agents: await observeAgents(roster, deps, sessions),
|
||||||
unmanagedSessions: Object.freeze(unmanagedSessions.sort()),
|
unmanagedSessions: Object.freeze(unmanagedSessions.sort()),
|
||||||
};
|
};
|
||||||
@@ -568,24 +517,6 @@ async function executeExplicitLifecycle(
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
try {
|
try {
|
||||||
// Broker FIRST (#1292): a gated runtime started without a running lease
|
|
||||||
// broker dies ~4 seconds in at registration — enable the unit (install
|
|
||||||
// places it) and start it before any holder/agent lifecycle effect. The
|
|
||||||
// socket re-check after start is the same probe observeBroker uses, so a
|
|
||||||
// unit that starts but never produces a socket is caught here, not four
|
|
||||||
// seconds later inside a doomed seat.
|
|
||||||
if (request.command === 'start') {
|
|
||||||
await runChecked(request.deps, 'systemctl', [
|
|
||||||
'--user',
|
|
||||||
'enable',
|
|
||||||
'mosaic-lease-broker.service',
|
|
||||||
]);
|
|
||||||
await runChecked(request.deps, 'systemctl', [
|
|
||||||
'--user',
|
|
||||||
'start',
|
|
||||||
'mosaic-lease-broker.service',
|
|
||||||
]);
|
|
||||||
}
|
|
||||||
if (request.command === 'start' && plan.holder === 'missing') {
|
if (request.command === 'start' && plan.holder === 'missing') {
|
||||||
await runChecked(request.deps, 'systemctl', [
|
await runChecked(request.deps, 'systemctl', [
|
||||||
'--user',
|
'--user',
|
||||||
@@ -631,12 +562,6 @@ async function applyDesiredLifecycle(
|
|||||||
(agent: FleetRosterV2Agent): boolean =>
|
(agent: FleetRosterV2Agent): boolean =>
|
||||||
agent.lifecycle.enabled && agent.lifecycle.desiredState === 'running',
|
agent.lifecycle.enabled && agent.lifecycle.desiredState === 'running',
|
||||||
);
|
);
|
||||||
// Broker before any running agent, same ordering and reason as the
|
|
||||||
// command-driven path above (#1292).
|
|
||||||
if (needsRunningAgent) {
|
|
||||||
await runChecked(deps, 'systemctl', ['--user', 'enable', 'mosaic-lease-broker.service']);
|
|
||||||
await runChecked(deps, 'systemctl', ['--user', 'start', 'mosaic-lease-broker.service']);
|
|
||||||
}
|
|
||||||
if (needsRunningAgent && plan.holder === 'missing') {
|
if (needsRunningAgent && plan.holder === 'missing') {
|
||||||
await runChecked(deps, 'systemctl', ['--user', 'start', 'mosaic-tmux-holder.service']);
|
await runChecked(deps, 'systemctl', ['--user', 'start', 'mosaic-tmux-holder.service']);
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,3 +1,4 @@
|
|||||||
|
import { existsSync } from 'node:fs';
|
||||||
import { join } from 'node:path';
|
import { join } from 'node:path';
|
||||||
import { homedir, platform } from 'node:os';
|
import { homedir, platform } from 'node:os';
|
||||||
|
|
||||||
@@ -21,18 +22,15 @@ export function getShellProfilePath(): string | null {
|
|||||||
|
|
||||||
const shell = detectShell();
|
const shell = detectShell();
|
||||||
switch (shell) {
|
switch (shell) {
|
||||||
// Both of these deliberately avoid the interactive-only rc files.
|
|
||||||
// Debian's default .bashrc returns early for non-interactive shells, so a
|
|
||||||
// PATH line appended to it never runs for `bash -lc`, systemd units, or
|
|
||||||
// agent seats — an install could report success and still leave `mosaic`
|
|
||||||
// unreachable. .profile is read by login shells and sources .bashrc for
|
|
||||||
// interactive ones, so one line covers both; .zshenv is zsh's equivalent.
|
|
||||||
case 'zsh': {
|
case 'zsh': {
|
||||||
const zdotdir = process.env['ZDOTDIR'] ?? home;
|
const zdotdir = process.env['ZDOTDIR'] ?? home;
|
||||||
return join(zdotdir, '.zshenv');
|
return join(zdotdir, '.zshrc');
|
||||||
}
|
}
|
||||||
case 'bash':
|
case 'bash': {
|
||||||
|
const bashrc = join(home, '.bashrc');
|
||||||
|
if (existsSync(bashrc)) return bashrc;
|
||||||
return join(home, '.profile');
|
return join(home, '.profile');
|
||||||
|
}
|
||||||
case 'fish':
|
case 'fish':
|
||||||
return join(home, '.config', 'fish', 'config.fish');
|
return join(home, '.config', 'fish', 'config.fish');
|
||||||
default:
|
default:
|
||||||
|
|||||||
+15
-293
@@ -309,124 +309,6 @@ require_cmd() {
|
|||||||
fi
|
fi
|
||||||
}
|
}
|
||||||
|
|
||||||
# True if any shell rc file already puts $1 on PATH.
|
|
||||||
#
|
|
||||||
# Each file is tested for existence first and grepped one at a time, rather than
|
|
||||||
# handed to a single `grep -qs ... "${rc_files[@]}"`. Handing grep a missing file
|
|
||||||
# makes the exit status implementation-defined: GNU grep 3.11 returns 0 when -q
|
|
||||||
# matched an earlier file, ugrep 7.5 returns 2 for the missing one regardless.
|
|
||||||
# On the 2 path the caller reads "not present yet" and appends a duplicate PATH
|
|
||||||
# line on every single install.
|
|
||||||
path_entry_exists() {
|
|
||||||
local dir="$1" rc_file
|
|
||||||
for rc_file in "$HOME/.profile" "$HOME/.zshenv" "$HOME/.zshrc" "$HOME/.bashrc"; do
|
|
||||||
if [[ -f "$rc_file" ]] && grep -qF "$dir" "$rc_file"; then
|
|
||||||
return 0
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
return 1
|
|
||||||
}
|
|
||||||
|
|
||||||
# Append `export PATH="$1:$PATH"` to the shell profile so $1 survives this
|
|
||||||
# process. An `export` here reaches only the installer; every directory the
|
|
||||||
# install leaves behind has to be written down somewhere a later shell reads.
|
|
||||||
#
|
|
||||||
# Deliberately NOT ~/.bashrc: Debian's default .bashrc returns early for
|
|
||||||
# non-interactive shells, so a PATH line appended to the bottom of it is
|
|
||||||
# unreachable to `bash -lc`, to systemd units, and to every agent seat — the
|
|
||||||
# exact consumers that need these binaries. ~/.profile is read by login shells
|
|
||||||
# and Debian's .profile sources .bashrc for interactive ones, so a single line
|
|
||||||
# there reaches both. For zsh the always-sourced file is .zshenv, not .zshrc.
|
|
||||||
#
|
|
||||||
# $1 = directory to add, $2 = label for the comment line.
|
|
||||||
# Returns 1 (having warned) if the profile could not be written.
|
|
||||||
persist_on_path() {
|
|
||||||
local dir="$1" label="$2" profile
|
|
||||||
|
|
||||||
if path_entry_exists "$dir"; then
|
|
||||||
return 0
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [[ -n "${ZSH_VERSION:-}" ]] || [[ "$(basename "${SHELL:-}")" == "zsh" ]]; then
|
|
||||||
profile="$HOME/.zshenv"
|
|
||||||
else
|
|
||||||
profile="$HOME/.profile"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Probe writability in a subshell. A redirection failure on a special built-in
|
|
||||||
# aborts the shell it runs in, so it has to be a child; and the redirection on
|
|
||||||
# the subshell is what silences the "Permission denied" the shell would
|
|
||||||
# otherwise print ahead of our own message.
|
|
||||||
if ! ( : >>"$profile" ) 2>/dev/null; then
|
|
||||||
warn "$dir is not on your PATH and $profile could not be written"
|
|
||||||
dim " Add to your shell rc: export PATH=\"$dir:\$PATH\""
|
|
||||||
return 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
{
|
|
||||||
echo ""
|
|
||||||
echo "# $label"
|
|
||||||
echo "export PATH=\"$dir:\$PATH\""
|
|
||||||
} >>"$profile"
|
|
||||||
ok "Added $dir to PATH in $profile"
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# Persist $PREFIX/bin on PATH instead of only warning about it.
|
|
||||||
#
|
|
||||||
# The warning it replaces was the last step of an otherwise successful install,
|
|
||||||
# so the installer reported success and left `mosaic: command not found` — an
|
|
||||||
# unattended install had no operator to read the advice and act on it.
|
|
||||||
ensure_prefix_on_path() {
|
|
||||||
if [[ ":$PATH:" == *":$PREFIX/bin:"* ]]; then
|
|
||||||
return
|
|
||||||
fi
|
|
||||||
|
|
||||||
if path_entry_exists "$PREFIX/bin"; then
|
|
||||||
warn "$PREFIX/bin is in your shell profile but not in this shell"
|
|
||||||
elif ! persist_on_path "$PREFIX/bin" "Mosaic CLI"; then
|
|
||||||
return
|
|
||||||
fi
|
|
||||||
dim " Run: export PATH=\"$PREFIX/bin:\$PATH\" (or start a new login shell)"
|
|
||||||
}
|
|
||||||
|
|
||||||
# Fleet transport binary (#1240).
|
|
||||||
#
|
|
||||||
# `mosaic fleet --help` reads "Manage the local Mosaic tmux fleet" and every
|
|
||||||
# roster the CLI scaffolds sets `transport: tmux`, but nothing in this script
|
|
||||||
# provides tmux and, until now, nothing in it mentioned tmux at all. A
|
|
||||||
# greenfield host came out of this installer able to install a fleet, start a
|
|
||||||
# fleet, and run no seat — the operator's first signal was `mosaic fleet ps`.
|
|
||||||
#
|
|
||||||
# Not a `require_cmd`: tmux is required by the fleet, not by mosaic. Plenty of
|
|
||||||
# hosts install this to run `mosaic claude` and will never scaffold a roster,
|
|
||||||
# and failing their install over a binary they do not need would be wrong. It
|
|
||||||
# is a warning that names precisely what it blocks.
|
|
||||||
#
|
|
||||||
# `tools/_scripts/mosaic-doctor` carries a deliberately parallel check, so the
|
|
||||||
# same host state gets the same answer from an audit as from an install. They
|
|
||||||
# are separate implementations because this one has to work before the
|
|
||||||
# framework's scripts are guaranteed to be on disk; keep their wording in step.
|
|
||||||
check_fleet_transport() {
|
|
||||||
local transport=tmux
|
|
||||||
local roster="$MOSAIC_HOME/fleet/roster.yaml"
|
|
||||||
local declared=""
|
|
||||||
|
|
||||||
if [[ -f "$roster" ]]; then
|
|
||||||
declared="$(sed -n 's/^[[:space:]]*transport:[[:space:]]*//p' "$roster" | head -1 |
|
|
||||||
tr -d '"'\''' | tr -d '\r' | awk '{print $1}')"
|
|
||||||
[[ -n "$declared" ]] && transport="$declared"
|
|
||||||
fi
|
|
||||||
|
|
||||||
command -v "$transport" &>/dev/null && return 0
|
|
||||||
|
|
||||||
warn "Fleet transport '$transport' is not installed."
|
|
||||||
echo " The Mosaic fleet runs its agent seats inside $transport. Without it,"
|
|
||||||
echo " ${C}mosaic fleet start${RESET} reports success and no seat comes up."
|
|
||||||
echo " Install it before using the fleet, e.g. ${C}sudo apt-get install -y $transport${RESET}"
|
|
||||||
echo " (this does not affect ${C}mosaic claude${RESET} or the other single-runtime commands)."
|
|
||||||
}
|
|
||||||
|
|
||||||
installed_cli_version() {
|
installed_cli_version() {
|
||||||
local json
|
local json
|
||||||
json="$(npm ls -g --depth=0 --json --prefix="$PREFIX" 2>/dev/null)" || true
|
json="$(npm ls -g --depth=0 --json --prefix="$PREFIX" 2>/dev/null)" || true
|
||||||
@@ -634,175 +516,8 @@ install_next_cli_from_registry() {
|
|||||||
ok "Installed @next packages: CLI ${installed_cli}, gateway ${installed_gateway}"
|
ok "Installed @next packages: CLI ${installed_cli}, gateway ${installed_gateway}"
|
||||||
}
|
}
|
||||||
|
|
||||||
# ─── node bootstrap ───────────────────────────────────────────────────────────
|
|
||||||
#
|
|
||||||
# Nothing on a greenfield host installs Node.js, yet this installer and the CLI
|
|
||||||
# it installs both hard-require it. Measured on a clean Debian 13 image: the
|
|
||||||
# installer stopped at `require_cmd node` with "Required command not found" and
|
|
||||||
# nothing was installed, with no hint of how to proceed.
|
|
||||||
#
|
|
||||||
# Inlined rather than factored into a sibling file on purpose: this script is
|
|
||||||
# fetched standalone by curl and has nothing to source.
|
|
||||||
#
|
|
||||||
# No-op when a suitable node is already on PATH, so it never fights an
|
|
||||||
# operator's nvm/fnm/distro node.
|
|
||||||
|
|
||||||
NODE_ROOT="${MOSAIC_NODE_ROOT:-$HOME/.mosaic/node}"
|
|
||||||
NODE_BOOTSTRAP_VERSION="${MOSAIC_NODE_VERSION:-v22.23.2}"
|
|
||||||
NODE_MIN_MAJOR="${MOSAIC_NODE_MIN_MAJOR:-20}"
|
|
||||||
NODE_DIST_BASE="${MOSAIC_NODE_DIST_BASE:-https://nodejs.org/dist}"
|
|
||||||
|
|
||||||
# Major version of the node at $1, or empty if it will not run.
|
|
||||||
node_major_of() {
|
|
||||||
local candidate="$1" version
|
|
||||||
version="$("$candidate" -e 'process.stdout.write(process.versions.node)' 2>/dev/null)" || return 0
|
|
||||||
printf '%s' "${version%%.*}"
|
|
||||||
}
|
|
||||||
|
|
||||||
node_is_suitable() {
|
|
||||||
local major
|
|
||||||
major="$(node_major_of "$1")"
|
|
||||||
[[ -n "$major" ]] && [[ "$major" -ge "$NODE_MIN_MAJOR" ]]
|
|
||||||
}
|
|
||||||
|
|
||||||
install_node() {
|
|
||||||
local node_os node_arch tarball release_url work_dir extracted target node_bin
|
|
||||||
|
|
||||||
case "$(uname -s)" in
|
|
||||||
Linux) node_os="linux" ;;
|
|
||||||
Darwin) node_os="darwin" ;;
|
|
||||||
*) fail "Unsupported OS '$(uname -s)'. Install Node.js >= $NODE_MIN_MAJOR manually."; return 1 ;;
|
|
||||||
esac
|
|
||||||
|
|
||||||
# Linux here means glibc. Node's official linux-x64 build is dynamically
|
|
||||||
# linked against glibc, so on musl (Alpine) the binary will not exec — but it
|
|
||||||
# fails visibly: node_is_suitable rejects it and ensure_node exits with
|
|
||||||
# "install Node.js manually". No silent breakage, just a wasted download.
|
|
||||||
# A musl host needs the unofficial build, which is out of scope here.
|
|
||||||
case "$(uname -m)" in
|
|
||||||
x86_64|amd64) node_arch="x64" ;;
|
|
||||||
aarch64|arm64) node_arch="arm64" ;;
|
|
||||||
armv7l) node_arch="armv7l" ;;
|
|
||||||
*) fail "Unsupported architecture '$(uname -m)'. Install Node.js >= $NODE_MIN_MAJOR manually."; return 1 ;;
|
|
||||||
esac
|
|
||||||
|
|
||||||
# .tar.gz rather than the smaller .tar.xz: gzip is universally present, xz is
|
|
||||||
# not, and a minimal image is exactly the case this exists to handle.
|
|
||||||
tarball="node-${NODE_BOOTSTRAP_VERSION}-${node_os}-${node_arch}.tar.gz"
|
|
||||||
release_url="${NODE_DIST_BASE}/${NODE_BOOTSTRAP_VERSION}"
|
|
||||||
|
|
||||||
work_dir="$(mktemp -d "${TMPDIR:-/tmp}/mosaic-node-XXXXXX")"
|
|
||||||
|
|
||||||
info "Installing Node.js $NODE_BOOTSTRAP_VERSION ($node_os-$node_arch) to $NODE_ROOT…"
|
|
||||||
|
|
||||||
if ! curl -fsSL "${release_url}/${tarball}" -o "$work_dir/$tarball"; then
|
|
||||||
fail "Download failed: ${release_url}/${tarball}"
|
|
||||||
rm -rf "$work_dir"; return 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Trust assumption, stated so nobody has to infer it: this verifies INTEGRITY
|
|
||||||
# (the tarball matches the manifest), not AUTHENTICITY (the manifest is
|
|
||||||
# genuinely Node's). The only thing establishing that is TLS to
|
|
||||||
# $NODE_DIST_BASE. Node publishes SHASUMS256.txt.sig signed by its release
|
|
||||||
# keys and we do not check it, which is on par with nvm but means pointing
|
|
||||||
# MOSAIC_NODE_DIST_BASE at an untrusted mirror has no signature backstop.
|
|
||||||
# Tracked as a hardening follow-up (raised by scooby in the #1229 review).
|
|
||||||
if ! curl -fsSL "${release_url}/SHASUMS256.txt" -o "$work_dir/SHASUMS256.txt"; then
|
|
||||||
fail "Could not fetch SHASUMS256.txt; refusing to install an unverified runtime."
|
|
||||||
rm -rf "$work_dir"; return 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Keep only our artifact's line, so a missing entry is an error not a pass.
|
|
||||||
if ! grep " ${tarball}\$" "$work_dir/SHASUMS256.txt" >"$work_dir/expected.sha256"; then
|
|
||||||
fail "$tarball has no entry in SHASUMS256.txt; refusing to install."
|
|
||||||
rm -rf "$work_dir"; return 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
if ! (cd "$work_dir" && verify_sha256 expected.sha256); then
|
|
||||||
fail "Checksum mismatch for $tarball; refusing to install."
|
|
||||||
rm -rf "$work_dir"; return 1
|
|
||||||
fi
|
|
||||||
ok "Checksum verified"
|
|
||||||
|
|
||||||
tar xzf "$work_dir/$tarball" -C "$work_dir"
|
|
||||||
extracted="$work_dir/node-${NODE_BOOTSTRAP_VERSION}-${node_os}-${node_arch}"
|
|
||||||
if [[ ! -x "$extracted/bin/node" ]]; then
|
|
||||||
fail "Extracted archive has no bin/node"
|
|
||||||
rm -rf "$work_dir"; return 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
mkdir -p "$NODE_ROOT"
|
|
||||||
target="$NODE_ROOT/$NODE_BOOTSTRAP_VERSION"
|
|
||||||
rm -rf "$target.incoming"
|
|
||||||
mv "$extracted" "$target.incoming"
|
|
||||||
rm -rf "$target"
|
|
||||||
mv "$target.incoming" "$target"
|
|
||||||
ln -sfn "$NODE_BOOTSTRAP_VERSION" "$NODE_ROOT/current"
|
|
||||||
rm -rf "$work_dir"
|
|
||||||
|
|
||||||
node_bin="$NODE_ROOT/current/bin"
|
|
||||||
if ! node_is_suitable "$node_bin/node"; then
|
|
||||||
fail "Installed node at $node_bin/node did not run"
|
|
||||||
return 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
export PATH="$node_bin:$PATH"
|
|
||||||
ok "Node.js $(node -v) installed with npm $(npm -v 2>/dev/null || echo '?')"
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# Make the Mosaic-managed Node reachable from the next shell as well as this
|
|
||||||
# one. Measured on a greenfield canary run: without this the install finished
|
|
||||||
# rc=0, wrote $PREFIX/bin to ~/.profile, and the next login shell found `mosaic`
|
|
||||||
# and then died on `env: 'node': No such file or directory` — the CLI is a Node
|
|
||||||
# script, so a CLI on PATH without its runtime is a successful install that
|
|
||||||
# produces a broken command.
|
|
||||||
persist_node_on_path() {
|
|
||||||
persist_on_path "$NODE_ROOT/current/bin" "Mosaic-managed Node.js" || true
|
|
||||||
}
|
|
||||||
|
|
||||||
ensure_node() {
|
|
||||||
if command -v node &>/dev/null && node_is_suitable node; then
|
|
||||||
return 0
|
|
||||||
fi
|
|
||||||
|
|
||||||
# A previous run may have installed one that is not on this shell's PATH.
|
|
||||||
if node_is_suitable "$NODE_ROOT/current/bin/node"; then
|
|
||||||
export PATH="$NODE_ROOT/current/bin:$PATH"
|
|
||||||
persist_node_on_path
|
|
||||||
return 0
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [[ "${MOSAIC_SKIP_NODE_BOOTSTRAP:-0}" == "1" ]]; then
|
|
||||||
fail "No suitable Node.js and MOSAIC_SKIP_NODE_BOOTSTRAP=1; refusing to download."
|
|
||||||
echo " Install Node.js >= $NODE_MIN_MAJOR yourself, then re-run this script."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
require_cmd curl
|
|
||||||
require_cmd tar
|
|
||||||
|
|
||||||
# sha256sum on Linux, shasum on macOS. Verification is not optional: without a
|
|
||||||
# checksum this would install an unauthenticated runtime.
|
|
||||||
if command -v sha256sum &>/dev/null; then
|
|
||||||
verify_sha256() { sha256sum -c --status "$1"; }
|
|
||||||
elif command -v shasum &>/dev/null; then
|
|
||||||
verify_sha256() { shasum -a 256 -c --status "$1"; }
|
|
||||||
else
|
|
||||||
fail "sha256sum or shasum required to verify the Node.js download"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
if ! install_node; then
|
|
||||||
fail "Could not bootstrap Node.js. Install Node.js >= $NODE_MIN_MAJOR and re-run."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
persist_node_on_path
|
|
||||||
}
|
|
||||||
|
|
||||||
# ─── preflight ────────────────────────────────────────────────────────────────
|
# ─── preflight ────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
ensure_node
|
|
||||||
require_cmd node
|
require_cmd node
|
||||||
require_cmd npm
|
require_cmd npm
|
||||||
|
|
||||||
@@ -967,7 +682,11 @@ if [[ "$FLAG_CLI" == "true" ]]; then
|
|||||||
ensure_monorepo
|
ensure_monorepo
|
||||||
install_cli_from_source
|
install_cli_from_source
|
||||||
|
|
||||||
ensure_prefix_on_path
|
# PATH check for npm prefix
|
||||||
|
if [[ ":$PATH:" != *":$PREFIX/bin:"* ]]; then
|
||||||
|
warn "$PREFIX/bin is not on your PATH"
|
||||||
|
dim " Add to your shell rc: export PATH=\"$PREFIX/bin:\$PATH\""
|
||||||
|
fi
|
||||||
elif is_next_registry_lane; then
|
elif is_next_registry_lane; then
|
||||||
info "Next mode — trying fast npm @next install from ${REGISTRY}…"
|
info "Next mode — trying fast npm @next install from ${REGISTRY}…"
|
||||||
if install_next_cli_from_registry; then
|
if install_next_cli_from_registry; then
|
||||||
@@ -980,7 +699,11 @@ if [[ "$FLAG_CLI" == "true" ]]; then
|
|||||||
export MOSAIC_GATEWAY_SKIP_NPM_INSTALL=1
|
export MOSAIC_GATEWAY_SKIP_NPM_INSTALL=1
|
||||||
fi
|
fi
|
||||||
|
|
||||||
ensure_prefix_on_path
|
# PATH check for npm prefix
|
||||||
|
if [[ ":$PATH:" != *":$PREFIX/bin:"* ]]; then
|
||||||
|
warn "$PREFIX/bin is not on your PATH"
|
||||||
|
dim " Add to your shell rc: export PATH=\"$PREFIX/bin:\$PATH\""
|
||||||
|
fi
|
||||||
else
|
else
|
||||||
if [[ -z "$LATEST" ]]; then
|
if [[ -z "$LATEST" ]]; then
|
||||||
warn "Could not reach registry at $REGISTRY — skipping npm CLI."
|
warn "Could not reach registry at $REGISTRY — skipping npm CLI."
|
||||||
@@ -998,7 +721,11 @@ if [[ "$FLAG_CLI" == "true" ]]; then
|
|||||||
ok "CLI is at or ahead of registry ($CURRENT ≥ $LATEST)."
|
ok "CLI is at or ahead of registry ($CURRENT ≥ $LATEST)."
|
||||||
fi
|
fi
|
||||||
|
|
||||||
ensure_prefix_on_path
|
# PATH check for npm prefix
|
||||||
|
if [[ ":$PATH:" != *":$PREFIX/bin:"* ]]; then
|
||||||
|
warn "$PREFIX/bin is not on your PATH"
|
||||||
|
dim " Add to your shell rc: export PATH=\"$PREFIX/bin:\$PATH\""
|
||||||
|
fi
|
||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
@@ -1143,11 +870,6 @@ if [[ "$FLAG_CHECK" == "false" ]]; then
|
|||||||
ok "Done."
|
ok "Done."
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Fleet readiness (#1240). Runs in both normal and --check mode: "what is the
|
|
||||||
# state of this host" is exactly the question --check is asked, and a host that
|
|
||||||
# cannot run a seat should not have to discover it from `fleet ps`.
|
|
||||||
check_fleet_transport
|
|
||||||
|
|
||||||
} # end main
|
} # end main
|
||||||
|
|
||||||
main "$@"
|
main "$@"
|
||||||
|
|||||||
Reference in New Issue
Block a user