Merge branch 'fix/reuse-lease-token' into 'main'

fix(agent): reuse a valid lease token; rate-limited lease no longer blocks a deploy; 0.1.6

See merge request tikali/applications/monky/monky-deployd!11

CHANGELOG.md

@@ -1,6 +1,14 @@
 <!-- xlate:verbatim-fences -->
 # Changelog
 
+## 0.1.6 — 2026-09-07
+
+- **A valid lease token is reused across applies.** Every apply requested a new lease, so a failing deploy
+  retried by the 60 s timer burned tenancy's 5-leases-per-hour budget and then failed on
+  `LEASE_RATE_LIMITED` forever (env-qa-02 pilot). Now: reuse a lease-derived token while `lookup-self`
+  says it is valid; swap the bootstrap token for a lease once; and if tenancy rate-limits the lease while a
+  working token exists, apply with it and defer the swap instead of failing the deploy.
+
 ## 0.1.5 — 2026-09-07
 
 - **`tenancy.port` defaults to 443 everywhere** — the ansible role default and the `TenancyCfg` default now

README.md

@@ -23,9 +23,9 @@ you the enrolment JWT, a one-time **bootstrap deploy grant** and the read-only *
 
 ```sh
 T=<deploy token>   # read-only GitLab deploy token (read_package_registry); the kit carries it
-curl -sSf -H "DEPLOY-TOKEN: $T" https://scm.tikali.ai/api/v4/projects/69/packages/generic/monky-deployd/0.1.5/install.sh \
+curl -sSf -H "DEPLOY-TOKEN: $T" https://scm.tikali.ai/api/v4/projects/69/packages/generic/monky-deployd/0.1.6/install.sh \
   | sudo bash -s -- --env env-qa-02 --site cbs --token "$T" --bootstrap-file bootstrap.jwt --enrol-jwt ./monky-host.env-qa-02.jwt
-#   [--transport sdk|proxy|system] [--version 0.1.5] [--docker-data-root /home/docker-data] [--laptop] [--bao-ca openbao-ca.pem] [--source gitlab|gitea]
+#   [--transport sdk|proxy|system] [--version 0.1.6] [--docker-data-root /home/docker-data] [--laptop] [--bao-ca openbao-ca.pem] [--source gitlab|gitea]
 ```
 
 `install.sh` installs `ziti-edge-tunnel` (OpenZiti `jammy` suite) and `docker-compose-plugin` if

ansible/roles/monky_deployd/README.md

@@ -16,7 +16,7 @@ template → optional openbao-ca PEM → optional `monky-deployd-proxy.service`
 
 | var | note |
 |---|---|
-| `monky_deployd_version` | pinned release, e.g. `0.1.5` |
+| `monky_deployd_version` | pinned release, e.g. `0.1.6` |
 | `monky_deployd_download_token` | **vaulted**: GitLab deploy token, scope `read_package_registry` only (revocable) — the registry is private; seeded in OpenBao at `monky/monky-tenancy/deployd-download` key `token` (path/key are the operator's choice). Empty = no header (only works with the Gitea `base_url`) |
 | `monky_deployd_env_id` / `_site` / `_transport` | per host (`env-dev-06`, `cbs`, `sdk`) |
 | `monky_deployd_bootstrap_grant` | tenancy-minted deploy grant (1 h) — `ansible-vault` or a lookup at play time; empty keeps the existing token |

ansible/roles/monky_deployd/defaults/main.yml

@@ -1,7 +1,7 @@
 ---
 # monky_deployd — install and configure the Monky backend pull agent (MONKY-ADR-0028 §D).
 # Copy this role into osg1-07 (roles/monky_deployd) and roll to env-dev-06..09 after the pilot.
-monky_deployd_version: "0.1.5"
+monky_deployd_version: "0.1.6"
 monky_deployd_deb: "monky-deployd_{{ monky_deployd_version }}_amd64.deb"
 # PRIMARY download = the GitLab project's generic package registry on scm.tikali.ai. Inside the estate
 # gitea.cbs.tikali.net is split-horizon to jump1's RED EIP (10.10.0.175, no HTTP ingress), so backend

config.example.yaml

@@ -1,4 +1,4 @@
-# /etc/monky-deployd/config.yaml — monky-deployd v0.1.5 (MONKY-ADR-0028 §D)
+# /etc/monky-deployd/config.yaml — monky-deployd v0.1.6 (MONKY-ADR-0028 §D)
 # Written by packaging/install.sh (or the ansible role monky_deployd). YAML *subset*: maps, scalars,
 # simple lists, comments. Keys not listed here are a config error.
 

monky_deployd/__init__.py

@@ -4,4 +4,4 @@ Dials monky-tenancy over the mesh with the box's host identity, fetches the rend
 leases a deploy grant, logs in to OpenBao, reads its own secrets, runs `docker compose`,
 reports. Stdlib only; the optional `openziti` SDK is the `sdk` transport."""
 
-__version__ = "0.1.5"
+__version__ = "0.1.6"

monky_deployd/agent.py

@@ -277,7 +277,7 @@ class Agent:
         # secrets: lease -> login -> reads (values never logged; names only)
         entries = b.manifest.get("entries", [])
         if entries:
-            token = self._lease_login("apply")
+            token = self._token_for_apply()
             for e in entries:
                 self._values[e["var"]] = self.bao.kv_read(token, e["path"], cfg.env_id, e.get("version"))
             log.info("read %d secret(s): %s", len(entries), ", ".join(sorted(self._values)))
@@ -392,6 +392,29 @@ class Agent:
         if old and old != token:
             self.bao.revoke_self(old)
 
+    def _token_for_apply(self) -> str:
+        """The OpenBao token to read this bundle's secrets with. A lease-derived token that is
+        still valid is REUSED (a lease per apply burned tenancy's 5/h budget on every retry —
+        env-qa-02 pilot, 2026-09-07); the bootstrap token is swapped for a lease once; and if
+        tenancy rate-limits the lease while we hold a working token, apply with what we have
+        and swap later rather than fail the deploy."""
+        cfg = self.cfg
+        st = self.state.token
+        if self.token and st is not None and st.source == "lease":
+            try:
+                info = self.bao.lookup_self(self.token)
+                if int(info.get("ttl") or 0) > cfg.bao.renew_below_s:
+                    return self.token
+            except BaoError as exc:
+                log.info("lease token no longer valid (%s); re-leasing", exc)
+        try:
+            return self._lease_login("apply")
+        except RateLimited as exc:
+            if self.token:
+                log.warning("lease rate-limited (%s); applying with the current token, swap deferred", exc)
+                return self.token
+            raise
+
     def _lease_login(self, reason: str) -> str:
         assert self.tenancy is not None
         lease = self.tenancy.lease(reason)

packaging/install.sh

@@ -3,9 +3,9 @@
 #
 #   T=<read-only GitLab deploy token, scope read_package_registry>   # from the install kit / OpenBao
 #   curl -sSf -H "DEPLOY-TOKEN: $T" \
-#     https://scm.tikali.ai/api/v4/projects/69/packages/generic/monky-deployd/0.1.5/install.sh \
+#     https://scm.tikali.ai/api/v4/projects/69/packages/generic/monky-deployd/0.1.6/install.sh \
 #     | sudo bash -s -- --env env-qa-02 --site cbs --token "$T" --bootstrap-file bootstrap.jwt \
-#     [--transport sdk|proxy|system] [--version 0.1.5] [--enrol-jwt /path/monky-host.env-qa-02.jwt] \
+#     [--transport sdk|proxy|system] [--version 0.1.6] [--enrol-jwt /path/monky-host.env-qa-02.jwt] \
 #     [--laptop] [--source gitlab|gitea] [--docker-data-root /home/docker-data]
 #
 # --token / MONKY_DEPLOYD_TOKEN: the GitLab project is PRIVATE (its parent groups are private, so it
@@ -29,7 +29,7 @@
 set -euo pipefail
 umask 077
 
-DEFAULT_VERSION="0.1.5"
+DEFAULT_VERSION="0.1.6"
 # Download source. PRIMARY is the GitLab project's generic package registry on scm.tikali.ai: inside
 # the estate gitea.cbs.tikali.net is split-horizon to jump1's RED EIP (10.10.0.175), which has no HTTP
 # ingress, so backend boxes cannot reach the Gitea mirror (cbs/iac#102); scm.tikali.ai they can. The

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "monky-deployd"
-version = "0.1.5"
+version = "0.1.6"
 description = "Monky backend pull agent: checkin -> bundle -> lease -> OpenBao -> docker compose -> report, over the ziti mesh (MONKY-ADR-0028)"
 readme = "README.md"
 requires-python = ">=3.12"

tests/test_agent.py

@@ -107,7 +107,7 @@ def test_rollback_refused_unless_allowed(bootstrapped, tenancy, fake_docker):
     tenancy.set_files(first)
     assert tick(cfg) == EX_FAIL
     assert tenancy.reports[-1]["result"] == "failed" and "ROLLBACK_REFUSED" in tenancy.reports[-1]["detail"]
-    assert len(tenancy.leases) == 2  # a refused bundle never leases
+    assert len(tenancy.leases) == 1  # a refused bundle never leases; the 2nd apply reused the lease token
     tenancy.set_files(make_files(meta={"agent": {"allow_rollback": True}}))
     assert tick(cfg) == EX_OK
 
@@ -246,10 +246,9 @@ def test_legacy_approle_lease_is_refused_loudly(bootstrapped, tenancy, fake_dock
     assert "compose up" not in fake_docker.subcommands()
 
 
-def test_lease_rate_limited_is_temporary(bootstrapped, tenancy, fake_docker):
+# (test_lease_rate_limited_is_temporary was retired in 0.1.6: a rate-limited lease is only a
-    cfg = bootstrapped
+# temporary failure when NO working token exists; with one, the agent applies and defers the swap —
-    tenancy.lease_limit = 0
+# see test_rate_limited_lease_does_not_block_an_apply_when_a_token_exists.)
-    assert tick(cfg) == EX_TEMPFAIL
 
 
 def test_unhealthy_after_up_reports_failed_with_compose_logs(bootstrapped, tenancy, fake_docker):
@@ -320,3 +319,27 @@ def test_write_private_mode(tmp_path):
     p = tmp_path / "d" / "f"
     statemod.write_private(p, b"x")
     assert oct(p.stat().st_mode & 0o777) == "0o600" and not any(n.startswith(".f.") for n in os.listdir(p.parent))
+
+
+def test_second_apply_reuses_the_lease_token(bootstrapped, tenancy, bao, fake_docker):
+    """A valid lease-derived token is reused: a new bundle does NOT lease again (5/h budget —
+    env-qa-02 pilot: a retried deploy re-leased every 60 s and hit LEASE_RATE_LIMITED forever)."""
+    cfg = bootstrapped
+    assert tick(cfg) == EX_OK
+    assert len(tenancy.leases) == 1
+    tenancy.set_files(make_files(manifest=make_manifest(versions={"gemini_api_key": 1})))
+    assert tick(cfg) == EX_OK
+    assert len(tenancy.leases) == 1  # reused
+    st = statemod.load(cfg.state_path, ENV)
+    assert st.applied_sha == tenancy.desired_sha and st.token.source == "lease"
+
+
+def test_rate_limited_lease_does_not_block_an_apply_when_a_token_exists(bootstrapped, tenancy, bao, fake_docker):
+    """tenancy 429 on lease while the bootstrap token still works → apply with it, swap deferred."""
+    cfg = bootstrapped
+    tenancy.lease_limit = 0
+    assert tick(cfg) == EX_OK
+    assert tenancy.leases == []
+    st = statemod.load(cfg.state_path, ENV)
+    assert st.applied_sha == tenancy.desired_sha and st.token.source == "bootstrap"
+    assert tenancy.reports[-1]["result"] == "applied"