From e278597ada5229c6b438cce8c516f6067bc84dfa Mon Sep 17 00:00:00 2001
From: kjgbot <kjgbot@agentrelay.dev>
Date: Thu, 10 Sep 2026 21:37:31 +0200
Subject: [PATCH] feat(testdata): promote shakedown scenarios into
 testdata/shakedown/

The 2026-09-10 launch-prep shakedown ran six canonical scenarios against
flows run. Their sources were snapshotted at
evidence/shakedown-0910/flow-sources.md on the shakedown branch but were
not on main, so nothing on main pointed at how to exercise the six shapes.

Extract the non-supplemental ones (hello-world, agent-inline, deep-cwd,
chained, error-path/error-dependency, observer) into testdata/shakedown/,
each still a self-contained YAML that flows run accepts unmodified. Add a
README naming what each scenario proves and which issue it covers (#262,
#263, #269/#286, #273, #275).

Supplemental variants stay on the shakedown branch as evidence rather
than as canonical examples; the README says so, so a future author knows
where to look.

Session-Id: efeda5df-9b7c-48d4-b2ce-957f5bef0a82
---
 testdata/shakedown/README.md                  | 32 +++++++++++++++++++
 testdata/shakedown/agent-inline.flow.yaml     | 14 ++++++++
 testdata/shakedown/chained.flow.yaml          | 30 +++++++++++++++++
 testdata/shakedown/deep-cwd.flow.yaml         |  6 ++++
 testdata/shakedown/error-dependency.flow.yaml |  7 ++++
 testdata/shakedown/error-path.flow.yaml       | 10 ++++++
 testdata/shakedown/hello-world.flow.yaml      |  6 ++++
 testdata/shakedown/observer.flow.yaml         |  6 ++++
 8 files changed, 111 insertions(+)
 create mode 100644 testdata/shakedown/README.md
 create mode 100644 testdata/shakedown/agent-inline.flow.yaml
 create mode 100644 testdata/shakedown/chained.flow.yaml
 create mode 100644 testdata/shakedown/deep-cwd.flow.yaml
 create mode 100644 testdata/shakedown/error-dependency.flow.yaml
 create mode 100644 testdata/shakedown/error-path.flow.yaml
 create mode 100644 testdata/shakedown/hello-world.flow.yaml
 create mode 100644 testdata/shakedown/observer.flow.yaml

diff --git a/testdata/shakedown/README.md b/testdata/shakedown/README.md
new file mode 100644
index 000000000..cfb3e8345
--- /dev/null
+++ b/testdata/shakedown/README.md
@@ -0,0 +1,32 @@
+Shakedown flows — 2026-09-10 v2 launch prep
+
+These are the six canonical scenarios the launch-prep shakedown ran against
+`flows run`, extracted from `evidence/shakedown-0910/flow-sources.md` on branch
+`shakedown/v2-launch-0910`. Their run transcripts live under
+`evidence/shakedown-0910/*.txt` on that branch (drafted at PR #281).
+
+Scenario map:
+
+- `hello-world.flow.yaml` — pure deterministic; no external deps. Baseline
+  that the CLI's happy path works.
+- `agent-inline.flow.yaml` — inline `agents: { drafter: { cli, model } }`.
+  Verifies #263: named-agent inline models work without a `flows.json` in
+  the current or any ancestor directory.
+- `deep-cwd.flow.yaml` — a deterministic flow to run from a working
+  directory deep enough to push the daemon socket past macOS's SUN_LEN.
+  Verifies #262: the hashed-under-tmp derivation.
+- `chained.flow.yaml` — the flagship `llm → agent → deterministic` shape,
+  with typed JSON output. **Currently blocked**: no local `llm` worker
+  path (#273) and no declarative upstream-output binding (#275).
+- `error-path.flow.yaml` — deliberately misspells a CLI to exercise the
+  refusal shape. Sibling `error-dependency.flow.yaml` names a nonexistent
+  `dependsOn` step.
+- `observer.flow.yaml` — a small run intended to be paired with a live
+  `RELAYCAST_WORKSPACE_KEY` so `flows run` mints an observer URL and prints
+  it on stdout. Verifies #269 / #286.
+
+Supplemental variants (agent-codex, chained-codex, chained-llm.flow.ts,
+binding, etc.) remain snapshotted at
+`evidence/shakedown-0910/flow-sources.md` on the shakedown branch rather
+than promoted into this directory: they are exploratory shape-tests, not
+canonical scenarios. Promote one if it becomes a first-class example.
diff --git a/testdata/shakedown/agent-inline.flow.yaml b/testdata/shakedown/agent-inline.flow.yaml
new file mode 100644
index 000000000..c1157b022
--- /dev/null
+++ b/testdata/shakedown/agent-inline.flow.yaml
@@ -0,0 +1,14 @@
+version: "0.1.0"
+name: agent-inline
+agents:
+  drafter:
+    cli: claude
+    model: claude-sonnet-4-6
+steps:
+  - id: draft
+    type: agent
+    agent: drafter
+    instruction: Reply with exactly hello. Do not use tools or modify files.
+    verification:
+      type: output_contains
+      value: hello
diff --git a/testdata/shakedown/chained.flow.yaml b/testdata/shakedown/chained.flow.yaml
new file mode 100644
index 000000000..141662224
--- /dev/null
+++ b/testdata/shakedown/chained.flow.yaml
@@ -0,0 +1,30 @@
+version: "0.1.0"
+name: chained
+agents:
+  drafter:
+    cli: claude
+    model: claude-sonnet-4-6
+steps:
+  - id: extract
+    type: llm
+    cli: claude
+    model: claude-sonnet-4-6
+    prompt: 'Return only JSON: {"message":"hello"}'
+    output:
+      type: object
+      required: [message]
+      properties:
+        message: {type: string}
+      additionalProperties: false
+  - id: draft
+    type: agent
+    agent: drafter
+    dependsOn: [extract]
+    instruction: 'Repeat the message from this JSON as plain text: {{steps.extract.output}}. Do not use tools or modify files.'
+    verification:
+      type: output_contains
+      value: hello
+  - id: write
+    type: deterministic
+    dependsOn: [draft]
+    command: "printf '%s' '{{steps.draft.output}}' > shakedown-result.txt"
diff --git a/testdata/shakedown/deep-cwd.flow.yaml b/testdata/shakedown/deep-cwd.flow.yaml
new file mode 100644
index 000000000..17135a148
--- /dev/null
+++ b/testdata/shakedown/deep-cwd.flow.yaml
@@ -0,0 +1,6 @@
+version: "0.1.0"
+name: deep-cwd
+steps:
+  - id: hello
+    type: deterministic
+    command: printf hello
diff --git a/testdata/shakedown/error-dependency.flow.yaml b/testdata/shakedown/error-dependency.flow.yaml
new file mode 100644
index 000000000..c9bd9f800
--- /dev/null
+++ b/testdata/shakedown/error-dependency.flow.yaml
@@ -0,0 +1,7 @@
+version: "0.1.0"
+name: error-dependency
+steps:
+  - id: broken
+    type: deterministic
+    dependsOn: [does-not-exist]
+    command: printf hello
diff --git a/testdata/shakedown/error-path.flow.yaml b/testdata/shakedown/error-path.flow.yaml
new file mode 100644
index 000000000..f66f03630
--- /dev/null
+++ b/testdata/shakedown/error-path.flow.yaml
@@ -0,0 +1,10 @@
+version: "0.1.0"
+name: error-path
+steps:
+  - id: broken
+    type: agent
+    cli: claudee
+    instruction: Reply hello.
+    verification:
+      type: output_contains
+      value: hello
diff --git a/testdata/shakedown/hello-world.flow.yaml b/testdata/shakedown/hello-world.flow.yaml
new file mode 100644
index 000000000..549b07a47
--- /dev/null
+++ b/testdata/shakedown/hello-world.flow.yaml
@@ -0,0 +1,6 @@
+version: "0.1.0"
+name: hello-world
+steps:
+  - id: hello
+    type: deterministic
+    command: printf hello
diff --git a/testdata/shakedown/observer.flow.yaml b/testdata/shakedown/observer.flow.yaml
new file mode 100644
index 000000000..37569a81e
--- /dev/null
+++ b/testdata/shakedown/observer.flow.yaml
@@ -0,0 +1,6 @@
+version: "0.1.0"
+name: observer
+steps:
+  - id: hello
+    type: deterministic
+    command: printf hello