diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml
new file mode 100644
index 0000000..aeca6a8
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/config.yml
@@ -0,0 +1,8 @@
+blank_issues_enabled: false
+contact_links:
+ - name: Design docs
+ url: https://git.produktor.io/eSlider/swarm-house/src/branch/main/docs/12-design-journey.md
+ about: Start with the design journey, then open an issue here.
+ - name: Open questions
+ url: https://git.produktor.io/eSlider/swarm-house/src/branch/main/docs/09-open-questions.md
+ about: Known unknowns — check before duplicating.
diff --git a/.github/ISSUE_TEMPLATE/default.md b/.github/ISSUE_TEMPLATE/default.md
new file mode 100644
index 0000000..0b6b8fe
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/default.md
@@ -0,0 +1,24 @@
+---
+name: Change / task
+about: Default issue template — caveman style
+title: ""
+labels: []
+---
+
+Write **caveman-full**: short lines, fragments OK, no filler. See [`CONTRIBUTING.md`](../../CONTRIBUTING.md#caveman-style-default).
+
+## What
+
+
+
+## Why
+
+
+
+## Done when
+
+- [ ]
+
+## Notes
+
+
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
new file mode 100644
index 0000000..fda7e31
--- /dev/null
+++ b/.github/pull_request_template.md
@@ -0,0 +1,19 @@
+Write **caveman-full** by default. See [`CONTRIBUTING.md`](../CONTRIBUTING.md#caveman-style-default).
+
+## What
+
+
+
+## Why
+
+
+
+## Test
+
+- [ ] `pytest tests/ -q` (if code touched)
+- [ ] `python bin/check_docs.py` (if docs touched)
+- [ ] ADR added if boundary/contract changed
+
+## Links
+
+
diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml
index ba20cd3..060406d 100644
--- a/.github/workflows/release.yaml
+++ b/.github/workflows/release.yaml
@@ -1,4 +1,5 @@
# Swarm House - Gitea Actions
+# docs-verify: markdown links, glossary anchors, readability rules (every push/PR)
# verify: compile check, virtual-drone smoke flight, SQL gate tests (every push/PR)
# scan: Trivy vulnerability + misconfiguration scan
# release: semantic version bump (conventional commits), tag, Gitea release
@@ -17,6 +18,27 @@ on:
branches: [main]
jobs:
+ docs-verify:
+ name: Verify documentation
+ runs-on: ubuntu-latest
+ container: python:3.12-bookworm
+ steps:
+ - name: Checkout
+ run: |
+ git init .
+ git remote add origin https://${{ gitea.actor }}:${{ gitea.token }}@git.produktor.io/${{ gitea.repository }}.git
+ git fetch --depth=50 origin "${{ gitea.ref }}"
+ git checkout FETCH_HEAD
+
+ - name: Fetch base branch for ADR immutability
+ run: git fetch --depth=1 origin main
+
+ - name: ADR immutability (no edits to accepted records)
+ run: python bin/check_adrs.py --base origin/main
+
+ - name: Documentation rules (links, glossary, readability)
+ run: python bin/check_docs.py
+
verify:
name: Verify simulator
runs-on: ubuntu-latest
@@ -24,8 +46,10 @@ jobs:
steps:
- name: Checkout
run: |
- git clone --depth=50 https://${{ gitea.actor }}:${{ gitea.token }}@git.produktor.io/${{ gitea.repository }}.git .
- git checkout ${{ gitea.sha }}
+ git init .
+ git remote add origin https://${{ gitea.actor }}:${{ gitea.token }}@git.produktor.io/${{ gitea.repository }}.git
+ git fetch --depth=50 origin "${{ gitea.ref }}"
+ git checkout FETCH_HEAD
- name: Install dependencies
run: pip install --quiet -r simulator/requirements.txt
@@ -61,8 +85,10 @@ jobs:
steps:
- name: Checkout
run: |
- git clone --depth=1 https://${{ gitea.actor }}:${{ gitea.token }}@git.produktor.io/${{ gitea.repository }}.git .
- git checkout ${{ gitea.sha }}
+ git init .
+ git remote add origin https://${{ gitea.actor }}:${{ gitea.token }}@git.produktor.io/${{ gitea.repository }}.git
+ git fetch --depth=1 origin "${{ gitea.ref }}"
+ git checkout FETCH_HEAD
- name: Install Trivy
run: |
@@ -81,7 +107,7 @@ jobs:
name: Semantic Release
runs-on: ubuntu-latest
container: python:3.12-bookworm
- needs: [verify, scan]
+ needs: [docs-verify, verify, scan]
if: gitea.event_name == 'push'
permissions:
contents: write
diff --git a/AGENTS.md b/AGENTS.md
index f110b52..1036ef2 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -24,6 +24,23 @@ See [`CONTRIBUTING.md`](CONTRIBUTING.md) for the development workflow and TDD re
## Conventions
+### Caveman style (default for collaboration)
+
+**Issues, pull requests, and code reviews** use **caveman-full** by default:
+
+- Short sentences or fragments; drop articles and filler when clear
+- Lead with fact, verdict, or ask — not preamble
+- Bullets over paragraphs; one idea per line
+- Keep technical terms, acronyms, paths, and code exact
+- English only; no identifying references (same as all repo prose)
+
+README tiers: root [`README.md`](README.md) = **caveman-lite** (full sentences, less filler);
+component READMEs = **caveman-full**. Design docs in `docs/` stay readable prose unless
+editing for consistency.
+
+Templates: [`.github/ISSUE_TEMPLATE/`](.github/ISSUE_TEMPLATE/),
+[`.github/pull_request_template.md`](.github/pull_request_template.md).
+
- Markdown: ATX headings, fenced code blocks with language tags, pipe tables.
- Python: PEP 8, type hints, pure functions where possible, no unnecessary classes.
- TypeScript: strict mode, functional components and hooks, no extra UI libraries.
@@ -44,7 +61,12 @@ Status / Context / Options / Decision / Consequences format. Start from
When a change alters a boundary, contract, or trade-off, add an ADR (copy
[`docs/adr/TEMPLATE.md`](docs/adr/TEMPLATE.md), take the next number, update the
index) and cross-link it from the affected design doc. A later reversal gets a
-new ADR that supersedes the old one — never edit an Accepted record.
+new ADR that supersedes the old one — **never edit an Accepted record**.
+
+**Immutable:** every `docs/adr/ADR-*.md` file is frozen once on `main`. CI rejects
+any change that modifies an existing ADR. Updates go in a new numbered ADR only.
+The index ([`docs/adr/README.md`](docs/adr/README.md)) and [`TEMPLATE.md`](docs/adr/TEMPLATE.md)
+may still change; decision bodies do not.
## Runtime & operations (sim environment)
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index db66de9..1692b18 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -17,6 +17,7 @@ The CI pipeline enforces this:
| Gate | When it runs |
| --- | --- |
+| `python bin/check_docs.py` | Every push/PR (`docs-verify` job) — links, glossary anchors, readability rules ([ci-rules](docs/improvement/ci-rules.md)) |
| `pytest tests/` | Every push/PR (`verify` job) |
| `RUN pytest tests/` in the simulator Docker build | Every `docker build` — a red test blocks the image |
| Smoke flight + DuckDB assertion | Every push/PR |
@@ -76,12 +77,47 @@ test: cover broadcast frame roundtrip
Never include AI tool references, `Co-authored-by` trailers for assistants, or
identifying names of people, companies, or locations.
+## Caveman style (default)
+
+Use **caveman-full** in **issues**, **pull requests**, and **reviews** unless the
+author explicitly asks otherwise.
+
+| Do | Skip |
+| --- | --- |
+| Short lines, fragments OK | Long preamble ("I wanted to start by saying…") |
+| Lead with what / why / verdict | Filler ("just", "basically", "kind of") |
+| Bullets, checklists | Repeated context already in diff or issue |
+| Exact terms, paths, code | Invented abbreviations or vague "the thing" |
+
+**Examples**
+
+| Fluffy | Caveman |
+| --- | --- |
+| I think we should probably consider adding a link checker to CI because links might break. | Add CI link checker. Broken relative links fail merge. |
+| This pull request implements the documentation improvements that were discussed in the audit. | Docs audit: glossary T0–T4, fix ground README link, rsync wording. |
+| LGTM but maybe we could think about whether the anchor format is consistent? | Merge OK. Fix glossary anchors in follow-up (#1). |
+
+README intensity: root = caveman-lite; `simulator/`, `prototype/`, `infra/`, `docs/adr/` READMEs =
+caveman-full. Numbered design docs in `docs/` stay full prose.
+
+Gitea pre-fills [issue](.github/ISSUE_TEMPLATE/default.md) and
+[PR](.github/pull_request_template.md) templates with this style.
+
+### Reviews
+
+Default review voice = caveman-full:
+
+1. **Verdict first** — merge / wait / no, or approve / request changes
+2. **Findings** — bullet per blocker or nit; file + line when useful
+3. **Scope** — say if issue AC met, partial, or out of scope
+4. No essay; link ADR, issue, or doc section instead of restating design
+
## Pull request checklist
- [ ] Tests added or updated; `pytest tests/ -q` passes locally
- [ ] `docker build` in `simulator/` succeeds (test stage included)
- [ ] Documentation updated if behaviour or boundaries changed
-- [ ] **ADR added** if the change alters an architectural boundary, contract, or trade-off (see [`docs/adr/`](docs/adr/))
+- [ ] **ADR added** if the change alters an architectural boundary, contract, or trade-off (see [`docs/adr/`](docs/adr/)) — never edit an existing `ADR-*.md`; supersede with a new number
- [ ] English only; no identifying references
- [ ] Conventional commit message
diff --git a/README.md b/README.md
index 7ca6989..8db51b1 100644
--- a/README.md
+++ b/README.md
@@ -2,9 +2,14 @@
**An on-prem data platform for autonomous drone swarms** — a design proposal from a DevOps perspective.
-A fleet of drones flies fully autonomously: no internet uplink, no external access, all data stays inside the swarm. Each drone collects high-rate sensor telemetry and runs on-board video object detection. The swarm must exchange just enough state to coordinate flight, store everything else locally, and hand its data over to a ground warehouse after landing — reproducibly, securely, and at scale.
+Fleet flies autonomous. No internet uplink, no external access. Data stays in the swarm. Each drone collects high-rate sensor telemetry and runs on-board video object detection. Swarm exchanges just enough state to coordinate; everything else stays local until a ground warehouse receives it after landing — reproducibly, securely, at scale.
-This repository describes how to build, deliver, test, and operate that platform: the storage layout, the sync strategy, the network trust model, the CI/CD chain, and the simulation environment that makes it all testable without touching real hardware.
+This repository covers storage layout, sync strategy, network trust model, CI/CD chain, and the simulation environment that tests it without real hardware.
+
+> **Restricted use.** Third parties may not use, copy, modify, or distribute this
+> source code, documentation, or related materials without **explicit written
+> permission** from the copyright holder. No license is granted by default. See
+> [LICENSE](LICENSE) for the full terms.
## Design principles
@@ -24,7 +29,7 @@ This repository describes how to build, deliver, test, and operate that platform
| [00 — Glossary](docs/00-glossary.md) | Terms and abbreviations used throughout |
| [01 — Problem statement](docs/01-problem-statement.md) | Goal, constraints, knowns vs assumptions |
| [02 — Architecture](docs/02-architecture.md) | On-board layers, service composition, communication planes |
-| [03 — Data platform](docs/03-data-platform.md) | Parquet/DuckDB storage tiers, partitioning, hot-write path |
+| [03 — Data platform](docs/03-data-platform.md) | Parquet/DuckDB storage floors (T0–T4), partitioning, hot-write path |
| [04 — Swarm sync](docs/04-swarm-sync.md) | What syncs, what does not, pub/sub transport, query standard |
| [05 — Network & security](docs/05-network-security.md) | Zero-trust mesh, key provisioning, encrypted transport |
| [06 — Environments](docs/06-environments.md) | Drone / ground warehouse / dev-simulation infrastructures |
@@ -36,7 +41,7 @@ This repository describes how to build, deliver, test, and operate that platform
| [12 — Design journey](docs/12-design-journey.md) | **Start here** — a narrative walk-through of how the design came together, linking into the code |
| [ADRs](docs/adr/) | Architecture Decision Records — the decisions behind the above, in the order they were made |
-New here? Read the [design journey](docs/12-design-journey.md) first: it tells the story chronologically and links straight into the code and decisions. The design principles below are the *what*; the [ADRs](docs/adr/) are the *why and when* — each principle traces to a dated, immutable decision record.
+New? Start with the [design journey](docs/12-design-journey.md) — story plus code links. Principles = *what*; [ADRs](docs/adr/) = *why and when*.
## Runnable parts
@@ -45,10 +50,10 @@ New here? Read the [design journey](docs/12-design-journey.md) first: it tells t
| [`simulator/`](simulator/) | Virtual drone fleet: generates realistic telemetry through the same Parquet/DuckDB pipeline a real drone would use; N drones via Docker Compose | Python, pyarrow, DuckDB |
| [`prototype/`](prototype/) | 2D top-down swarm visualization: drones, obstacles, inter-drone links with live transfer metrics; **live mode** renders real positions from the k3d fleet | React, TypeScript, Vite, SVG |
| [`infra/ansible/`](infra/ansible/) | Host preparation: drone bench provisioning (keys, forced commands, WireGuard, Compose bundle) and local k3d simulation cluster | Ansible |
-| [`infra/terraform/`](infra/terraform/) | Declared workloads on the sim cluster: virtual fleet + observability ([`sim-env`](infra/terraform/sim-env/)), warehouse + T1→T3 offload ([`ground`](infra/terraform/ground/)) | Terraform, kubernetes provider |
+| [`infra/terraform/`](infra/terraform/) | Declared workloads on the sim cluster: virtual fleet + observability ([`sim-env`](infra/terraform/sim-env/)), warehouse + [T1→T3](docs/03-data-platform.md#storage-floors-tiers) offload ([`ground`](infra/terraform/ground/)) | Terraform, kubernetes provider |
| [`infra/gitops/`](infra/gitops/) | Flux overlays for the ground segment — policy labels, dashboard bundles; drones stay on the fleet manifest | Flux, Kustomize |
-Shared runtime data (gitignored): `var/t1/` (live lake), `var/t3/` (warehouse). See [`CONTRIBUTING.md`](CONTRIBUTING.md).
+Shared runtime data (gitignored): [`var/t1/`](docs/00-glossary.md#t1--warm) (live lake, [T1](docs/00-glossary.md#t1--warm)), [`var/t3/`](docs/00-glossary.md#t3--warehouse) (warehouse, [T3](docs/00-glossary.md#t3--warehouse)). See [`CONTRIBUTING.md`](CONTRIBUTING.md).
## Quick start
diff --git a/bin/check_adrs.py b/bin/check_adrs.py
new file mode 100644
index 0000000..f27db7f
--- /dev/null
+++ b/bin/check_adrs.py
@@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+"""Reject modifications to accepted Architecture Decision Records."""
+
+from __future__ import annotations
+
+import argparse
+import subprocess
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+ADR_PREFIX = "docs/adr/ADR-"
+
+
+def _git(*args: str) -> str:
+ return subprocess.check_output(
+ ["git", *args],
+ cwd=ROOT,
+ text=True,
+ stderr=subprocess.DEVNULL,
+ ).strip()
+
+
+def _exists_on(base: str, path: str) -> bool:
+ try:
+ _git("cat-file", "-e", f"{base}:{path}")
+ return True
+ except subprocess.CalledProcessError:
+ return False
+
+
+def find_modified_adrs(base: str) -> list[str]:
+ try:
+ diff_out = _git("diff", "--name-only", f"{base}...HEAD", "--", "docs/adr/")
+ except subprocess.CalledProcessError:
+ return []
+
+ modified: list[str] = []
+ for rel in diff_out.splitlines():
+ if not rel.startswith(ADR_PREFIX) or not rel.endswith(".md"):
+ continue
+ if _exists_on(base, rel):
+ modified.append(rel)
+ return sorted(modified)
+
+
+def run_check(base: str = "origin/main") -> int:
+ modified = find_modified_adrs(base)
+ if modified:
+ print("Immutable ADR violation — accepted records cannot be edited:")
+ for path in modified:
+ print(f" error: {path}")
+ print(
+ "\nReversal or refinement → new ADR-NNNN file. "
+ "Never edit an existing ADR-*.md."
+ )
+ return 1
+
+ print(f"ADR immutability OK (base {base})")
+ return 0
+
+
+def main() -> None:
+ parser = argparse.ArgumentParser(description=__doc__)
+ parser.add_argument(
+ "--base",
+ default="origin/main",
+ help="Git ref to compare against (default: origin/main)",
+ )
+ args = parser.parse_args()
+ sys.exit(run_check(base=args.base))
+
+
+if __name__ == "__main__":
+ main()
diff --git a/bin/check_docs.py b/bin/check_docs.py
new file mode 100644
index 0000000..1cb64b0
--- /dev/null
+++ b/bin/check_docs.py
@@ -0,0 +1,212 @@
+#!/usr/bin/env python3
+"""Validate markdown links, glossary anchors, and readability rules."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import re
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+RULES_PATH = Path(__file__).with_name("docs_rules.json")
+
+LINK_RE = re.compile(r"!?\[[^\]]*\]\(([^)]+)\)")
+BARE_SEE_RE = re.compile(r"(? dict:
+ return json.loads(path.read_text(encoding="utf-8"))
+
+
+def slug_heading(text: str) -> str:
+ """Anchor slug used in this repository's glossary links."""
+ text = text.strip()
+ text = re.sub(r"\s&\s", " — ", text)
+ if " — " in text:
+ left, right = text.split(" — ", 1)
+ return f"{_slug_part(left)}--{_slug_part(right)}"
+ return _slug_part(text)
+
+
+def _slug_part(text: str) -> str:
+ slug = text.strip().lower()
+ slug = re.sub(r"[^\w\s-]", "", slug)
+ slug = re.sub(r"\s+", "-", slug)
+ return slug
+
+
+def collect_anchors(md_path: Path) -> set[str]:
+ anchors: set[str] = set()
+ for line in md_path.read_text(encoding="utf-8").splitlines():
+ if line.startswith("##"):
+ anchors.add(slug_heading(line.lstrip("#").strip()))
+ return anchors
+
+
+def expand_markdown_paths(patterns: list[str]) -> list[Path]:
+ files: set[Path] = set()
+ for pattern in patterns:
+ for path in ROOT.glob(pattern):
+ if path.is_file() and path.suffix == ".md":
+ files.add(path)
+ return sorted(files)
+
+
+def split_link_target(raw: str) -> tuple[str, str | None]:
+ target = raw.strip()
+ if target.startswith("<") and target.endswith(">"):
+ target = target[1:-1]
+ if "#" in target:
+ path_part, fragment = target.split("#", 1)
+ return path_part, fragment or None
+ return target, None
+
+
+def resolve_path(source: Path, link_path: str) -> Path | None:
+ if not link_path or link_path.startswith(SKIP_SCHEMES):
+ return None
+ candidate = (source.parent / link_path).resolve()
+ try:
+ candidate.relative_to(ROOT.resolve())
+ except ValueError:
+ return None
+ return candidate
+
+
+def is_glossary_link(link_path: str, rules: dict) -> bool:
+ glossary = rules["glossary"]["file"].replace("\\", "/")
+ normalized = link_path.replace("\\", "/")
+ return (
+ normalized == glossary
+ or normalized.endswith("/" + glossary)
+ or normalized.endswith(glossary.split("/")[-1])
+ )
+
+
+def check_file(
+ md_path: Path,
+ rules: dict,
+ anchor_cache: dict[Path, set[str]],
+) -> tuple[list[str], list[str]]:
+ errors: list[str] = []
+ warnings: list[str] = []
+ rel = md_path.relative_to(ROOT)
+ text = md_path.read_text(encoding="utf-8")
+
+ if rules.get("readability", {}).get("forbid_bare_see_refs"):
+ prose = re.sub(r"`[^`]*`", "", text)
+ for match in BARE_SEE_RE.finditer(prose):
+ errors.append(
+ f"{rel}:{_line_no(text, match.start())}: bare cross-ref "
+ f"'see {match.group(1)}' — use a markdown link"
+ )
+
+ for match in LINK_RE.finditer(text):
+ raw = match.group(1)
+ if any(raw.startswith(s) for s in SKIP_SCHEMES):
+ continue
+
+ link_path, fragment = split_link_target(raw)
+ if not link_path.endswith(".md"):
+ continue
+
+ for banned in rules.get("banned_link_targets", []):
+ if banned in link_path.replace("\\", "/"):
+ errors.append(
+ f"{rel}:{_line_no(text, match.start())}: banned link target "
+ f"'{link_path}'"
+ )
+
+ target = resolve_path(md_path, link_path)
+ if target is None:
+ errors.append(
+ f"{rel}:{_line_no(text, match.start())}: link escapes repo or "
+ f"is invalid: {raw}"
+ )
+ continue
+ if not target.is_file():
+ errors.append(
+ f"{rel}:{_line_no(text, match.start())}: broken link "
+ f"{link_path} -> {target.relative_to(ROOT)}"
+ )
+ continue
+
+ if fragment:
+ if target not in anchor_cache:
+ anchor_cache[target] = collect_anchors(target)
+ if fragment not in anchor_cache[target]:
+ errors.append(
+ f"{rel}:{_line_no(text, match.start())}: unknown anchor "
+ f"#{fragment} in {target.relative_to(ROOT)}"
+ )
+
+ if fragment and is_glossary_link(link_path, rules):
+ section_anchors = set(rules.get("glossary_section_anchors", []))
+ if fragment in section_anchors:
+ warnings.append(
+ f"{rel}:{_line_no(text, match.start())}: glossary section "
+ f"link #{fragment} — prefer a ### term anchor where one exists"
+ )
+
+ return errors, warnings
+
+
+def _line_no(text: str, index: int) -> int:
+ return text.count("\n", 0, index) + 1
+
+
+def run_checks(warnings_as_errors: bool = False) -> int:
+ rules = load_rules(RULES_PATH)
+ anchor_cache: dict[Path, set[str]] = {}
+ all_errors: list[str] = []
+ all_warnings: list[str] = []
+
+ glossary_path = ROOT / rules["glossary"]["file"]
+ anchor_cache[glossary_path] = collect_anchors(glossary_path)
+
+ for md_path in expand_markdown_paths(rules["markdown_paths"]):
+ errors, warnings = check_file(md_path, rules, anchor_cache)
+ all_errors.extend(errors)
+ all_warnings.extend(warnings)
+
+ if all_warnings:
+ print("Documentation warnings:")
+ for msg in sorted(all_warnings):
+ print(f" warning: {msg}")
+ print()
+
+ if all_errors:
+ print("Documentation errors:")
+ for msg in sorted(all_errors):
+ print(f" error: {msg}")
+ print(f"\n{len(all_errors)} error(s), {len(all_warnings)} warning(s)")
+ return 1
+
+ if warnings_as_errors and all_warnings:
+ print(f"\n{len(all_warnings)} warning(s) treated as errors")
+ return 1
+
+ print(
+ f"Documentation checks passed "
+ f"({len(expand_markdown_paths(rules['markdown_paths']))} files, "
+ f"{len(all_warnings)} warning(s))"
+ )
+ return 0
+
+
+def main() -> None:
+ parser = argparse.ArgumentParser(description=__doc__)
+ parser.add_argument(
+ "--warnings-as-errors",
+ action="store_true",
+ help="Exit non-zero when section-link warnings are present",
+ )
+ args = parser.parse_args()
+ sys.exit(run_checks(warnings_as_errors=args.warnings_as_errors))
+
+
+if __name__ == "__main__":
+ main()
diff --git a/bin/docs_rules.json b/bin/docs_rules.json
new file mode 100644
index 0000000..38aa906
--- /dev/null
+++ b/bin/docs_rules.json
@@ -0,0 +1,42 @@
+{
+ "markdown_paths": [
+ "docs/**/*.md",
+ "README.md",
+ "CONTRIBUTING.md",
+ "AGENTS.md",
+ "simulator/README.md",
+ "prototype/README.md",
+ "infra/**/README.md"
+ ],
+ "glossary": {
+ "file": "docs/00-glossary.md"
+ },
+ "banned_link_targets": [
+ "03-storage-design.md"
+ ],
+ "glossary_section_anchors": [
+ "data--storage",
+ "swarm--robotics",
+ "infrastructure--delivery"
+ ],
+ "preferred_term_anchors": [
+ "t0--hot",
+ "t1--warm",
+ "t2--shared",
+ "t3--warehouse",
+ "t4--dev",
+ "source-of-truth",
+ "architecture-layer-1--ingestion",
+ "architecture-layer-2--storage-and-transform",
+ "architecture-layer-3--serving-and-sync",
+ "pipeline-stage",
+ "bulk-sync",
+ "offload",
+ "rclone",
+ "adr",
+ "asr"
+ ],
+ "readability": {
+ "forbid_bare_see_refs": true
+ }
+}
diff --git a/docs/00-glossary.md b/docs/00-glossary.md
index e7fc14b..25cbdaa 100644
--- a/docs/00-glossary.md
+++ b/docs/00-glossary.md
@@ -2,6 +2,70 @@
Terms and abbreviations used throughout this proposal.
+**Vocabulary guide:** **architecture layers** (1–3) = on-board software stack; **storage floors** (T0–T4) = retention/latency ladder; **pipeline stages** = narrative capture → reduction → sync only ([12 — Design journey](12-design-journey.md) §4). Do not mix these three.
+
+## Project vocabulary
+
+### T0 — hot
+
+RAM / DuckDB in-process sliding window of the last minutes; what mission logic queries in flight. Retention: minutes. Maps to **hot** in the classic three-tier model.
+
+### T1 — warm
+
+Drone NVMe: full raw `telemetry` + `detections` + `state` of the current flight; never leaves the drone in flight. Retention: current flight plus quota-based headroom. Maps to **warm**. Runtime path: [`var/t1/`](../var/t1/) ([ADR-0008](adr/ADR-0008-runtime-data-paths.md)).
+
+### T2 — shared
+
+On-board MinIO bucket: derived data only (`detections`, `state`), replicated opportunistically across the swarm. Retention: current mission.
+
+### T3 — warehouse
+
+Ground on-prem object store + Parquet lakehouse: every flight of every drone, forever; replay, analytics, model training. Retention: years. Maps to **cold** / **DWH**. Runtime path: [`var/t3/`](../var/t3/) ([ADR-0008](adr/ADR-0008-runtime-data-paths.md)). After offload and integrity audit, T3 is the [source of truth](#source-of-truth) for historical flight data.
+
+### T4 — dev
+
+Engineer laptop or sim farm: slices pulled from T3, or synthetic data from the simulator. Retention: ephemeral.
+
+### Source of truth
+
+The authoritative copy of flight data after [offload](#offload) and integrity audit: the [T3](#t3--warehouse) warehouse. Each drone holds its own partial record in flight ([T1](#t1--warm)); peers exchange derived state only ([04 — Swarm sync](04-swarm-sync.md)). Replay, post-flight fusion, training, and audit read from T3 — not from any single drone's local store. See [06 — Environments](06-environments.md), [ADR-0003](adr/ADR-0003-sync-derived-state-only.md).
+
+### Architecture layer 1 — ingestion
+
+On-board services that capture sensor streams and video analytics ([02 — Architecture](02-architecture.md)): `sensor-ingest`, `video-analytics`.
+
+### Architecture layer 2 — storage and transform
+
+On-board Parquet write path, sealer, DuckDB, NVMe ([02 — Architecture](02-architecture.md)).
+
+### Architecture layer 3 — serving and sync
+
+On-board event hook, pub/sub broadcast, MinIO derived bucket, peer query API ([02 — Architecture](02-architecture.md)).
+
+### Pipeline stage
+
+Narrative inside each drone: (1) raw capture, (2) ETL/reduction, (3) bidirectional sync interface. Not the same as storage floors T0–T4 ([12 — Design journey](12-design-journey.md) §4).
+
+### Bulk sync
+
+In-flight pull of sealed `detections`/`state` Parquet partitions between peers via **rsync** delta over persistent SSH forced commands ([04 — Swarm sync](04-swarm-sync.md)).
+
+### Offload
+
+Post-flight mirror of sealed T1 partitions into T3 at the dock: **rsync** or MinIO **`mc mirror`**, then integrity audit before local prune ([03 — Data platform](03-data-platform.md)).
+
+### rclone
+
+Optional rsync-class tool when the far end is object storage and rsync is awkward; not the default in-flight mesh path ([09 — Open questions](09-open-questions.md) §12).
+
+### ADR
+
+Architecture Decision Record — a point-in-time decision for this repository ([adr/README.md](adr/README.md)).
+
+### ASR
+
+Architecture Standard Record — a standing cross-repository policy (lives in the ecosystem `inventar` repo, not here). See [adr/README.md](adr/README.md).
+
## Data & storage
| Term | Meaning |
@@ -10,8 +74,8 @@ Terms and abbreviations used throughout this proposal.
| **Hive partitioning** | Directory layout `key=value/…` understood by most engines; enables partition pruning (only relevant directories are read) |
| **DuckDB** | In-process analytical SQL engine; queries Parquet globs directly, no server to operate |
| **ZSTD** | Zstandard compression; the default codec for all Parquet files here |
-| **DWH** | Data warehouse — here: the on-prem ground store holding every flight ever flown |
-| **Hot / warm / cold tiers** | Storage floors ordered by access latency and retention: in-memory window → local NVMe → ground warehouse |
+| **DWH** | Data warehouse — here: the on-prem ground store holding every flight ever flown; same role as [source of truth](#source-of-truth) |
+| **Hot / warm / cold tiers** | Classic three-tier model: in-memory window → local NVMe → ground warehouse. Here mapped to [T0](#t0--hot), [T1](#t1--warm), and [T3](#t3--warehouse); [T2](#t2--shared) and [T4](#t4--dev) are named explicitly |
| **Sealing** | Compacting many small streamed Parquet files into one final file per partition once a time window closes |
| **UUIDv7** | Time-ordered UUID; sortable by creation time, used as the canonical flight identifier |
| **DuckDB spatial** | Extension adding a GEOMETRY type and `ST_*` functions; used for separation audits, perimeter predicates, and trajectory analysis in the local planar frame |
diff --git a/docs/01-problem-statement.md b/docs/01-problem-statement.md
index 4f3e809..f2001d4 100644
--- a/docs/01-problem-statement.md
+++ b/docs/01-problem-statement.md
@@ -15,7 +15,7 @@ Plus everything a platform needs around that: reproducible builds and deployment
| Constraint | Consequence |
| --- | --- |
| **No internet, no external access, ever** | All infrastructure self-hosted; updates through an in-air-gap registry mirror; no cloud services of any kind |
-| **Autonomous operation** | No human in the control loop during flight; the platform must not require operator intervention |
+| **Autonomous operation** | No human in the control loop during flight; the platform must not require operator intervention. A [supervising operator](00-glossary.md#swarm--robotics) may set mission intent over [C2](00-glossary.md#swarm--robotics) before and during flight, but does not steer individual vehicles |
| **Intermittent mesh connectivity** | No component may assume a stable link between any two drones; no swarm-wide orchestrator |
| **Mixed hardware** | ARM64 and AMD64 Linux targets; some nodes carry GPUs for inference; all images built multi-arch |
| **Bounded on-board resources** | Multi-TB NVMe but finite; high-rate ingest must be compressed and retention-managed in flight |
@@ -30,8 +30,8 @@ Plus everything a platform needs around that: reproducible builds and deployment
- **Parquet** adoption is at the evaluation stage — the storage layout in this proposal is the core of what is being asked.
- **MinIO** is available and considered as the inter-drone sync mechanism.
- A **lightweight Kubernetes** exists in the ecosystem; this proposal scopes it to ground infrastructure only (see [02 — Architecture](02-architecture.md)).
-- After landing, each drone's data is **offloaded to an on-prem warehouse** for replay and iterative model training.
-- Mission intent (declarative goals) reaches the swarm over a narrow **C2 channel**; there is no continuous ground link in flight.
+- After landing, each drone's data is **offloaded to the on-prem [source of truth](00-glossary.md#source-of-truth)** for replay and iterative model training.
+- Mission intent (declarative goals) reaches the swarm over a narrow **[C2](00-glossary.md#swarm--robotics) channel**; there is no continuous ground link in flight.
## What is assumed (explicitly marked as assumptions)
diff --git a/docs/02-architecture.md b/docs/02-architecture.md
index c2aff81..ddd6c3b 100644
--- a/docs/02-architecture.md
+++ b/docs/02-architecture.md
@@ -2,7 +2,7 @@
## On-board: three layers, one Compose file
-Every drone runs the same three-layer data plane. **Docker Compose under systemd is the only on-board orchestrator.** Cluster orchestrators (Kubernetes, Swarm mode) assume a stable control plane and continuous connectivity — in an ad-hoc mesh with intermittent links that is an anti-pattern. Each drone is fully autonomous; coordination happens through data exchange, not through a shared control plane. Lightweight Kubernetes (k3s) is used on the ground only (warehouse, CI runners, simulation farm — see [06 — Environments](06-environments.md)).
+Every drone runs the same [three-layer](00-glossary.md#architecture-layer-1--ingestion) data plane ([storage floors](00-glossary.md#t0--hot) T0–T4 are a separate concept — see [03 — Data platform](03-data-platform.md#storage-floors-tiers)). **Docker Compose under systemd is the only on-board orchestrator.** Cluster orchestrators (Kubernetes, Swarm mode) assume a stable control plane and continuous connectivity — in an ad-hoc mesh with intermittent links that is an anti-pattern. Each drone is fully autonomous; coordination happens through data exchange, not through a shared control plane. Lightweight Kubernetes (k3s) is used on the ground only (warehouse, CI runners, simulation farm — see [06 — Environments](06-environments.md)).
```mermaid
graph TB
@@ -42,7 +42,7 @@ graph TB
### Layer 1 — Ingestion
- `sensor-ingest` subscribes to sensor sources (ROS 2 topics where available, raw drivers otherwise) and normalizes them into typed streams: IMU, barometer, temperature, LiDAR, RSSI, power, and so on.
-- `video-analytics` runs a **YOLO-like object detector** on the camera stream. The model is deliberately treated as a swappable, versioned artifact (weights differ per mission and improve over time — see [11 — CI/CD & delivery](11-cicd-delivery.md)). GPU access via nvidia-container-toolkit; ARM64 builds use the vendor's L4T-class base images.
+- `video-analytics` runs a [**YOLO-like**](00-glossary.md#swarm--robotics) object detector on the camera stream. The model is deliberately treated as a swappable, versioned artifact (weights differ per mission and improve over time — see [11 — CI/CD & delivery](11-cicd-delivery.md)). GPU access via nvidia-container-toolkit; ARM64 builds use the vendor's L4T-class base images.
- Both services emit rows, not files. Timestamps are `int64` epoch **nanoseconds** end to end (native for ROS 2; IMU-class rates make milliseconds insufficient).
### Layer 2 — Storage and transform
@@ -55,7 +55,7 @@ graph TB
- The **event hook** is the on-board "lambda": when the writer lands new *derived* rows (state, detections), it triggers registered actions — broadcast, MinIO upload, or a local mission-logic callback. Nothing polls.
- The **state publisher** broadcasts compact position/attitude/detection payloads over the mesh pub/sub (transport analysis in [04 — Swarm sync](04-swarm-sync.md)).
-- **Bulk sync** pulls sealed derived partitions from peers over persistent SSH (rsync delta transfer); MinIO remains optional where an S3 API is wanted.
+- **Bulk sync** pulls sealed derived partitions from peers over persistent SSH ([rsync](00-glossary.md#bulk-sync) delta transfer); MinIO remains optional where an S3 API is wanted.
- **Peer queries** are read-only DuckDB SQL over SSH forced commands — SELECT-only gate, read-only OS user, columnar responses (the design decision and its reasoning are in [04](04-swarm-sync.md)).
## Communication planes
@@ -65,11 +65,11 @@ Three isolated planes with different lifecycles:
```mermaid
graph LR
subgraph planes [Communication planes]
- C2["C2 control plane
mission intent, narrow, in production"]
+ C2["[C2](00-glossary.md#swarm--robotics) control plane
mission intent, narrow, in production"]
DATA["swarm data plane
state broadcast + sync, in production"]
DEV["dev/debug plane
live telemetry, bench only"]
end
- OPERATOR["supervising operator
(man-in-the-loop)"] --> C2
+ OPERATOR["supervising operator
([man-in-the-loop](00-glossary.md#swarm--robotics))"] --> C2
C2 --> SWARM["swarm"]
SWARM <--> DATA
DEV -.->|absent from production builds| SWARM
@@ -79,7 +79,7 @@ graph LR
| --- | --- | --- | --- |
| **C2 control plane** | Deliver declarative mission goals and boundaries; receive high-level status. Human supervises intent, not actions | Very low | Yes |
| **Swarm data plane** | State broadcast, derived-data replication, peer queries | The scarce resource; budget per message class | Yes |
-| **Dev/debug plane** | Full live telemetry for bench development and HIL tests | High | **No — physically absent from production builds** |
+| **Dev/debug plane** | Full live telemetry for bench development and [HIL](00-glossary.md#infrastructure--delivery) tests | High | **No — physically absent from production builds** |
The dev plane is not "disabled by config": production images and radio profiles simply do not contain it. That removes an entire attack surface instead of guarding it.
diff --git a/docs/03-data-platform.md b/docs/03-data-platform.md
index 1002bab..c2ab0a3 100644
--- a/docs/03-data-platform.md
+++ b/docs/03-data-platform.md
@@ -1,6 +1,6 @@
# 03 — Data platform
-The heart of the proposal: how raw sensor streams become a compressed, queryable, offloadable store — with **one format and one layout on every floor** of the system.
+The heart of the proposal: how raw sensor streams become a compressed, queryable, offloadable store — with **one format and one layout on every [storage floor](00-glossary.md#t0--hot)** of the system.
## Datasets
@@ -14,7 +14,7 @@ Three logical datasets, distinct because their consumers and sync policies diffe
## Partitioning layout
-Identity dimensions first, calendar time last, everything Hive-style `key=value`:
+Identity dimensions first, calendar time last, everything [Hive-style](00-glossary.md#data--storage) `key=value`:
```
dataset=telemetry/flight=20260708T1100Z-a3f2/drone=dr-017/sensor=imu/year=2026/month=07/day=08/hour=11/
@@ -29,7 +29,7 @@ Design decisions and their reasons:
- **`flight` before `drone`.** The dominant warehouse query is *replay of one flight across all drones*. With `flight` on top, a replay reads one subtree. (On board, `drone=` is constant and costs nothing — but keeping it means the on-board layout is byte-identical to the warehouse layout.)
- **`sensor` before time.** Each sensor has its own schema, so sensors need separate leaves anyway; and "one sensor over a period" is the most common analytical scan. Partition pruning handles both.
-- **Flight identifiers.** The canonical flight id is a **UUIDv7** (time-ordered, globally unique, embedded timestamp — sortable by design). Partition paths use a short human-readable time-sortable alias (`20260708T1100Z-a3f2`) so directory listings stay debuggable; the full UUIDv7 lives in the data and in the flight manifest.
+- **Flight identifiers.** The canonical flight id is a [**UUIDv7**](00-glossary.md#data--storage) (time-ordered, globally unique, embedded timestamp — sortable by design). Partition paths use a short human-readable time-sortable alias (`20260708T1100Z-a3f2`) so directory listings stay debuggable; the full UUIDv7 lives in the data and in the flight manifest.
- **Timestamps: `int64` epoch nanoseconds.** Same 8 bytes as milliseconds, native resolution of ROS 2, sufficient for IMU-class rates, valid until year 2262. One time type everywhere — no unit confusion at merge time.
- **No rounding in raw data.** Coordinates and measurements are stored exactly as the sensor emits them (float64/float32 per sensor spec). ZSTD plus Parquet delta encoding makes rounding-for-size unnecessary. Quantization (millimeters as int32) is applied **only** to broadcast payloads, where every byte of air time counts ([04 — Swarm sync](04-swarm-sync.md)).
@@ -50,7 +50,7 @@ sequenceDiagram
S->>W: rows (int64 ns, typed)
W->>C: flush min_NN.parquet (small, ZSTD-fast)
end
- Note over Z: window closes (hour sealed
or flight ends)
+ Note over Z: window closes (hour [sealed](00-glossary.md#data--storage)
or flight ends)
Z->>C: read all min_*.parquet
Z->>P: write one compact file (ZSTD-high)
Z->>C: remove blocks after verify
@@ -63,26 +63,28 @@ sequenceDiagram
## Storage floors (tiers)
-Same format on every floor; only volume, retention, and location change:
+Same [Parquet](00-glossary.md#data--storage) + [DuckDB](00-glossary.md#data--storage) format on every floor; only volume, retention, and location change. See [glossary](00-glossary.md#t0--hot) for the full T0–T4 definitions.
| Floor | Where | Contents | Retention |
| --- | --- | --- | --- |
-| **T0 — hot** | RAM / DuckDB in-process | Sliding window of the last minutes; what mission logic queries in flight | Minutes |
-| **T1 — warm** | Drone NVMe | Full raw `telemetry` + `detections` + `state` of the current flight; never leaves the drone in flight | Current flight (+ quota-based headroom) |
-| **T2 — shared** | On-board MinIO bucket | Derived data only (`detections`, `state`), replicated opportunistically across the swarm | Current mission |
-| **T3 — warehouse** | Ground on-prem object store + Parquet lakehouse | Every flight of every drone, forever; replay, analytics, model training | Years |
-| **T4 — dev** | Engineer laptop / sim farm | Slices pulled from T3, or synthetic data from the simulator | Ephemeral |
+| **[T0 — hot](00-glossary.md#t0--hot)** | RAM / DuckDB in-process | Sliding window of the last minutes; what mission logic queries in flight | Minutes |
+| **[T1 — warm](00-glossary.md#t1--warm)** | Drone NVMe | Full raw `telemetry` + `detections` + `state` of the current flight; never leaves the drone in flight | Current flight (+ quota-based headroom) |
+| **[T2 — shared](00-glossary.md#t2--shared)** | On-board MinIO bucket | Derived data only (`detections`, `state`), replicated opportunistically across the swarm | Current mission |
+| **[T3 — warehouse](00-glossary.md#t3--warehouse)** | Ground on-prem object store + Parquet lakehouse | Every flight of every drone, forever; [source of truth](00-glossary.md#source-of-truth) for replay, analytics, model training | Years |
+| **[T4 — dev](00-glossary.md#t4--dev)** | Engineer laptop / sim farm | Slices pulled from T3, or synthetic data from the simulator | Ephemeral |
## Flight offload: a mirror, not a migration
-Because T1 and T3 share the identical layout, offload after landing is:
+Because [T1](00-glossary.md#t1--warm) and [T3](00-glossary.md#t3--warehouse) share the identical layout, [offload](00-glossary.md#offload) after landing is:
```bash
# per drone, at the base station
-mc mirror drone-nvme/flights/ warehouse/flights/ # or rsync over the wired dock
+rsync -a drone-nvme/flights/ warehouse/flights/ # or mc mirror to object store
duckdb -c "…integrity audit: row counts, time coverage, gap scan per partition…"
```
+For S3-only backends where rsync is awkward, [rclone](00-glossary.md#rclone) is an optional rsync-class alternative — not the default mesh path ([09 — Open questions](09-open-questions.md) §12).
+
The audit compares expected vs actual coverage per partition (row counts, min/max timestamps, gap detection) before the drone's local copy is released for cleanup. Missing or corrupt partitions are re-pulled — a lazy gap-repair pass rather than a failed batch job.
## Retention and quotas on board
@@ -138,6 +140,6 @@ On the ground this powers replay overlays, coverage analysis (did ubiquitous sen
## Schema management
-- Every dataset schema is versioned in-repo (`schemas/` — SemVer, one file per dataset version) and referenced by the fleet release manifest ([11](11-cicd-delivery.md)).
+- Every dataset schema is versioned in-repo (planned `schemas/` directory — [roadmap stage 2](08-roadmap.md), [09 — Open questions](09-open-questions.md) §14; SemVer, one file per dataset version) and referenced by the fleet release manifest ([11](11-cicd-delivery.md)).
- Parquet files carry the schema version in file metadata; readers select the matching deserializer.
- Additive evolution only within a MAJOR version (new nullable columns); breaking changes bump MAJOR and require a manifest release.
diff --git a/docs/04-swarm-sync.md b/docs/04-swarm-sync.md
index c7c4f38..888a8f8 100644
--- a/docs/04-swarm-sync.md
+++ b/docs/04-swarm-sync.md
@@ -16,19 +16,21 @@ Bandwidth is the scarcest resource in the system. Every message class gets an ex
## Broadcast payload: small on the wire, precise at rest
-The `state` broadcast is a fixed compact frame:
+The `state` broadcast is a fixed compact frame (46 bytes, little-endian):
| Field | Type | Notes |
| --- | --- | --- |
-| `drone_id` | uint16 | Fleet-scoped registry |
+| `magic` | 2 bytes | `b"SH"` |
+| `version` | uint8 | Protocol version |
+| `drone_id` | 8 bytes | Zero-padded ASCII fleet id |
| `ts_ns` | int64 | Epoch nanoseconds, same clock domain as storage |
| `pos_x/y/z` | int32 | **Millimeters** in the mission frame — quantized only here, storage keeps full float precision |
| `att_roll/pitch/yaw` | int16 | Centi-degrees |
| `vel_x/y/z` | int16 | cm/s |
-| `frame_ref` | uint8 | Frame of reference id (GPS-denied: local/visual-odometry frames must be explicit) |
+| `frame_ref` | uint8 | Frame of reference id ([GPS-denied](00-glossary.md#swarm--robotics): local/visual-odometry frames must be explicit) |
| `flags` | uint8 | Battery-low, returning, degraded-sensors, … |
-~40 bytes per frame → a 50-drone swarm at 5 Hz is ~10 KB/s of pose traffic before transport overhead. Trivial even on a congested mesh.
+46 bytes per frame → a 50-drone swarm at 5 Hz is ~11.5 KB/s of pose traffic before transport overhead. Trivial even on a congested mesh.
`detections` events are slightly larger (class, confidence, bounding volume, ego-pose) but event-shaped and rare by comparison.
@@ -51,7 +53,7 @@ graph LR
SB -->|"store-and-forward relay"| SC
```
-### Recommended: Zenoh
+### Recommended: [Zenoh](00-glossary.md#swarm--robotics)
- Designed exactly for constrained, dynamic networks: built-in peer discovery, brokerless peer-to-peer mode, store-and-forward, and a query layer on top of pub/sub.
- First-class robotics citizenship: an official ROS 2 RMW implementation exists, so the ingestion side and the sync side can share one middleware.
@@ -68,13 +70,13 @@ graph LR
## Two sync mechanisms, deliberately separate
-1. **Fast path — pub/sub (Zenoh):** pose frames and detection events. Fire-and-forget with bounded staleness; consumers keep a peer-state cache.
-2. **Bulk path — rsync over persistent SSH:** sealed `detections`/`state` Parquet partitions are pulled opportunistically between drones when links allow. This is how a drone that was out of range catches up on mission history without anyone re-sending events.
+1. **Fast path — pub/sub ([Zenoh](00-glossary.md#swarm--robotics)):** pose frames and detection events. Fire-and-forget with bounded staleness; consumers keep a peer-state cache.
+2. **Bulk path — [rsync](00-glossary.md#bulk-sync) over persistent SSH:** sealed `detections`/`state` Parquet partitions are pulled opportunistically between drones when links allow. This is how a drone that was out of range catches up on mission history without anyone re-sending events.
Why SSH-based bulk sync over object-store replication:
-- **Identity is already there.** Every drone holds pre-provisioned ed25519 keys and a fixed `known_hosts`/`authorized_keys` set from ground provisioning ([05](05-network-security.md)) — the trust model needs no new machinery.
-- **One persistent multiplexed session** (`ControlMaster`) per peer costs almost nothing at idle and survives as a single TCP stream; every transfer rides it without new handshakes.
+- **Identity is already there.** Every drone holds pre-provisioned [ed25519](00-glossary.md#infrastructure--delivery) keys and a fixed `known_hosts`/`authorized_keys` set from ground provisioning ([05](05-network-security.md)) — the trust model needs no new machinery.
+- **One persistent multiplexed session** ([`ControlMaster`](00-glossary.md#infrastructure--delivery)) per peer costs almost nothing at idle and survives as a single TCP stream; every transfer rides it without new handshakes.
- **rsync delta transfer is resumable** across link drops — exactly the failure mode of an ad-hoc mesh — and the shared partition layout makes it trivially incremental: same paths, same files, pull only what is missing.
- **Zero extra services** on the flight-critical node. MinIO remains available where an S3 API is genuinely wanted (ground warehouse, and optionally on board), but the in-flight bulk path does not depend on it.
@@ -83,7 +85,7 @@ Partition healing is automatic: replication is pull-based, addressed by partitio
Two deliberate non-features of the SSH channel:
- **No remote filesystem mounts in flight.** FUSE/sshfs over a lossy mesh inherits NFS hang semantics — processes block uninterruptibly when the link drops. Mounts are fine on the bench and at the dock; in flight, data moves by pull, never by mount.
-- **No free-form remote execution.** Arbitrary drone-to-drone exec would mean one compromised unit owns the fleet. Instead, every permitted operation is an **SSH forced command** (`command="…"` in `authorized_keys`, one key pair per operation): the key *is* the API. Flexible like a CLI, auditable like an RPC, least-privilege by construction.
+- **No free-form remote execution.** Arbitrary drone-to-drone exec would mean one compromised unit owns the fleet. Instead, every permitted operation is an **SSH [forced command](00-glossary.md#infrastructure--delivery)** (`command="…"` in `authorized_keys`, one key pair per operation): the key *is* the API. Flexible like a CLI, auditable like an RPC, least-privilege by construction.
## Design decision: SQL-over-SSH as the peer query channel
@@ -114,7 +116,7 @@ SQL access must not become a write channel. A single "read-only connection" flag
- **Schema-first:** all datasets share the versioned schemas from [03](03-data-platform.md); a query addresses `dataset + partition predicates + column projection + time range`. Schema version is negotiated from the fleet release manifest — peers on one release speak one schema by construction.
- **Read-only SELECT over the local Parquet store**, streamed back as Parquet/Arrow batches over the multiplexed SSH session. Never JSON blobs.
-- **On the ground — GraphQL as the integration standard:** the warehouse exposes the same schemas through GraphQL for the multi-team surface, where flexibility and introspection matter more than grams and milliwatts. **Arrow Flight** is the upgrade path for heavy columnar serving from T3 if result sizes outgrow it.
+- **On the ground — GraphQL as the integration standard:** the warehouse exposes the same schemas through GraphQL for the multi-team surface, where flexibility and introspection matter more than grams and milliwatts. **Arrow Flight** is the upgrade path for heavy columnar serving from [T3](00-glossary.md#t3--warehouse) if result sizes outgrow it.
What this buys operationally: the dev/bench experience and the flight protocol are the same thing. An engineer debugging on the bench runs the identical query a peer drone would run — same wrapper, same permissions, same output format. There is no "debug API" that behaves differently from the real one.
diff --git a/docs/05-network-security.md b/docs/05-network-security.md
index 10b6ff2..94fda4c 100644
--- a/docs/05-network-security.md
+++ b/docs/05-network-security.md
@@ -23,9 +23,9 @@ graph TB
A["drone A
wg key + certs"]
B["drone B
wg key + certs"]
C["drone C
wg key + certs"]
- A <-->|"WireGuard + mTLS"| B
- B <-->|"WireGuard + mTLS"| C
- A <-->|"WireGuard + mTLS"| C
+ A <-->|"WireGuard tunnel"| B
+ B <-->|"WireGuard tunnel"| C
+ A <-->|"WireGuard tunnel"| C
end
PROV -->|"per-device identity, peer list"| A
PROV --> B
@@ -65,7 +65,7 @@ Keep both layers: WireGuard for *who is on the network and whether the wire is r
## Data at rest
- On-board NVMe is encrypted (LUKS) with keys held in the device's secure element / TPM where the hardware provides one; the disk alone is unreadable.
-- The ground warehouse applies standard at-rest encryption plus role-based access; it is the single most valuable asset in the system (every flight ever flown).
+- The ground warehouse applies standard at-rest encryption plus role-based access; it is the [source of truth](00-glossary.md#source-of-truth) and the single most valuable asset in the system (every flight ever flown).
## Attack surface, deliberately shortened
diff --git a/docs/06-environments.md b/docs/06-environments.md
index 2d6831f..89be9af 100644
--- a/docs/06-environments.md
+++ b/docs/06-environments.md
@@ -9,15 +9,15 @@ graph LR
subgraph dev [3 — Dev and simulation]
SIM["virtual drone fleet
(simulator, Compose)"]
LAP["engineer laptop
Dev Container"]
- SLICE["T4: data slices"]
+ SLICE["[T4](00-glossary.md#t4--dev): data slices"]
end
subgraph fleet [1 — Fleet, in flight]
- D1["drone: Compose data plane
T0 hot + T1 NVMe + T2 MinIO"]
+ D1["drone: Compose data plane
[T0](00-glossary.md#t0--hot) hot + [T1](00-glossary.md#t1--warm) NVMe + [T2](00-glossary.md#t2--shared) MinIO"]
D2["drone …"]
end
subgraph ground [2 — Ground, on-prem]
DOCK["base station docks"]
- DWH["T3 warehouse
object store + Parquet/DuckDB"]
+ DWH["[T3](00-glossary.md#t3--warehouse) warehouse
object store + Parquet/DuckDB"]
K3S["k3s: CI runners, registry mirror,
sim farm, dashboards"]
TRAIN["model training (out of scope)
reads T3, ships weights"]
end
@@ -34,7 +34,7 @@ graph LR
## 1 — Fleet infrastructure (on the drones)
- Docker Compose under systemd; the full stack from [02 — Architecture](02-architecture.md).
-- Storage floors T0–T2. Nothing here requires ground contact during a mission.
+- Storage floors [T0–T2](00-glossary.md#t0--hot). Nothing here requires ground contact during a mission.
- Receives new software only while docked, from the registry mirror, pinned by the fleet release manifest.
## 2 — Ground infrastructure (on-prem)
@@ -43,7 +43,7 @@ The permanent installation. This **is** allowed to be a cluster — links are wi
| Component | Runs on | Role |
| --- | --- | --- |
-| **Warehouse (T3)** | Object store (MinIO or equivalent) + Parquet | Every flight of every drone; the system's long-term memory |
+| **Warehouse ([T3](00-glossary.md#t3--warehouse))** | Object store (MinIO or equivalent) + Parquet | Every flight of every drone; the system's [source of truth](00-glossary.md#source-of-truth) and long-term memory |
| **Base station docks** | Bare metal | Wired offload + integrity audit + drone provisioning ([03](03-data-platform.md), [05](05-network-security.md)) |
| **Registry mirror** | k3s | In-air-gap container registry + artifact storage; the only software source drones ever see |
| **CI runners** | k3s | Multi-arch builds, tests, scans ([11](11-cicd-delivery.md)) |
@@ -60,7 +60,7 @@ The environment engineers live in daily — and deliberately the first thing to
- **No debug API** ([04](04-swarm-sync.md)): bench access to a drone's data goes through the same read-only SQL-over-SSH wrapper the peers use in flight — same permissions, same statement gate, same columnar output. Debugging exercises the production path instead of a parallel one, so the query channel is regression-tested every working day for free.
- **The virtual drone fleet** ([`simulator/`](../simulator/)) runs the *identical* data plane: same writer, same partitioning, same sealing, same broadcast schema. `DRONE_COUNT=10 docker compose up` is a swarm on a laptop.
- **Scenarios are reproducible by seed:** route shapes, sensor noise, drone dropouts, link losses are all parameterized — a bug report is a seed + config, not a war story.
-- **T4 data slices**: a thin tool pulls partition subsets from T3 (`flight=X, drone=Y, hour=Z`) for local work — layout-identical, so every query and pipeline runs unmodified.
+- **[T4](00-glossary.md#t4--dev) data slices**: a thin tool pulls partition subsets from [T3](00-glossary.md#t3--warehouse) (`flight=X, drone=Y, hour=Z`) for local work — layout-identical, so every query and pipeline runs unmodified.
- The same simulator images scale out on the ground k3s farm for CI regression runs: every merge request replays canonical scenarios and asserts on the resulting Parquet output (row counts, coverage, staleness budgets).
## IaC boundaries
@@ -74,13 +74,13 @@ Infrastructure as code follows the same discipline as the data plane: each tool
| Ongoing ground configuration | **Flux** ([`infra/gitops/`](../infra/gitops/)) | Policy labels, dashboard bundles, offload knobs — reconciled from git without reprovisioning PVCs. Drones stay on the fleet manifest, not GitOps. |
| On-board runtime | **Compose bundle from the fleet release manifest** | Terraform is deliberately *not* on the drone: there is no API server to reconcile against mid-flight, and the release manifest already gives atomic, versioned, rollback-able delivery ([11](11-cicd-delivery.md)). |
-Shared local data paths (same layout everywhere): **`var/t1/`** (live lake, T1) and **`var/t3/`** (warehouse, T3). Compose, k3d, and DuckDB on the host all read the same Parquet tree.
+Shared local data paths (same layout everywhere): **`var/t1/`** (live lake, [T1](00-glossary.md#t1--warm)) and **`var/t3/`** (warehouse, [T3](00-glossary.md#t3--warehouse)). Compose, k3d, and DuckDB on the host all read the same Parquet tree.
Two Terraform modules, two states, one deliberate split: [`sim-env`](../infra/terraform/sim-env/) (the disposable virtual fleet) and [`ground`](../infra/terraform/ground/) (the warehouse that must survive every `destroy` of the fleet). They never share a lifecycle.
### k3d: the ground segment as an executable miniature
-`ansible-playbook infra/ansible/sim-cluster.yml` creates a local k3d cluster (k3s in Docker — the same distribution as the real ground segment) and `terraform apply` populates it: virtual drones as StatefulSet replicas over a shared Parquet lake, the exporter/Prometheus/Grafana stack, the data-plane explorer, MinIO, and the T1→T3 offload CronJob. The whole diagram at the top of this page runs on one workstation, and the prototype's **live mode** renders real drone positions straight from the explorer's read-only SQL API.
+`ansible-playbook infra/ansible/sim-cluster.yml` creates a local k3d cluster (k3s in Docker — the same distribution as the real ground segment) and `terraform apply` populates it: virtual drones as StatefulSet replicas over a shared Parquet lake, the exporter/Prometheus/Grafana stack, the data-plane explorer, MinIO, and the [T1](00-glossary.md#t1--warm)→[T3](00-glossary.md#t3--warehouse) offload CronJob. The sim CronJob uses `cp -ru` plus `mc mirror` as a shortcut; production dock [offload](00-glossary.md#offload) uses rsync or `mc mirror` with checksum audit ([03](03-data-platform.md)). The whole diagram at the top of this page runs on one workstation, and the prototype's **live mode** renders real drone positions straight from the explorer's read-only SQL API.
### Next fidelity step: microVMs
@@ -90,7 +90,7 @@ The k3d fleet shares one kernel and one network namespace tree — good enough t
| Operation | What it costs with one layout everywhere |
| --- | --- |
-| Flight offload | `mc mirror` / `rsync` + audit — no transform step |
+| Flight offload | `rsync` / `mc mirror` + audit — no transform step ([03](03-data-platform.md)) |
| Debugging a field issue | Pull the flight slice, replay locally, same queries |
| Validating a pipeline change | Run simulator, diff Parquet outputs |
| Training data prep | Read T3 directly, no export pipeline |
diff --git a/docs/07-observability.md b/docs/07-observability.md
index 71a0061..0a16d70 100644
--- a/docs/07-observability.md
+++ b/docs/07-observability.md
@@ -29,7 +29,7 @@ graph LR
LG["structured logs
= Parquet partitions"]
end
subgraph ground [Ground k3s]
- DWH["T3 warehouse"]
+ DWH["[T3](00-glossary.md#t3--warehouse) warehouse"]
PR["Prometheus
(live: docks, CI, sim farm)"]
LK["Loki
(live logs, dev plane)"]
GF["Grafana
dashboards + replay"]
@@ -44,7 +44,7 @@ graph LR
```
- **Prometheus/Grafana/Loki** cover everything that is alive on the ground: docks, registry, CI runners, warehouse, simulation farm — plus drones on the bench through the dev plane.
-- **Flight post-mortems query the warehouse directly** with DuckDB: staleness budgets vs actuals, link quality vs distance (RSSI), sealing backlog vs ingest rate — per flight, per drone, per minute.
+- **Flight post-mortems query the [source of truth](00-glossary.md#source-of-truth) warehouse directly** with DuckDB: staleness budgets vs actuals, link quality vs distance (RSSI), sealing backlog vs ingest rate — per flight, per drone, per minute.
## Health questions this design answers cheaply
diff --git a/docs/08-roadmap.md b/docs/08-roadmap.md
index 0a8420b..6be60f5 100644
--- a/docs/08-roadmap.md
+++ b/docs/08-roadmap.md
@@ -12,7 +12,7 @@ graph TD
S4["Stage 4
Serving layer
event hook, query API, local MinIO"]
S5["Stage 5
Virtual swarm simulation
N drones in Compose, seeded scenarios, CI regression"]
S6["Stage 6
Mesh network and security
WireGuard overlay, PKI provisioning, mTLS"]
- S7["Stage 7
Swarm sync
pose broadcast, detections pub/sub, MinIO replication"]
+ S7["Stage 7
Swarm sync
pose broadcast, detections pub/sub, bulk replication (rsync over SSH)"]
S8["Stage 8
Ground warehouse
offload + audit, T3 store, replay tooling"]
S9["Stage 9
Observability
platform metrics as sensor stream, ground dashboards"]
S10["Stage 10
Fleet releases
manifest, mirror, dock delivery, atomic rollback"]
diff --git a/docs/09-open-questions.md b/docs/09-open-questions.md
index 3066c66..3041c10 100644
--- a/docs/09-open-questions.md
+++ b/docs/09-open-questions.md
@@ -18,7 +18,7 @@ Visual-odometry positions are relative; different drones may hold different loca
By construction there are no write conflicts in bulk sync (each drone writes only its own `drone=` subtree). But *derived swarm-level* products (shared maps, fused detections) may need merging.
-*Proposal:* keep swarm-level fusion out of the storage layer entirely: every drone stores its own observations; fusion is computed, not stored, in flight — and recomputed from ground truth in the warehouse. If a persistent shared structure becomes unavoidable, use a CRDT type for it rather than inventing reconciliation.
+*Proposal:* keep swarm-level fusion out of the storage layer entirely: every drone stores its own observations; fusion is computed, not stored, in flight — and recomputed from the [source of truth](00-glossary.md#source-of-truth) in the warehouse. If a persistent shared structure becomes unavoidable, use a [CRDT](00-glossary.md#infrastructure--delivery) type for it rather than inventing reconciliation.
## 4 — Degradation policy under sustained link loss
@@ -42,7 +42,7 @@ The degradation ladder ([03](03-data-platform.md)) needs a domain-approved order
The virtual swarm covers logic and protocol; it does not cover radio behavior, GPU thermals, or NVMe write endurance under vibration.
-*Proposal:* a small HIL rig at the bench — real compute module + radio, simulated sensor feeds — as stage 5.5 of the roadmap, exercised by the same seeded scenarios as CI.
+*Proposal:* a small [HIL](00-glossary.md#infrastructure--delivery) rig at the bench — real compute module + radio, simulated sensor feeds — as stage 5.5 of the roadmap, exercised by the same seeded scenarios as CI.
## 8 — Video retention policy
@@ -64,6 +64,24 @@ Sub-250 g class units cannot run the full stack (no GPU, minimal CPU/storage).
## 11 — Lake retention and partition pruning
-The observability path now scans only the most recent flights ([ADR-0009](adr/ADR-0009-bounded-lake-scans.md)), but old `flight=` partitions still accumulate on T1 disk after offload to T3.
+The observability path now scans only the most recent flights ([ADR-0009](adr/ADR-0009-bounded-lake-scans.md)), but old `flight=` partitions still accumulate on [T1](00-glossary.md#t1--warm) disk after offload to [T3](00-glossary.md#t3--warehouse).
*Proposal:* a scheduled prune of T1 partitions whose flights are confirmed present in the T3 warehouse (offload as the retention gate), configurable by age and free-space watermark. On the drone the same policy is bounded by the NVMe quota ladder ([03](03-data-platform.md)); in the sim environment it is a ground CronJob alongside the offload job.
+
+## 12 — Bulk transfer tool choice
+
+In-flight peer bulk sync, dock offload, and sim shortcuts have used different wording (rsync, rclone, `mc mirror`, `cp -ru`).
+
+*Proposal:* **rsync over SSH** is the default for peer [bulk sync](00-glossary.md#bulk-sync) and wired dock [offload](00-glossary.md#offload) of the Hive partition tree; **MinIO `mc mirror`** when the far end is the object-store facade; **[rclone](00-glossary.md#rclone)** only when the backend is S3-compatible and rsync is awkward; sim CronJob keeps **`cp -ru` + `mc mirror`** as a documented shortcut. Pick one primary tool per path in provisioning, not all at once.
+
+## 13 — DuckLake vs plain DuckDB + Parquet on T3
+
+The design journey mentions DuckLake; no ADR or implementation commits to it yet.
+
+*Proposal:* baseline remains DuckDB `read_parquet` globs over the [T3](00-glossary.md#t3--warehouse) Hive tree with MinIO underneath; evaluate DuckLake only if catalog/versioning pain appears at warehouse scale — decision gets its own ADR before any dependency lands.
+
+## 14 — `schemas/` registry layout
+
+[03 — Data platform](03-data-platform.md) references an in-repo `schemas/` directory that does not exist yet (roadmap stage 2).
+
+*Proposal:* add `schemas/` as part of stage 2 with one SemVer file per dataset version, referenced from the fleet release manifest; until then treat schema versions as manifest-only fields and document the gap here rather than implying the directory already exists.
diff --git a/docs/10-domain-context.md b/docs/10-domain-context.md
index 476cb3d..99f6ded 100644
--- a/docs/10-domain-context.md
+++ b/docs/10-domain-context.md
@@ -9,14 +9,14 @@ Swarm autonomy has moved past biomimicry-driven research toward practical, opera
| **Decentralization** | No single controller; every unit perceives locally and decides autonomously; no single point of failure | No swarm-wide orchestrator; each drone runs its own full data plane ([02](02-architecture.md)) |
| **Local interactions** | Behavior emerges from neighbor-to-neighbor exchange, not top-down commands | State broadcast between peers; event hooks trigger local reactions ([04](04-swarm-sync.md)) |
| **Self-organization** | The group coordinates without pre-planned orchestration and survives the loss of members | Opportunistic replication; store-and-forward through intermediate peers; automatic reconciliation after partitions ([04](04-swarm-sync.md)) |
-| **Sustainable pulsing** | The swarm repeatedly engages a target area from multiple directions and re-forms as conditions change | Requires every unit to know peer state with bounded staleness — exactly the state-sync contract ([04](04-swarm-sync.md)) |
-| **Ubiquitous sensing** | The swarm acts as one distributed sensor, fusing observations into shared "top sight" | Detections are first-class derived data: locally stored, selectively shared, fully preserved for post-flight fusion ([03](03-data-platform.md)) |
+| **[Sustainable pulsing](00-glossary.md#swarm--robotics)** | The swarm repeatedly engages a target area from multiple directions and re-forms as conditions change | Requires every unit to know peer state with bounded staleness — exactly the state-sync contract ([04](04-swarm-sync.md)) |
+| **[Ubiquitous sensing](00-glossary.md#swarm--robotics)** | The swarm acts as one distributed sensor, fusing observations into shared "top sight" | Detections are first-class derived data: locally stored, selectively shared, fully preserved for post-flight fusion ([03](03-data-platform.md)) |
| **Edge intelligence** | Detection and classification happen on the unit; a local event can autonomously cue nearby units without central validation | On-board YOLO-like inference + event hook that publishes detections to the mesh immediately ([02](02-architecture.md)) |
| **Mesh networking** | Units relay data for each other; loss of any single link degrades nothing | Encrypted ad-hoc mesh, no infrastructure dependency ([05](05-network-security.md)) |
-| **GPS-denied operation** | Position comes from visual odometry and relative localization, not satellites | The state schema carries a frame-of-reference field and covariance, not just raw coordinates ([03](03-data-platform.md), [09](09-open-questions.md)) |
-| **Man-in-the-loop** | A supervisor defines intent and boundaries; the system distributes tasks itself | Narrow C2 plane for declarative goals; no per-vehicle steering ([02](02-architecture.md)) |
+| **[GPS-denied operation](00-glossary.md#swarm--robotics)** | Position comes from visual odometry and relative localization, not satellites | The state schema carries a frame-of-reference field and covariance, not just raw coordinates ([03](03-data-platform.md), [09](09-open-questions.md)) |
+| **[Man-in-the-loop](00-glossary.md#swarm--robotics)** | A supervisor defines intent and boundaries; the system distributes tasks itself | Narrow C2 plane for declarative goals; no per-vehicle steering ([02](02-architecture.md)) |
| **Adaptive re-tasking** | A detected event re-prioritizes nearby units without manual replanning | Event-driven data plane: detections propagate as events, mission logic subscribes ([02](02-architecture.md)) |
-| **Ethical autonomy / traceability** | Autonomous actions must be explainable: event-driven sensing over indiscriminate collection, decisions logged and auditable | Every broadcast, sync, and re-tasking trigger is recorded in the flight data; the warehouse preserves the full decision trail for replay ([03](03-data-platform.md), [06](06-environments.md)) |
+| **Ethical autonomy / traceability** | Autonomous actions must be explainable: event-driven sensing over indiscriminate collection, decisions logged and auditable | Every broadcast, sync, and re-tasking trigger is recorded in the flight data; the [source of truth](00-glossary.md#source-of-truth) warehouse preserves the full decision trail for replay ([03](03-data-platform.md), [06](06-environments.md)) |
| **Adaptive learning** | Experience gathered by one unit improves the whole team over iterations | Complete flights land in the ground warehouse; training reads from it and ships improved model weights through the fleet release cycle ([06](06-environments.md), [11](11-cicd-delivery.md)) |
| **Multi-domain scaling** | The same swarm concepts apply to aerial, ground, surface, and underwater units — including sub-250 g platforms | The data plane is a set of small independent services; the minimal profile (writer + publisher, no GPU stack) fits constrained units ([02](02-architecture.md)) |
@@ -25,7 +25,7 @@ Swarm autonomy has moved past biomimicry-driven research toward practical, opera
Every one of these principles quietly assumes a working data layer underneath:
- *Pulsing* and *re-tasking* assume each unit **knows peer state** — that is a sync latency and staleness budget.
-- *Ubiquitous sensing* assumes observations are **fused later** — that is a warehouse with aligned timestamps and schemas.
+- *Ubiquitous sensing* assumes observations are **fused later** — that is the [source of truth](00-glossary.md#source-of-truth) warehouse with aligned timestamps and schemas.
- *Edge intelligence* assumes detection events **reach neighbors fast** — that is an event-driven publish path, not a polling loop.
- *Traceability* assumes actions are **replayable** — that is complete, immutable, partitioned flight data.
- *Learning* assumes flights are **comparable across the fleet and across time** — that is schema versioning and a single storage format.
diff --git a/docs/11-cicd-delivery.md b/docs/11-cicd-delivery.md
index c84d457..6ffba00 100644
--- a/docs/11-cicd-delivery.md
+++ b/docs/11-cicd-delivery.md
@@ -85,7 +85,7 @@ schemas:
config:
compose-bundle: 3.4.0
radio-profile: production-2
- peer-registry: fleet-42-r7 # provisioning + revocations, see 05
+ peer-registry: fleet-42-r7 # provisioning + revocations, see [05 — Network & security](05-network-security.md)
```
- Everything is **semver-versioned individually**, and the manifest itself carries the fleet version — a lockfile for the whole swarm.
diff --git a/docs/12-design-journey.md b/docs/12-design-journey.md
index 679eda1..ee107fe 100644
--- a/docs/12-design-journey.md
+++ b/docs/12-design-journey.md
@@ -4,6 +4,7 @@ How this design came together, told in the order the thinking actually happened.
It is a walk-through, not a report. The formal decisions, with options and
trade-offs, live as [Architecture Decision Records](adr/README.md). This is the
story behind them, and each chapter links straight into the code it produced.
+Terms: [Glossary](00-glossary.md).
---
@@ -46,17 +47,17 @@ conclusion: constrain the transport, but do not constrain on-board capture. Keep
everything locally. Send only what peers truly need.
> **Read more**
-> - [01 — Problem statement](01-problem-statement.md) and [03 — Data platform](03-data-platform.md) — the constraints and the storage tiers
+> - [01 — Problem statement](01-problem-statement.md) and [03 — Data platform](03-data-platform.md) — the constraints and the [storage floors](00-glossary.md#t0--hot) (T0–T4)
-## 4. Three tiers inside each unit
+## 4. Three pipeline stages inside each unit
-That gave [three layers](03-data-platform.md) on every drone:
+That gave [three architecture layers](02-architecture.md) on every drone — not the same as [storage floors](00-glossary.md#t0--hot) T0–T4:
-1. **Raw capture**, never transformed.
-2. **ETL / reduction**, where data is cut down to what has to be shared:
- millimetres to centimetres, thinning time series where that is enough,
+1. **Raw capture** (pipeline stage 1), never transformed.
+2. **ETL / reduction** (pipeline stage 2), where data is cut down to what has to be shared:
+ millimeters to centimeters, thinning time series where that is enough,
dropping what nobody downstream reads.
-3. **A bidirectional interface**: on one side it broadcasts position into the
+3. **A bidirectional interface** (pipeline stage 3): on one side it broadcasts position into the
shared channel, on the other it lets peers pull data.
The ETL is deliberately not over-specified. How sensor data is transformed is a
@@ -65,7 +66,7 @@ stored and in which structure, not to step into that work.
> **Read the code**
> - [`simulator/virtual_drone/writer.py`](https://git.produktor.io/eSlider/swarm-house/src/branch/main/simulator/virtual_drone/writer.py#L23-L80) — the Hive-partition layout and the seal step that compacts a flight
-> - [`simulator/virtual_drone/sensors.py`](https://git.produktor.io/eSlider/swarm-house/src/branch/main/simulator/virtual_drone/sensors.py) — the raw capture that feeds tier one
+> - [`simulator/virtual_drone/sensors.py`](https://git.produktor.io/eSlider/swarm-house/src/branch/main/simulator/virtual_drone/sensors.py) — the raw capture that feeds pipeline stage 1
## 5. What actually needs to sync
@@ -131,17 +132,19 @@ coming back to foundations DevOps and sysadmins already trust.
## 8. Replication and offload
-Moving accumulated data uses rsync-class tooling (rclone) over the same SSH
-channel. It transfers diffs of the Hive tree efficiently. This matters because a
-unit can be lost, and if it is, we want its data to already exist elsewhere.
-When peers have a stable link the partition tree is pulled between them, which
-gives redundancy and a way to cross-check later. On the ground, when the fleet
-returns, the same path unifies every unit's data into a
-[local warehouse](06-environments.md). The warehouse is read-mostly for
-analytics, so transaction contention is not a concern, which opens a
-DuckDB / DuckLake approach with MinIO underneath, the
-[same storage model on both ends](adr/ADR-0002-one-storage-format.md). One
-uniform structure is what lets an analyst trust a single picture even when a
+Moving accumulated data uses [rsync](00-glossary.md#bulk-sync) over the same SSH
+channel for in-flight peer [bulk sync](00-glossary.md#bulk-sync) and dock
+[offload](00-glossary.md#offload). It transfers diffs of the Hive tree efficiently.
+This matters because a unit can be lost, and if it is, we want its data to
+already exist elsewhere. When peers have a stable link the partition tree is
+pulled between them, which gives redundancy and a way to cross-check later. On
+the ground, when the fleet returns, the same path unifies every unit's data into
+a [local warehouse](06-environments.md) ([T3](00-glossary.md#t3--warehouse)).
+The warehouse is read-mostly for analytics, so transaction contention is not a
+concern — plain DuckDB over Parquet with MinIO underneath is the baseline;
+DuckLake remains under evaluation ([09 — Open questions](09-open-questions.md)
+§13). The [same storage model on both ends](adr/ADR-0002-one-storage-format.md).
+One uniform structure is what lets an analyst trust a [single picture](00-glossary.md#source-of-truth) even when a
unit's data has a gap.
> **Read the code**
diff --git a/docs/improvement/2026-07-10-audit.md b/docs/improvement/2026-07-10-audit.md
new file mode 100644
index 0000000..ead72e9
--- /dev/null
+++ b/docs/improvement/2026-07-10-audit.md
@@ -0,0 +1,68 @@
+# Documentation audit — 2026-07-10
+
+Manual pass over `docs/`, all READMEs, and glossary. Goal: correct links, unify T0–T4 vocabulary, align rsync/offload wording with code, improve readability.
+
+## Summary
+
+| Metric | Result |
+| --- | --- |
+| Markdown files checked | 33 |
+| Broken relative links (after fixes) | 0 |
+| Glossary `###` anchors added | 15 (T0–T4, layers, bulk sync, source of truth, …) |
+| Open questions added | §12–§14 (tooling, DuckLake, `schemas/`) |
+
+## Findings fixed
+
+### Links
+
+- `infra/terraform/ground/README.md` pointed at non-existent `03-storage-design.md` → `03-data-platform.md`.
+- `11-cicd-delivery.md` bare cross-reference to doc 05 → proper markdown link.
+
+### Factual drift (code vs docs)
+
+| Item | Was | Now (matches `broadcast.py`, `sim.ts`) |
+| --- | --- | --- |
+| Pose frame | ~40 bytes, uint16 `drone_id` | 46 bytes, 8-byte ASCII `drone_id` |
+
+### Terminology
+
+- Extended [00 — Glossary](../00-glossary.md) with T0–T4, architecture layers, pipeline stages, source of truth.
+- Disambiguated design journey §4: pipeline stages ≠ storage floors.
+- Roadmap Stage 7: rsync bulk path, not “MinIO replication”.
+
+### rsync / rclone / offload
+
+| Path | Canonical tool |
+| --- | --- |
+| Peer bulk sync | rsync over SSH |
+| Dock offload | rsync or `mc mirror` |
+| S3 backends (optional) | rclone |
+| Sim CronJob | `cp -ru` + `mc mirror` (documented shortcut) |
+
+### Live demos (design journey)
+
+Tracked in [PR #3](https://git.produktor.io/eSlider/swarm-house/pulls/3) — explorer + Grafana links in `12-design-journey.md` §7/§9. Prototype link already on `main` §2.
+
+### README / LICENSE
+
+- Restricted-use notice with link to [LICENSE](../../LICENSE).
+- Component READMEs tightened (caveman style).
+
+## Remaining (documented, not bugs)
+
+| Item | Where |
+| --- | --- |
+| `schemas/` directory absent | OQ §14, roadmap stage 2 |
+| DuckLake undecided | OQ §13 |
+| rsync bulk sync not in sim code | Design only |
+| Glossary table terms link to section headers, not row anchors | Optional polish |
+| T4 after “Source of truth” in glossary order | Cosmetic |
+| GitOps “source of truth” vs data SSOT | Different meanings in `11-cicd-delivery` |
+
+## Suggested CI checks (for issue #1)
+
+Implemented in [`bin/check_docs.py`](../../bin/check_docs.py) — see [ci-rules.md](ci-rules.md).
+
+## Files touched
+
+`docs/00`–`12`, `docs/adr/*`, nine READMEs, root `README.md`.
diff --git a/docs/improvement/README.md b/docs/improvement/README.md
new file mode 100644
index 0000000..3ccac0b
--- /dev/null
+++ b/docs/improvement/README.md
@@ -0,0 +1,27 @@
+# Documentation improvement records
+
+Point-in-time audits and follow-up work for links, terminology, readability, and factual alignment with code.
+
+| Report | Date | Scope |
+| --- | --- | --- |
+| [2026-07-10 audit](2026-07-10-audit.md) | 2026-07-10 | Full `docs/` + README pass; glossary T0–T4; live demo links |
+
+## Collaboration style
+
+Issues, PRs, and reviews default to **caveman-full** ([`CONTRIBUTING.md`](../../CONTRIBUTING.md#caveman-style-default),
+[`AGENTS.md`](../../AGENTS.md#caveman-style-default-for-collaboration)). Gitea templates live under
+[`.github/ISSUE_TEMPLATE/`](../../.github/ISSUE_TEMPLATE/) and
+[`.github/pull_request_template.md`](../../.github/pull_request_template.md).
+
+## CI automation
+
+Enforced in Gitea Actions (`docs-verify` job). Rules live in [`bin/docs_rules.json`](../../bin/docs_rules.json); see [ci-rules.md](ci-rules.md).
+
+Originally tracked in [issue #1](https://git.produktor.io/eSlider/swarm-house/issues/1).
+
+## How to add a new report
+
+1. Copy the structure from the latest audit file.
+2. Name it `YYYY-MM-DD-short-topic.md`.
+3. Add a row to the table above.
+4. Cross-link from [09 — Open questions](../09-open-questions.md) if new ambiguities appear.
diff --git a/docs/improvement/ci-rules.md b/docs/improvement/ci-rules.md
new file mode 100644
index 0000000..d472712
--- /dev/null
+++ b/docs/improvement/ci-rules.md
@@ -0,0 +1,58 @@
+# CI documentation rules
+
+Automated checks for markdown in this repository. Enforced on every **pull request** and on **push to `main`** (including docs-only pushes that skip the simulator gate).
+
+Implementation: [`bin/check_docs.py`](../../bin/check_docs.py) reads [`bin/docs_rules.json`](../../bin/docs_rules.json).
+
+Workflow: [`.github/workflows/release.yaml`](../../.github/workflows/release.yaml) job **`Verify documentation`**.
+
+Tracked from [issue #1](https://git.produktor.io/eSlider/swarm-house/issues/1) and the [2026-07-10 audit](2026-07-10-audit.md).
+
+## Gates
+
+| Rule | Severity | What it checks |
+| --- | --- | --- |
+| Relative links | error | Every `[text](path)` and `[text](path#anchor)` to a local `.md` file resolves to an existing file |
+| Fragment anchors | error | `#anchor` fragments match a `##` or `###` heading in the target file (GitHub-style slug) |
+| Banned targets | error | Known-bad paths (e.g. deleted `03-storage-design.md`) are not linked |
+| Glossary fragments | error | All `00-glossary.md#…` links use anchors that exist in the glossary |
+| Section vs term links | warning | Links to glossary *section* headers (`#swarm--robotics`, …) are listed; prefer `###` term anchors where they exist |
+| Bare cross-refs | error | Prose cross-references to numbered docs without a proper markdown link |
+| ADR immutability | error | No modifications to existing `docs/adr/ADR-*.md` (compare `origin/main`); add new ADR to supersede |
+
+Warnings are printed in the job log but do not fail CI. Errors exit non-zero and block merge.
+
+## PR workflow
+
+```mermaid
+flowchart LR
+ PR[Pull request] --> DV[docs-verify]
+ PR --> V[verify simulator]
+ V --> S[Trivy scan]
+ DV --> OK{All required green?}
+ V --> OK
+ S --> OK
+ OK -->|yes| Merge[Mergeable]
+```
+
+| Event | `docs-verify` | `verify` + `scan` |
+| --- | --- | --- |
+| PR → `main` | always | always |
+| Push → `main` (code paths) | always | runs |
+| Push → `main` (docs/README/AGENTS only) | always | skipped (`paths-ignore`) |
+
+Docs-only changes therefore still get link and glossary validation on `main`; they do not trigger a semantic release.
+
+## Local run
+
+```bash
+python bin/check_docs.py
+python bin/check_adrs.py --base origin/main
+python bin/check_docs.py --warnings-as-errors # treat section-link warnings as failures
+```
+
+## Changing rules
+
+1. Edit `bin/docs_rules.json` (paths, banned targets, preferred anchors).
+2. Adjust `bin/check_docs.py` only when adding a new rule *type*.
+3. Add a row to the table above and mention it in the audit/improvement record if the change is significant.
diff --git a/infra/ansible/README.md b/infra/ansible/README.md
index 5e00f2b..2051447 100644
--- a/infra/ansible/README.md
+++ b/infra/ansible/README.md
@@ -1,14 +1,11 @@
# Ansible — host preparation
-Ansible owns everything that happens **on a host before workloads run**.
-Terraform ([`../terraform/`](../terraform/)) owns the workloads themselves.
-The boundary is deliberate and documented in
-[06 — Environments](../../docs/06-environments.md#iac-boundaries).
+Ansible = host prep before workloads run. Terraform ([`../terraform/`](../terraform/)) owns workloads. Boundary: [06 — IaC boundaries](../../docs/06-environments.md#iac-boundaries).
| Playbook | Target | What it does |
| --- | --- | --- |
-| `drone-provision.yml` | Drone (on the bench, before a mission) | Identity keys, peer trust with forced commands, WireGuard, Compose bundle from the fleet release manifest |
-| `sim-cluster.yml` | Local workstation / CI host | k3d cluster that miniatures the ground segment; shared data volume; simulator image import |
+| `drone-provision.yml` | Drone (bench, before mission) | Identity keys, peer trust with forced commands, WireGuard, Compose bundle from fleet manifest |
+| `sim-cluster.yml` | Local workstation / CI host | k3d cluster miniaturing ground segment; shared data volume; simulator image import |
## Provision a drone
@@ -16,16 +13,12 @@ The boundary is deliberate and documented in
ansible-playbook -i inventory.example.yml drone-provision.yml
```
-The playbook is idempotent and runs only over the bench network — drones
-are never provisioned in flight (see [05 — Network & security](../../docs/05-network-security.md)):
+Idempotent. Bench network only. Never provision in flight ([05 — Network & security](../../docs/05-network-security.md)):
-1. **Identity**: generate the drone's ed25519 keypair if absent.
-2. **Peer trust**: install every fleet member's public key into
- `authorized_keys`, each pinned to the read-only SQL forced command —
- the only thing a peer can execute.
-3. **WireGuard**: render `wg0.conf` with the drone's address and peers.
-4. **Data plane**: lay down the Compose bundle referenced by the fleet
- release manifest and enable it as a systemd unit.
+1. **Identity**: generate drone ed25519 keypair if absent.
+2. **Peer trust**: fleet public keys in `authorized_keys`, each pinned to read-only SQL forced command.
+3. **WireGuard**: render `wg0.conf` with drone address and peers.
+4. **Data plane**: Compose bundle from fleet manifest, systemd unit enabled.
## Create the simulation cluster
@@ -34,6 +27,4 @@ ansible-playbook sim-cluster.yml # creates k3d cluster 'swarm-sim'
cd ../terraform/sim-env && terraform init && terraform apply
```
-The cluster mounts a shared host directory as `/data` on the (single)
-node, so drone pods, the exporter, and the explorer see one Parquet lake —
-the same contract as the on-board NVMe layout.
+Shared host directory mounted as `/data` — drone pods, exporter, explorer see one Parquet lake (same contract as on-board NVMe).
diff --git a/infra/gitops/README.md b/infra/gitops/README.md
index dbabcf6..a8d8f28 100644
--- a/infra/gitops/README.md
+++ b/infra/gitops/README.md
@@ -1,20 +1,16 @@
# GitOps — ground segment (Flux)
-Flux reconciles **long-lived ground configuration** from this repository. It does
-not run on drones and does not replace the fleet release manifest — those are
-different lifecycles by design ([11 — CI/CD](../../docs/11-cicd-delivery.md)).
+Flux = long-lived ground config from git. Not on drones. Not fleet manifest. Different lifecycles ([11 — CI/CD](../../docs/11-cicd-delivery.md)).
## Boundary: Terraform vs Flux vs fleet manifest
| Layer | Tool | Owns |
| --- | --- | --- |
-| Cluster + first boot | **Terraform** ([`../terraform/`](../terraform/)) | Namespaces, PVCs, Deployments, CronJobs, NodePorts — the shape of the simulation |
-| Ongoing ground config | **Flux** (this directory) | Policy labels, dashboard bundles, offload knobs — things that change without reprovisioning PVCs |
-| Drones | **Fleet release manifest** | Compose bundle digests, model weights, peer registry — atomic, dock-only delivery |
+| Cluster + first boot | **Terraform** ([`../terraform/`](../terraform/)) | Namespaces, PVCs, Deployments, CronJobs, NodePorts |
+| Ongoing ground config | **Flux** (this directory) | Policy labels, dashboard bundles, offload knobs |
+| Drones | **[Fleet release manifest](../../docs/11-cicd-delivery.md)** | Compose digests, model weights, peer registry — dock-only |
-Drones are **outside GitOps**: there is no reconciler in flight. A dock applies
-the pinned manifest once; mid-mission drift is impossible because the update
-endpoint does not exist in the radio profile.
+Drones outside GitOps. No reconciler in flight. Dock applies pinned manifest once. No mid-mission drift — no update endpoint in radio profile.
## Layout
@@ -26,9 +22,7 @@ infra/gitops/
## Bootstrap on the k3d simulation cluster
-`infra/ansible/sim-cluster.yml` installs Flux controllers and applies the CRs
-below. After the first `git push`, Flux polls `origin` and reconciles
-`infra/gitops/ground/` into the `ground` namespace.
+`infra/ansible/sim-cluster.yml` installs Flux and applies CRs. After first `git push`, Flux reconciles `infra/gitops/ground/`.
```bash
# Manual bootstrap (if you skipped Ansible):
@@ -36,17 +30,13 @@ flux install --namespace=flux-system
kubectl apply -k infra/gitops/flux
```
-To reconcile immediately without waiting for the poll interval:
+Reconcile immediately:
```bash
flux reconcile source git swarm-house -n flux-system
flux reconcile kustomization ground-segment -n flux-system
```
-## What Flux manages here (example)
+## What Flux manages
-The [`ground/`](ground/) overlay currently carries a **GitOps-managed ConfigMap**
-that tags the warehouse segment with fleet policy metadata. In production this
-pattern extends to Grafana dashboard bundles, Prometheus rule files, and
-offload-schedule ConfigMaps — all versioned in git, all auditable, none of
-them requiring a `terraform apply` to tweak a label.
+[`ground/`](ground/) overlay: GitOps-managed ConfigMap with fleet policy metadata. Production extends to Grafana dashboards, Prometheus rules, offload-schedule ConfigMaps — git-versioned, no `terraform apply` for label tweaks.
diff --git a/infra/terraform/README.md b/infra/terraform/README.md
index d508982..e184c29 100644
--- a/infra/terraform/README.md
+++ b/infra/terraform/README.md
@@ -1,7 +1,18 @@
+# Terraform — ground workloads
+
+Declared workloads on the k3d simulation cluster. See [06 — IaC boundaries](../../docs/06-environments.md#iac-boundaries).
+
+| Module | Tier | Purpose |
+| --- | --- | --- |
+| [`sim-env/`](sim-env/) | [T4](../../docs/00-glossary.md#t4--dev) dev/sim | Virtual fleet + observability on k3d |
+| [`ground/`](ground/) | [T3](../../docs/00-glossary.md#t3--warehouse) | Warehouse + [T1→T3](../../docs/03-data-platform.md#storage-floors-tiers) offload |
+
+Two modules, two states. Fleet disposable; warehouse survives `destroy` of sim-env.
+
## Recovering from partial state
If resources were created outside Terraform (or state was lost), import them
-before `terraform apply`:
+before `terraform apply`. Run from the target module directory (`sim-env/` or `ground/`):
```bash
# sim-env (namespace: swarm)
diff --git a/infra/terraform/ground/README.md b/infra/terraform/ground/README.md
index e6fc8c6..7b21911 100644
--- a/infra/terraform/ground/README.md
+++ b/infra/terraform/ground/README.md
@@ -1,19 +1,14 @@
-# Terraform — ground warehouse (T3)
+# Terraform — ground warehouse ([T3](../../../docs/00-glossary.md#t3--warehouse))
-The stationary half of the system: the historical warehouse that receives
-sealed partitions after every flight ([03 — Storage tiers](../../../docs/03-storage-design.md)).
-It is the longest-lived, most conventional infrastructure in the design —
-and therefore the most natural Terraform territory.
+Ground warehouse. Receives sealed partitions post-flight ([storage floors](../../../docs/03-data-platform.md#storage-floors-tiers)). Long-lived infra → Terraform.
-Runs in the same k3d cluster as [`../sim-env`](../sim-env/) but in its own
-namespace with its own state: the fleet is disposable, the warehouse is not,
-and the two lifecycles must never share a `terraform destroy`.
+Runs in same k3d cluster as [`../sim-env`](../sim-env/) but separate namespace and state: fleet disposable, warehouse not — never share `terraform destroy`.
| Resource | Purpose |
| --- | --- |
-| Deployment `minio` + PVC + NodePort 30901 | Object-store facade of the warehouse for downstream consumers (training pipelines, replay) |
-| CronJob `offload` | Post-flight offload: copies Hive partitions verbatim from the fleet lake (T1) into the warehouse (T3), then mirrors into MinIO |
-| Deployment `warehouse-explorer` + NodePort 30089 | Second explorer instance over the warehouse path — historical read-only SQL across **all** flights |
+| Deployment `minio` + PVC + NodePort 30901 | Object-store facade for downstream consumers |
+| CronJob `offload` | [T1](../../../docs/00-glossary.md#t1--warm) → [T3](../../../docs/00-glossary.md#t3--warehouse) offload: Hive partitions verbatim, then `mc mirror` into MinIO |
+| Deployment `warehouse-explorer` + NodePort 30089 | Read-only SQL across **all** offloaded flights |
## Usage
@@ -23,16 +18,9 @@ terraform apply
terraform output
```
-After a couple of offload runs, the warehouse explorer shows the same
-partition tree as the live lake but accumulated across flights — the T1
-layout **is** the T3 layout, which is the whole point: no transform step,
-no schema drift, DuckDB queries work identically on both ends.
+After offload runs, warehouse explorer shows same partition tree as live lake, accumulated across flights. [T1](../../../docs/00-glossary.md#t1--warm) layout **is** [T3](../../../docs/00-glossary.md#t3--warehouse) layout. No transform. No schema drift. Same DuckDB queries both ends.
## Simulation vs production
-- The CronJob compresses "drone lands, docks, offloads, prunes" into a
- periodic rsync-style copy. Production offload is event-driven per docking
- and verifies checksums from the flight's partition manifest before pruning
- the on-board lake.
-- MinIO credentials here are throwaway defaults; production credentials are
- sealed per site and never in state or VCS.
+- Sim CronJob: `cp -ru` + `mc mirror` on a schedule — shortcut for "lands, offloads, prunes". Production: event-driven per dock, rsync or `mc mirror`, checksum audit before prune ([03 — Data platform](../../../docs/03-data-platform.md)).
+- MinIO credentials here are throwaway defaults; production credentials sealed per site, never in state or VCS.
diff --git a/infra/terraform/sim-env/README.md b/infra/terraform/sim-env/README.md
index b305735..f118f15 100644
--- a/infra/terraform/sim-env/README.md
+++ b/infra/terraform/sim-env/README.md
@@ -1,17 +1,14 @@
-# Terraform — simulation environment (T4)
+# Terraform — simulation environment ([T4](../../../docs/00-glossary.md#t4--dev))
-Declares the simulated fleet and its observability stack on the k3d cluster
-created by [`../../ansible/sim-cluster.yml`](../../ansible/sim-cluster.yml).
-This module is the executable miniature of the dev/sim environment from
-[06 — Environments](../../../docs/06-environments.md).
+Sim fleet + observability on k3d. Cluster from [`../../ansible/sim-cluster.yml`](../../ansible/sim-cluster.yml). Executable [T4](../../../docs/00-glossary.md#t4--dev) miniature ([06 — Environments](../../../docs/06-environments.md)).
| Resource | Purpose |
| --- | --- |
-| StatefulSet `drone` × `drone_count` | Virtual drones; stable pod names become `DRONE_ID`s; all write Hive-partitioned Parquet into the shared `/data` lake |
-| Deployment `exporter` | Prometheus exporter reading the lake with DuckDB |
-| Deployment `explorer` + NodePort 30088 | Partition tree + read-only SQL console (also feeds the prototype's live mode) |
-| Deployment `prometheus` + NodePort 30990 | Scrapes the exporter |
-| Deployment `grafana` + NodePort 30300 | Same dashboard JSON as the Compose profile, provisioned from a ConfigMap |
+| StatefulSet `drone` × `drone_count` | Virtual drones; pod names → `DRONE_ID`; shared `/data` lake |
+| Deployment `exporter` | Prometheus exporter reading lake with DuckDB |
+| Deployment `explorer` + NodePort 30088 | Partition tree + read-only SQL (prototype live mode) |
+| Deployment `prometheus` + NodePort 30990 | Scrapes exporter |
+| Deployment `grafana` + NodePort 30300 | Dashboard JSON from ConfigMap |
## Usage
@@ -22,7 +19,7 @@ terraform apply
terraform output # URLs
```
-Scale the fleet without touching YAML:
+Scale without YAML edits:
```bash
terraform apply -var drone_count=9 -var speedup=4
@@ -30,11 +27,6 @@ terraform apply -var drone_count=9 -var speedup=4
## Notes
-- `image_pull_policy = "Never"` — the simulator image is imported by the
- Ansible playbook (`k3d image import`); the cluster never pulls from a
- registry, mirroring the air-gap doctrine.
-- Pods discover their identity from the pod name (StatefulSet ordinal), so
- a flight survives `kubectl delete pod` the same way a drone survives a
- power cycle: new process, same identity, new flight ID.
-- State is local (`terraform.tfstate` in this directory) — the simulation
- cluster is disposable; nothing here is shared infrastructure.
+- `image_pull_policy = "Never"` — image imported by Ansible (`k3d image import`); no registry pull. Air-gap mirror.
+- Pod name → identity (StatefulSet ordinal). `kubectl delete pod` = power cycle: new process, same identity, new flight ID.
+- Local state only — cluster disposable.
diff --git a/prototype/README.md b/prototype/README.md
index dae6e30..b708c59 100644
--- a/prototype/README.md
+++ b/prototype/README.md
@@ -1,8 +1,8 @@
# Swarm visualization prototype
-A 2D top-down view of the swarm data plane from [04 — Swarm sync](../docs/04-swarm-sync.md): drones patrol an area with static and mobile obstacles, exchange 5 Hz pose broadcasts (blue link flashes), and run opportunistic bulk sync of sealed partitions (green links with live rate and cumulative up/down counters).
+2D top-down view of swarm data plane from [04 — Swarm sync](../docs/04-swarm-sync.md): drones patrol with obstacles, 5 Hz pose broadcasts (blue flashes), opportunistic bulk sync (green links with rate and byte counters).
-No backend — a pure client-side simulation of the same behavioral model the Python simulator implements over real Parquet and UDP.
+No backend. Client-side sim. Same behavioral model as Python simulator (Parquet + UDP).
## Run
@@ -11,9 +11,16 @@ npm install
npm run dev # http://localhost:5173
```
+## Live mode
+
+With k3d fleet + explorer running (`ansible-playbook` + `terraform apply` — see [sim-env README](../infra/terraform/sim-env/README.md)):
+
+- Explorer at `http://localhost:30088`
+- Header → **go live** — polls read-only SQL API for real drone positions
+
## What to look at
-- **Links appear and disappear** as drones move in and out of radio range; persistent links render semi-transparent, broadcast deliveries flash them briefly.
-- **Busy links turn green** and show current rate plus total transferred (`↑` / `↓`) — the bandwidth budget from the sync design made visible.
-- **Per-drone label**: id, current Wi-Fi channel (hopping), battery.
-- Controls: drone count, simulation speed, pause.
+- Links form and break by radio range; broadcasts flash active links
+- Busy links turn green — rate plus `↑` / `↓` totals
+- Per-drone label: id, Wi-Fi channel, battery
+- Controls: drone count, speed, pause
diff --git a/simulator/README.md b/simulator/README.md
index 380754c..ed157e7 100644
--- a/simulator/README.md
+++ b/simulator/README.md
@@ -1,8 +1,8 @@
# Virtual drone fleet
-A data generator that exercises the **exact on-board pipeline** described in [03 — Data platform](../docs/03-data-platform.md): seeded kinematics along a patrol route, sensor streams at realistic rates, detection events, the hot `current/` → sealed Parquet write path, and the compact UDP state broadcast between drones.
+Data generator. Same on-board pipeline as [03 — Data platform](../docs/03-data-platform.md): seeded kinematics, sensor streams, detection events, hot `current/` → sealed Parquet, compact UDP state broadcast.
-One process = one drone. Scaling the swarm is a Compose flag.
+One process = one drone. Scale swarm with Compose flag.
## Run a swarm
@@ -14,7 +14,7 @@ FLIGHT_ID=$(date -u +%Y%m%dT%H%MZ)-sim docker compose up --build --scale drone=5
DRONE_COUNT=10 DURATION_S=300 SPEEDUP=4 docker compose up --build --scale drone=10
```
-Output lands in [`../var/t1/`](../var/t1/) (the shared T1 lake — same path the k3d fleet and warehouse offload use). Override with `SWARM_T1_DIR` if needed:
+Output lands in [`../var/t1/`](../var/t1/) ([T1](../docs/00-glossary.md#t1--warm) live lake — same path k3d fleet and warehouse offload use). Override with `SWARM_T1_DIR` if needed:
```
var/t1/dataset=telemetry/flight=…/drone=…/sensor=imu/year=…/…/hour=…/data.parquet
@@ -22,7 +22,7 @@ var/t1/dataset=detections/flight=…/drone=…/…
var/t1/dataset=state/flight=…/drone=…/… ← sent + received broadcasts
```
-Historical flights after offload live under [`../var/t3/`](../var/t3/) (T3 warehouse).
+Historical flights after offload: [`../var/t3/`](../var/t3/) ([T3](../docs/00-glossary.md#t3--warehouse) warehouse).
## Run a single drone without Docker
@@ -52,33 +52,32 @@ print(con.sql("""
EOF
```
-## Monitoring: Grafana over the generated data
+## Monitoring
-The `monitoring` profile spins up a small metrics chain — a DuckDB-based exporter that scans the generated Parquet every few seconds, Prometheus, and a pre-provisioned Grafana dashboard:
+`monitoring` profile: DuckDB exporter → Prometheus → Grafana ([07 — Observability](../docs/07-observability.md)):
```bash
-docker compose --profile monitoring up -d # exporter + prometheus + grafana
-# generate some flights in parallel or beforehand:
+docker compose --profile monitoring up -d
FLIGHT_ID=$(date -u +%Y%m%dT%H%MZ)-sim docker compose up --scale drone=5
```
-- Grafana: `http://localhost:3000` (anonymous admin — demo only) → dashboard **Swarm Fleet — generated data**
+- Grafana: `http://localhost:3000` → **Swarm Fleet — generated data**
- Prometheus: `http://localhost:9090` · exporter: `http://localhost:9105/metrics`
-Panels: telemetry rows by drone/sensor, detections by class, pose frames sent/received, battery per drone, RSSI and estimated distance per link, Parquet bytes/files on disk. The exporter is deliberately a demonstration of the observability doctrine from [07 — Observability](../docs/07-observability.md): fleet statistics are *derived from the data platform itself* — no agent on the drone, just SQL over the same Parquet everyone else reads.
+Fleet stats derived from Parquet via SQL — no on-drone agent.
## Data-plane explorer
-The `monitoring` profile also starts a **data-plane explorer** at `http://localhost:8088` — a single-page web view over the lake itself, complementing Grafana (which shows aggregates, not the structure):
+`monitoring` profile also starts explorer at `http://localhost:8088` (k3d: `:30088`):
-- **Partition tree**, live: `dataset → flight → drone → sensor → year/…/hour → file`, with file counts and bytes rolled up at every level. You can watch `current/` files appear and get sealed while a swarm is flying.
-- **Read-only SQL console** with the datasets pre-registered as views (`telemetry`, `detections`, `state`) and one-click sample queries (fleet overview, battery timeline, detections by class, peer link quality, schema).
+- Partition tree live: `dataset → flight → drone → sensor → hour → file`
+- Read-only SQL console — same [statement gate](../docs/04-swarm-sync.md) as peer query channel: `SELECT`/`WITH`/`DESCRIBE`/`SUMMARIZE`/`SHOW` only
-The console enforces the **same statement gate as the peer query channel** from [04 — Swarm sync](../docs/04-swarm-sync.md): a single statement, `SELECT`/`WITH`/`DESCRIBE`/`SUMMARIZE`/`SHOW` only, write/config/extension keywords rejected. That is the point: exploring the data plane on the bench uses the same read-only SQL contract a peer drone uses in flight — the explorer is the "no debug API" principle made visible.
+Point: bench exploration uses same read-only SQL contract as flight peers.
## Reproducibility
-Every run is deterministic per `(SEED, DRONE_ID)`: same route jitter, same sensor noise, same detection sequence. A bug report is a seed and a config, not a description.
+Deterministic per `(SEED, DRONE_ID)`. Bug report = seed + config.
## Knobs
diff --git a/simulator/tests/test_check_adrs.py b/simulator/tests/test_check_adrs.py
new file mode 100644
index 0000000..f276388
--- /dev/null
+++ b/simulator/tests/test_check_adrs.py
@@ -0,0 +1,70 @@
+"""Tests for bin/check_adrs.py — ADR immutability gate."""
+
+from __future__ import annotations
+
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+SCRIPTS = Path(__file__).resolve().parents[2] / "bin"
+sys.path.insert(0, str(SCRIPTS))
+
+from check_adrs import find_modified_adrs, run_check # noqa: E402
+
+
+def _git(cwd: Path, *args: str) -> None:
+ subprocess.check_call(["git", *args], cwd=cwd, stdout=subprocess.DEVNULL)
+
+
+def test_no_modified_adrs_on_current_branch() -> None:
+ assert run_check(base="origin/main") == 0
+
+
+def test_detects_adr_edit_in_sandbox(tmp_path: Path) -> None:
+ _git(tmp_path, "init")
+ _git(tmp_path, "config", "user.email", "ci@test")
+ _git(tmp_path, "config", "user.name", "ci")
+ adr = tmp_path / "docs/adr"
+ adr.mkdir(parents=True)
+ (adr / "ADR-0001-test.md").write_text("v1\n")
+ _git(tmp_path, "add", ".")
+ _git(tmp_path, "commit", "-m", "add adr")
+ _git(tmp_path, "branch", "-M", "main")
+ (adr / "ADR-0001-test.md").write_text("v2\n")
+ _git(tmp_path, "checkout", "-b", "feature")
+ _git(tmp_path, "add", ".")
+ _git(tmp_path, "commit", "-m", "edit adr")
+
+ monkeypatch = pytest.MonkeyPatch()
+ monkeypatch.setattr("check_adrs.ROOT", tmp_path)
+ try:
+ assert find_modified_adrs("main") == ["docs/adr/ADR-0001-test.md"]
+ assert run_check(base="main") == 1
+ finally:
+ monkeypatch.undo()
+
+
+def test_new_adr_allowed(tmp_path: Path) -> None:
+ _git(tmp_path, "init")
+ _git(tmp_path, "config", "user.email", "ci@test")
+ _git(tmp_path, "config", "user.name", "ci")
+ adr = tmp_path / "docs/adr"
+ adr.mkdir(parents=True)
+ (adr / "ADR-0001-test.md").write_text("v1\n")
+ _git(tmp_path, "add", ".")
+ _git(tmp_path, "commit", "-m", "add adr")
+ _git(tmp_path, "branch", "-M", "main")
+ (adr / "ADR-0002-new.md").write_text("new\n")
+ _git(tmp_path, "checkout", "-b", "feature")
+ _git(tmp_path, "add", ".")
+ _git(tmp_path, "commit", "-m", "add adr 2")
+
+ monkeypatch = pytest.MonkeyPatch()
+ monkeypatch.setattr("check_adrs.ROOT", tmp_path)
+ try:
+ assert find_modified_adrs("main") == []
+ assert run_check(base="main") == 0
+ finally:
+ monkeypatch.undo()
diff --git a/simulator/tests/test_check_docs.py b/simulator/tests/test_check_docs.py
new file mode 100644
index 0000000..4460667
--- /dev/null
+++ b/simulator/tests/test_check_docs.py
@@ -0,0 +1,77 @@
+"""Tests for bin/check_docs.py — documentation CI rules."""
+
+from __future__ import annotations
+
+import json
+import sys
+from pathlib import Path
+
+import pytest
+
+SCRIPTS = Path(__file__).resolve().parents[2] / "bin"
+sys.path.insert(0, str(SCRIPTS))
+
+from check_docs import ( # noqa: E402
+ collect_anchors,
+ run_checks,
+ slug_heading,
+ split_link_target,
+)
+
+ROOT = Path(__file__).resolve().parents[2]
+GLOSSARY = ROOT / "docs/00-glossary.md"
+
+
+def test_slug_heading_matches_glossary_anchors() -> None:
+ assert slug_heading("T0 — hot") == "t0--hot"
+ assert slug_heading("T3 — warehouse") == "t3--warehouse"
+ assert slug_heading("Source of truth") == "source-of-truth"
+ assert slug_heading("Data & storage") == "data--storage"
+
+
+def test_glossary_term_anchors_exist() -> None:
+ anchors = collect_anchors(GLOSSARY)
+ for term in (
+ "t0--hot",
+ "t1--warm",
+ "t2--shared",
+ "t3--warehouse",
+ "t4--dev",
+ "source-of-truth",
+ "bulk-sync",
+ "offload",
+ ):
+ assert term in anchors, f"missing glossary anchor #{term}"
+
+
+def test_split_link_target() -> None:
+ assert split_link_target("foo.md#bar") == ("foo.md", "bar")
+ assert split_link_target("foo.md") == ("foo.md", None)
+
+
+def test_repo_docs_pass() -> None:
+ assert run_checks() == 0
+
+
+def test_broken_link_detected(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+ docs = tmp_path / "docs"
+ docs.mkdir()
+ (docs / "00-glossary.md").write_text("# Glossary\n\n## Data & storage\n")
+ (docs / "bad.md").write_text("See [missing](missing.md).\n")
+ rules = tmp_path / "bin"
+ rules.mkdir()
+ (rules / "docs_rules.json").write_text(
+ json.dumps(
+ {
+ "markdown_paths": ["docs/**/*.md"],
+ "glossary": {"file": "docs/00-glossary.md"},
+ "banned_link_targets": [],
+ "glossary_section_anchors": [],
+ "preferred_term_anchors": [],
+ "readability": {"forbid_bare_see_refs": False},
+ }
+ )
+ )
+ monkeypatch.setattr("check_docs.ROOT", tmp_path)
+ monkeypatch.setattr("check_docs.RULES_PATH", rules / "docs_rules.json")
+ assert run_checks() == 1