Add prose write test iterations

packages/std/ops/README.md

@@ -19,7 +19,7 @@ come back as `unresolved-intent` instead of terminal prompts.
 | `preflight.prose.md` | `prose preflight <file>` | Check that dependencies are installed and environment variables are set |
 | `wire.prose.md` | `prose run std/ops/wire` | Run Forme wiring to produce an execution manifest |
 | `status.prose.md` | `prose status` | Show recent runs with system name, duration, and pass/fail status |
-| `prose-author.prose.md` | `prose write [--out <path>] [--apply] [--run] [request...]` | Interactive-by-default authoring of a validated OpenProse package from rough English or pseudo-Prose; `--out --apply` may write it, and host adapters that support `--run` expand it to write/apply followed by ordinary `prose run <generated-root>` |
+| `prose-author.prose.md` | `prose write [--out <path>] [--apply] [--run] [--test-iterations <0-3>] [request...]` | Interactive-by-default authoring of a validated OpenProse package from rough English or pseudo-Prose; `--out --apply` may write it, CLI host adapters may test generated `kind: test` files after apply, and `--run` expands to ordinary `prose run <generated-root>` |
 | `diagnose.prose.md` | `prose run std/ops/diagnose` | Diagnose why a run failed -- root cause analysis with fix recommendations |
 | `profiler.prose.md` | `prose run std/ops/profiler` | Profile a run for cost, tokens, and time using actual API session data |
 

skills/open-prose/SKILL.md

@@ -128,7 +128,7 @@ executing the system. The shell executable is the agent runner, e.g.
 | `prose run runtime/judge-responsibility.prose.md` | Resolve from the OpenProse skill root; judge one responsibility from activation context |
 | `prose run <host>/<owner>/<repo>[/path]` | Resolve installed dependency service or system, detect format, then route as above |
 | `prose run std/...` / `co/...` | Expand OpenProse package shorthand, resolve installed dependency service or system, then route as above |
-| `prose write [--out <path>] [--apply] [--run] [request...]` | Interactive-by-default authoring: load `contract-markdown.md`, `guidance/tenets.md`, and `guidance/authoring.md`; run `std/ops/prose-author`; scan the local landscape read-only, decide shape/root/path, load shape-specific guidance, ask a small number of targeted `ask_user` questions when the host can support them, then return a fully validated source package. If the caller or host marks the run non-interactive, return `unresolved-intent` with the missing decisions instead of guessing. Apply generated files only when the caller explicitly passes apply permission, normally through `--out <path> --apply`; `--run` is a host-adapter macro that implies apply permission and expands to an ordinary `prose run <generated-root>` only after authoring succeeds |
+| `prose write [--out <path>] [--apply] [--run] [--test-iterations <0-3>] [request...]` | Interactive-by-default authoring: load `contract-markdown.md`, `guidance/tenets.md`, and `guidance/authoring.md`; run `std/ops/prose-author`; scan the local landscape read-only, decide shape/root/path, load shape-specific guidance, ask a small number of targeted `ask_user` questions when the host can support them, then return a fully validated source package. If the caller or host marks the run non-interactive, return `unresolved-intent` with the missing decisions instead of guessing. Apply generated files only when the caller explicitly passes apply permission, normally through `--out <path> --apply`; `--run` is a host-adapter macro that implies apply permission and expands to an ordinary `prose run <generated-root>` only after authoring succeeds. `--test-iterations` is a CLI host-adapter macro with default `1`; `0` disables generated-test execution, and `3` is the maximum bounded repair loop |
 | `prose lint <file.prose.md>` | Validate Contract Markdown structure, headers, frontmatter, contracts, shapes, and wiring |
 | `prose preflight <file.prose.md>` | Check dependencies and `### Environment` declarations without executing |
 | `prose test <path>` | Load `contract-markdown.md`, `state/README.md` plus the selected backend, and `prose.md`; run `kind: test` file(s) |
@@ -149,6 +149,18 @@ authoring succeeds. A host that cannot perform this macro must reject
 `prose write --run` before authoring and must not pass the macro into
 `prose-author`.
 
+`prose write --test-iterations` is also a host-adapter macro for apply-enabled
+CLI writes. The CLI host adapter defaults to one generated-test attempt: it
+runs ordinary `prose test` for generated `kind: test` files after authoring
+succeeds, repairs by invoking a new apply-enabled `prose-author` pass only
+between failed test attempts, and stops at the requested bound. The macro is
+off when set to `0`, and the maximum is `3`. Plain in-session `prose write`
+still routes to `prose-author`; a non-CLI host that cannot perform this macro
+must reject an explicit `--test-iterations` option before authoring, must not
+pass the test-iteration macro into `prose-author`, and must not perform
+optional giving-back, memory, or mycelium note side effects while executing a
+forwarded/non-interactive write loop.
+
 There is one skill: `open-prose`. Do not look for separate `prose-run`,
 `prose-lint`, `prose-compile`, or `prose-boot` skills.
 

skills/open-prose/help.md

@@ -48,7 +48,7 @@ Options:
 | `prose compile [path] [--out <dir>]` | Compile source into `<openprose-root>/dist/manifest.next.json` |
 | `prose serve` | Serve the active IR as local cron and HTTP trigger adapters |
 | `prose run <file.prose.md>` | Run a service or system |
-| `prose write [--out <path>] [--apply] [--run] [request...]` | Interactive-by-default authoring from rough English/pseudo-Prose into a validated source package; `--out <path> --apply` writes it after lint passes, and host adapters that support `--run` expand it to write/apply followed by ordinary `prose run <generated-root>` |
+| `prose write [--out <path>] [--apply] [--run] [--test-iterations <0-3>] [request...]` | Interactive-by-default authoring from rough English/pseudo-Prose into a validated source package; `--out <path> --apply` writes it after lint passes, supported host adapters run generated tests after apply, and `--run` expands to ordinary `prose run <generated-root>` |
 | `prose lint <file.prose.md>` | Validate structure, schema, and contracts |
 | `prose preflight <file.prose.md>` | Check dependencies and environment |
 | `prose test <test.prose.md>` | Run tests with assertions |

skills/open-prose/prose.md

@@ -45,7 +45,7 @@ codex exec "prose run system.prose.md"
 | `prose run <owner>/<repo>`       | Reserved for the OpenProse registry (future home at `p.prose.md`)         |
 | `prose run ...@<version>`        | Pin to a SHA or tag; require that version in `<openprose-root>/deps/`                     |
 | `prose run ... --offline`        | Require disk-only resolution; error if not in `<openprose-root>/deps/`                   |
-| `prose write [--out <path>] [--apply] [--run] [request...]` | Interactive-by-default authoring through `std/ops/prose-author`, asking targeted shape/root questions when supported and returning a validated source package; `--out --apply` writes it when permitted, and host adapters that support `--run` expand it to write/apply followed by ordinary `prose run <generated-root>` |
+| `prose write [--out <path>] [--apply] [--run] [--test-iterations <0-3>] [request...]` | Interactive-by-default authoring through `std/ops/prose-author`, asking targeted shape/root questions when supported and returning a validated source package; `--out --apply` writes it when permitted, host adapters that support `--test-iterations` run generated tests after apply, and host adapters that support `--run` expand it to write/apply followed by ordinary `prose run <generated-root>` |
 | `prose lint <file.prose.md>`      | Validate structure, schema, shapes, and contracts               |
 | `prose preflight <file.prose.md>` | Check dependencies, declared tools, and environment variables   |
 | `prose test <path>`         | Run test(s) and report results                                  |

tools/cli/README.md

@@ -77,6 +77,7 @@ prose run std/evals/inspector
 prose run std/evals/prose-contributor -- subjects: 20260406-201439-1a3369
 prose write "draft a release readiness responsibility"
 prose write --out src/release-readiness --run "draft a release readiness responsibility"
+prose write --out src/release-readiness --apply --test-iterations=3 "draft a release readiness responsibility"
 cat brief.txt | prose write --harness codex-sdk
 prose run std/evals/inspector --harness codex-sdk
 prose run co/systems/company-repo-checker --harness claude-sdk
@@ -169,6 +170,18 @@ then starts a separate ordinary `prose run` for the generated root file only
 after authoring succeeds. Directory targets run `<path>/index.prose.md`; file
 targets must end in `.prose.md`.
 
+Generated-test execution is also a CLI host-adapter macro. After apply-enabled
+authoring succeeds, the CLI discovers generated `kind: test` files under
+`--out` and runs ordinary `prose test` for each one. `--test-iterations=1` is
+the default for `--apply` and `--run`, `--test-iterations=0` disables the test
+loop, and `--test-iterations=3` allows up to three test attempts with repair
+authoring passes between failures. The test loop never commits generated files and does
+not ask the authoring run to perform optional giving-back, memory, or mycelium
+note side effects. Repair prompts include captured failing test output capped
+at 12 KB; the side-effect ban and target-path repair instruction are prepended
+before that output. If the loop exhausts its iteration bound, the CLI returns
+the final failing `prose test` exit code rather than a distinct sentinel.
+
 `--out` is a validated, root-relative target contract passed to the authoring
 harness. The CLI rejects absolute paths, parent traversal, and file targets
 that do not end in `.prose.md`; the actual write is still performed by the
@@ -184,6 +197,7 @@ prose run src/systems/reviewer.prose.md
 prose write "draft a release readiness responsibility"
 prose write --out src/reviewer --apply "draft a reviewer system"
 prose write --out src/reviewer --run "draft a reviewer system"
+prose write --out src/reviewer --apply --test-iterations=0 "draft a reviewer system"
 prose write < brief.txt
 prose run co/systems/company-repo-checker --harness claude-sdk
 prose upgrade