deviatdd 2.23.0__tar.gz → 2.23.1__tar.gz

{deviatdd-2.23.0 → deviatdd-2.23.1}/CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Added
+- **ChatGPT Codex is a first-class setup + meso/micro backend.** `--agent codex` (and the interactive prompt) is a valid install target. Setup writes packaged skills to `.agents/skills/deviatdd/SKILL.md` plus one `.agents/skills/<command>/SKILL.md` per slash command (Codex CLI 0.117+ dropped `.codex/prompts`). `[agent].backend = "codex"` is persisted. Dispatch uses `codex exec --sandbox workspace-write --ask-for-approval never` with the existing stdin prompt path and `--model` injection. Transport stays `cli`. Pinned by `tests/test_cli/test_setup.py::TestSetupCodex` and `tests/test_core/test_agent.py::TestCodexBackendRegistration`.
 - **On-demand GitHub Actions Release workflow (`workflow_dispatch`).** A maintainer runs Actions → Release → Run workflow. The job computes the next SemVer from conventional commits since the current `pyproject.toml` version (`feat` → minor, `fix` → patch, `BREAKING CHANGE` / `feat!` / `fix!` → major; chore/docs/test/ci/style/refactor still bump patch), writes `pyproject.toml` + the `deviatdd` version in `uv.lock`, commits `chore(release): version X.Y.Z` on the default branch, tags `vX.Y.Z`, and publishes with `uv build` / `uv publish --trusted-publishing always` (PyPI trusted publishing via GitHub OIDC; `contents: write` + `id-token: write`; no `PYPI_API_TOKEN` and no GitHub secret). Optional inputs: `bump` (`auto` / `patch` / `minor` / `major`) and `dry_run` (print the version; skip commit/tag/publish). Refuses a non-default branch unless `dry_run` is true. Does not rewrite `CHANGELOG.md` (stays `[Unreleased]`). Operator adds a pending PyPI trusted publisher for `wernerbisschoff/deviatdd` workflow `release.yml` (no environment). Local fallback remains `mise run publish`. Pinned by `tests/test_release/test_next_version.py`.
 - **COMPLETED `tasks.jsonl` rows now persist runner-validated JUDGE evidence (GH-84).** After the #65 mechanical gate accepts a TDD completion path (`skip_refactor` / bare `COMPLIANCE_PASS` / post-REFACTOR complete / adjudicated already-exists), `_append_status_transition(..., "COMPLETED")` copies `HandoverManifest.evidence` (`ac`, `test_path`, `test_quote`, `impl_path`, `impl_quote`) onto an optional `TaskRecord.evidence` bundle and stamps `red` (`session.red_commit_sha`) plus `green`/`head` (`HEAD` at the write). TDD complete fail-closes when the plan contract has `AC-PLAN-NNN` tokens and the bundle is missing or does not cover them (`evaluate_judge_evidence`, no new matcher). EXECUTE / IMMEDIATE / DIRECT stay ungated; enabling/infra plans with no AC tokens may complete with empty evidence. `deviate inspect tasks show` prints the field when present. Session files are not the proof store. Pinned by `tests/test_micro/test_completed_evidence.py`, `tests/test_state/test_ledger.py`, and `tests/test_cli/test_inspect.py`.
 - **`deviate micro run --review` pauses before each phase commit (GH-101).** After the agent finishes a phase and tests/lint have run, `--review` (and `--all --review`) halt before `_commit_phase` / `_commit_phase_with_recovery` (`git add -A`), print `REVIEW_PAUSE <phase> <task_id>`, leave the worktree dirty for herdr/hunk, and wait for TTY confirmation (`Enter` / yes). Then the runner commits as today and continues. Pause applies to RED, GREEN, REFACTOR, and EXECUTE — not JUDGE feedback commits. RED is still committed before GREEN so `session.red_commit_sha` remains available for JUDGE `revert_to_red`. Non-TTY / `--json` / missing stdin fail closed with `REVIEW_REQUIRES_TTY` and never auto-commit past the flag. Off by default; no config key. The pause is one helper (`_maybe_review_pause`) in front of `_commit_phase`, not a copy in each phase. Pinned by `tests/test_micro/test_review_pause.py`.
@@ -55,6 +56,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **`/deviate-merge` no longer auto-pushes after the squash-merge commit; the push gate runs inline and the network push is opt-in.** The slash command previously ran `git push` as its final step. As of v2.4.0 the squash-merge commit lands on `main`, then a new `push_gate` step inlines the body of `.githooks/pre-push` (lint + format-check + testmon-driven affected tests with the warm-cache / full-suite fallback — bash 3.2 portable, `GIT_DIR` reset + trap preserved) so the safety net fires even though no `git push` happens yet. After the gate passes the skill asks the operator whether to `git push` (which fires the real `pre-push` hook and re-runs the same gate) or stop and push manually. The squash-merge commit and the ledger transition inside it are durable on `main` regardless of the push outcome — only the network push is deferred. New failure states: `Push_Gate_Failed` (inline gate non-zero), `Push_Failed` (`git push` non-zero, raw stderr surfaced), `Push_Deferred` (user chose "Stop — I'll push manually"). Inline gate body and `.githooks/pre-push` body must stay byte-equivalent; divergence is pinned by `tests/test_meso/test_auto_prompt_templates.py::TestMergePromptPushGate::test_hook_and_prompt_agree_on_gate_body` (which compares non-blank non-comment lines in both bodies and fails on drift in either direction) plus 3 supporting assertions on the upstream-first logic, the testmon fallback, and the prompt structure. Prompt: `src/deviate/prompts/commands/deviate-merge.md` (v2.3.0 → v2.4.0). Spec mirrors updated: `specs/DeviaTDD-architecture.md` (Merge bullet, new `**Push gate + opt-in push (v2.4.0)**` sub-bullet) and `specs/DeviaTDD-api.md` (new `**/deviate-merge push behavior (v2.4.0)**` entry under the `deviate merge` reference).
 
 ### Fixed
+- **`deviate setup --agent X` now installs slash commands and the packaged `deviatdd` skill only for X.** Previously setup wrote into all five of `.claude/`, `.opencode/`, `.factory/`, `.pi/`, and `.omp/` regardless of `--agent`; the flag only persisted `[agent].backend`. `droid` still writes `.factory/` only. Unknown `--agent` values stay fail-closed. Pinned by `tests/test_cli/test_setup.py::TestSetupSelectedAgentIsolation`.
 - **JUDGE prompt injection now uses the Judge-Feedback-stripped task card (GH-118).** `_build_auto_prompt("judge")` still reads the raw card via `_task_card_text`, then applies the same `_strip_judge_feedback` pass that `resolve_task_ac_tokens` already used for token resolution (#89). Prior-round `**Judge Feedback**` bullets and their continuation lines (including false ownership claims such as "AC-PLAN-003 belongs to a later task") no longer appear in `<task_card>`. Token resolution, `_append_judge_feedback`, and the COMPLETED evidence gate are unchanged. Specs: `specs/DeviaTDD-api.md`, `specs/DeviaTDD-architecture.md`. Pinned by `tests/test_micro/test_judge.py::TestJudgePromptStripsJudgeFeedback`.
 - **Ledger appenders no longer concatenate a new JSONL record onto a last line that lacks a trailing newline (GH-117).** `_append_record` and `_append_with_compound_key` insert a leading `\n` when the file is non-empty and does not already end in a newline, so `_read_ledger` cannot skip a fused BACKLOG+SPECIFIED line. `claim_issue` now writes through `append_issue_transition` instead of a raw `"a"` append. Pinned by `tests/test_state/test_ledger.py` and `tests/test_core/test_issues.py`.
 - **JUDGE handover parse now recovers unescaped `"` inside evidence quote fields (GH-116).** `AgentBackend.parse_output` retries `yaml.safe_load` after rewriting broken `quote` / `test_quote` / `impl_quote` double-quoted scalars as `|` block scalars, so citations such as `assert "YAGNI" in text` and `== ["AC-PLAN-002"]` no longer raise `MalformedHandoverManifestError`. Well-formed YAML is unchanged. The auto judge prompt also prefers `|` block scalars when a quote contains `"`. Pinned by `tests/test_core/test_agent.py`.

{deviatdd-2.23.0 → deviatdd-2.23.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: deviatdd
-Version: 2.23.0
+Version: 2.23.1
 Summary: DeviaTDD CLI — agent orchestration framework
 Project-URL: Homepage, https://github.com/wernerbisschoff/deviatdd
 Project-URL: Repository, https://github.com/wernerbisschoff/deviatdd
@@ -74,11 +74,11 @@ deviate --version                # confirm install
 
 # Bootstrap a new project + install slash commands into your agent of
 # choice. Does it all in one shot: scaffolds .deviate/, specs/constitution.md,
-# governance blocks, and installs /deviate-* slash commands for every
-# supported agent. The --agent flag picks the default backend persisted
-# to .deviate/config.toml (slash commands themselves are installed to all
-# supported agent directories regardless).
-deviate setup --agent claude     # or: opencode | pi | droid | factory | omp
+# governance blocks, and installs /deviate-* slash commands for the
+# selected agent only. The --agent flag picks the backend persisted to
+# .deviate/config.toml and is the only install target (`droid` writes
+# `.factory/`; `codex` writes `.agents/skills/`).
+deviate setup --agent claude     # or: opencode | pi | droid | factory | omp | codex
 ```
 
 Once setup is done, drive the entire lifecycle from inside your agent. Each phase emits a single artifact, commits it, and (at the two gates) pauses for human review.

{deviatdd-2.23.0 → deviatdd-2.23.1}/README.md

@@ -41,11 +41,11 @@ deviate --version                # confirm install
 
 # Bootstrap a new project + install slash commands into your agent of
 # choice. Does it all in one shot: scaffolds .deviate/, specs/constitution.md,
-# governance blocks, and installs /deviate-* slash commands for every
-# supported agent. The --agent flag picks the default backend persisted
-# to .deviate/config.toml (slash commands themselves are installed to all
-# supported agent directories regardless).
-deviate setup --agent claude     # or: opencode | pi | droid | factory | omp
+# governance blocks, and installs /deviate-* slash commands for the
+# selected agent only. The --agent flag picks the backend persisted to
+# .deviate/config.toml and is the only install target (`droid` writes
+# `.factory/`; `codex` writes `.agents/skills/`).
+deviate setup --agent claude     # or: opencode | pi | droid | factory | omp | codex
 ```
 
 Once setup is done, drive the entire lifecycle from inside your agent. Each phase emits a single artifact, commits it, and (at the two gates) pauses for human review.

{deviatdd-2.23.0 → deviatdd-2.23.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "deviatdd"
-version = "2.23.0"
+version = "2.23.1"
 description = "DeviaTDD CLI — agent orchestration framework"
 readme = "README.md"
 license = "MIT"

{deviatdd-2.23.0 → deviatdd-2.23.1}/specs/DeviaTDD-api.md

@@ -31,14 +31,15 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
   constitution. `deviate init pre` continues to scaffold the constitution independently.
   slash commands + 1 standalone `tools-mcp-servers` command (for Factory Droid)
   — 25 flat `.md` files total in the Factory install; 24 in every other agent
-  `.{agent}/prompts/` for Pi) during `deviate setup`. Commands land in all agent
-  directories — `.claude/commands/`, `.opencode/commands/`,
-  `.factory/commands/`, `.pi/prompts/`, `.omp/prompts/` — in a single invocation, regardless of which agent was passed
-  via `--agent`. Each command is a flat `<name>.md` file with a minimal YAML
-  frontmatter (`name:` + `description:`). The agent backend selected via `--agent`
-  (`opencode`, `claude`, `droid`, `factory`, `pi`, `omp`) is persisted to `[agent].backend` in
-  `config.toml` for use by the meso/micro layers; it does **not** gate which agent
-  directories receive commands.
+  `.{agent}/prompts/` for Pi) during `deviate setup`. Commands land only in the
+  selected agent's directory — `.claude/commands/`, `.opencode/commands/`,
+  `.factory/commands/` (`--agent factory` and `--agent droid`), `.pi/prompts/`,
+  `.omp/prompts/`, or Codex skills under `.agents/skills/<name>/SKILL.md`.
+  Each command is a flat `<name>.md` file (or a Codex `SKILL.md`) with a
+  minimal YAML frontmatter (`name:` + `description:`). The agent selected via
+  `--agent` (`opencode`, `claude`, `droid`, `factory`, `pi`, `omp`, `codex`)
+  is persisted to `[agent].backend` in `config.toml` and is the only install
+  target.
 
   **Single-source prompt derivation:** for each of the 11 overlapping phases
   (`explore`, `research`, `prd`, `shard`, `plan`, `tasks`, `red`, `green`,
@@ -84,8 +85,8 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
   duplicates rules), preserves user-authored `.gitattributes` content,
   and stages the file via `deviate init post` alongside the other
   scaffolded artifacts.
-* **Agent Selection:** Accepts `--agent [claude|opencode|droid|factory|pi]` to override
-  auto-detect. If omitted, the persisted value is reused; if no persisted value exists and
+* **Agent Selection:** Accepts `--agent [claude|opencode|droid|factory|pi|omp|codex]` to override
+  the persisted backend. If omitted, the persisted value is reused; if no persisted value exists and
   the session is interactive, a Rich `Prompt.ask` menu is shown. In non-interactive mode
   the command halts with `NO_AGENT_SELECTED` and a directive to re-run with `--agent`.
 * **Execution Modes:**
@@ -106,7 +107,7 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
   `${VARIABLE}` resolver described in earlier revisions of this spec has been removed.
 * **Input Parameters:**
   * `--agent-export-mode [local|global]` (Defaults to `local`)
-  * `--agent [claude|opencode|droid|factory|pi]` (Override auto-detect)
+  * `--agent [claude|opencode|droid|factory|pi|omp|codex]` (Override persisted backend)
   * `--no-claim-remote` (Disable push-as-lock; merges `claim_remote = false` into
   * `--libref` (Force-enable `libref` CLI integration; merges `use_libref = true` into
     `config.toml`)
@@ -134,9 +135,10 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
   * `specs/constitution.md` — Resolved boilerplate constitution
   * `AGENTS.md` — Symlink to `CLAUDE.md` (or vice-versa if only `AGENTS.md`
     existed pre-setup). Created by `_linkify_governance_files`; idempotent.
-  * `.claude/commands/`, `.opencode/commands/`, `.factory/commands/`,
-    supported agent (24 `deviate-*` + 1 standalone `tools-mcp-servers`
-    for Factory = 25 flat `.md` files total in that one directory)
+  * Selected-agent command install only: `.claude/commands/`,
+    `.opencode/commands/`, `.factory/commands/`, `.pi/prompts/`,
+    `.omp/prompts/`, or `.agents/skills/<name>/SKILL.md` for Codex.
+    Factory also receives the standalone `tools-mcp-servers` command.
 
 #### `deviatdd` Skill (Project-Local Single Skill)
 
@@ -147,21 +149,19 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
   `src/deviate/cli/__init__.py`, called from `setup()` after
   `_install_commands_to_agents(...)`. Idempotent (content-equality skip
   mirrors `install_command`'s contract).
-* **Install targets (all five `active_agents`):** the skill is written
-  to `<workdir>/.<agent>/skills/deviatdd/SKILL.md` for every agent
-  platform that `setup` provisions commands for, regardless of whether
-  each platform documents a project-local skills convention. Mirrors
-  `_install_commands_to_agents`'s write-everywhere policy — every
-  operator using `--agent <platform>` gets the skill at the canonical
-  skills directory for their platform, ready to be picked up if/when
-  that platform ships a discovery convention.
+* **Install target (selected agent only):** the skill is written to
+  `<workdir>/.<agent>/skills/deviatdd/SKILL.md` for the agent passed to
+  `--agent` (or the persisted backend / interactive prompt). `droid`
+  normalizes to `factory`. Codex writes
+  `<workdir>/.agents/skills/deviatdd/SKILL.md` and does **not** write
+  `.codex/prompts` or `.codex/commands`.
   * `claude` -> `<workdir>/.claude/skills/deviatdd/SKILL.md`
     (verified — same form as user-level `~/.claude/skills/<name>/SKILL.md`).
   * `opencode` -> `<workdir>/.opencode/skills/deviatdd/SKILL.md`
     (no documented project-local skills convention; file on disk for
     forward-compat).
   * `factory` -> `<workdir>/.factory/skills/deviatdd/SKILL.md`
-    (same as opencode).
+    (same as opencode; `--agent droid` uses this path).
   * `pi` -> `<workdir>/.pi/skills/deviatdd/SKILL.md`
     (verified — `pi@latest` docs at
     `packages/coding-agent/docs/skills.md` list `.pi/skills/` as a
@@ -171,6 +171,9 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
     `~/.omp/agent/managed-skills/<name>/SKILL.md` and via a
     settings-driven `skills` array; operators can register the
     project-local file via OMP's settings).
+  * `codex` -> `<workdir>/.agents/skills/deviatdd/SKILL.md`
+    (Codex CLI 0.117+ official project-local discovery). Each packaged
+    slash command is also installed as `.agents/skills/<name>/SKILL.md`.
 * **Scope:** Unified Meso and Micro orchestration. The skill first runs
   `deviate meso run`. In an existing feature worktree, the runner validates
   `plan.md` and `tasks.md`, skips completed phases, and resumes at Tasks when
@@ -218,14 +221,17 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
 * **`.gitignore` exclusions:** `_ensure_root_gitignore` adds
   `*/skills/deviatdd/` to the entries tuple alongside
   `*/commands/deviate-*.md` and `*/prompts/deviate-*.md`. The
-  single-level wildcard covers all five agent platforms
-  (`.claude/`, `.opencode/`, `.factory/`, `.pi/`, `.omp/`) with one
-  pattern. The single-level prefix (`*/`, not `**/`) is critical: it
+  single-level wildcard covers every selected-agent skill install
+  (`.claude/`, `.opencode/`, `.factory/`, `.pi/`, `.omp/`, `.agents/`)
+  with one pattern. `*/skills/deviate-*/` covers Codex per-command
+  skill dirs. The single-level prefix (`*/`, not `**/`) is critical: it
   scopes the pattern to the project root, never matching the
   source-of-truth at `src/deviate/prompts/skills/deviatdd/` (three
   directories deep).
-* **Tests:** `TestInstallDeviatddSkill` (8 tests) in
-  `tests/test_cli/test_init.py` covers install-to-all-five-agents,
+* **Tests:** `TestInstallDeviatddSkill` in
+  `tests/test_cli/test_init.py` and `TestSetupSelectedAgentIsolation` /
+  `TestSetupCodex` in `tests/test_cli/test_setup.py` cover
+  selected-agent-only install, Codex skills + `backend = "codex"`,
   idempotence, gitignore entry presence + idempotence, safety-gate
   fragments in the SKILL.md body, well-formed frontmatter, and the
   dispatch table's canonical slash-command references.
@@ -257,7 +263,7 @@ scripts. All commands are registered in `src/deviate/cli/__init__.py` using Type
 
 ### 1.5 Product Layer *(optional, sits above Macro)*
 
-The Product layer ships as **agent skills** (no dedicated CLI subcommands) — the prompts live at `src/deviate/prompts/commands/deviate-{flows,architecture,release}.md` and are installed to all four agent directories alongside the rest. They are **not** wired into the `deviate` CLI's `pre`/`post` subcommand pattern: the agent invokes them directly as `/deviate-flows`, `/deviate-architecture`, `/deviate-release`, and the conversation produces the artifact. The CLI's only involvement is installing the skill files during `deviate setup` and (via `deviate-shard` / `deviate-adhoc`) consuming the `flow_refs:` frontmatter those artifacts emit.
+The Product layer ships as **agent skills** (no dedicated CLI subcommands) — the prompts live at `src/deviate/prompts/commands/deviate-{flows,architecture,release}.md` and are installed to the selected agent directory alongside the rest. They are **not** wired into the `deviate` CLI's `pre`/`post` subcommand pattern: the agent invokes them directly as `/deviate-flows`, `/deviate-architecture`, `/deviate-release`, and the conversation produces the artifact. The CLI's only involvement is installing the skill files during `deviate setup` and (via `deviate-shard` / `deviate-adhoc`) consuming the `flow_refs:` frontmatter those artifacts emit.
 
 | Command | Source skill | Artifact committed | Notes |
 |---------|--------------|--------------------|-------|

{deviatdd-2.23.0 → deviatdd-2.23.1}/specs/DeviaTDD-architecture.md

@@ -887,6 +887,7 @@ handing the manifest to the rest of the pipeline:
 | `claude` | `claude -p --permission-mode auto` | Commands copied into `.claude/commands/` (flat `.md`) | `--model <id>` flag (may be ignored by host env) | Print mode, auto permission |
 | `droid` | `droid exec` | Commands copied into `.factory/commands/` (flat `.md`) | `--model <id>` flag | Factory Droid IDE-owned commands dir |
 | `pi` | `pi -p` | Commands file-copied into `<workdir>/.pi/prompts/<name>.md` (project-local; flat top-level only per Pi's documented slash-command convention) | `--model <id>` flag (accepts `provider/model` shorthand) | Lean spawn after `pi -p` / RPC `--no-session`: `--no-extensions`, `--tools read,bash,edit,write`, `--no-skills`, optional `--skill`; schema-limit tokens abort as `AGENT_ERROR` |
+| `codex` | `codex exec --sandbox workspace-write --ask-for-approval never` | Skills written to `<workdir>/.agents/skills/<name>/SKILL.md` (Codex CLI 0.117+ dropped `.codex/prompts`). Packaged `deviatdd` skill plus one skill folder per slash command. | `--model <id>` flag | CLI transport only (no Codex RPC). Prompt via stdin. Do not use `--full-auto` or `--dangerously-bypass-approvals-and-sandbox`. |
 
 Pi implements slash-command discovery natively — `pi -p` loads commands from
 `~/.pi/agent/`, `.pi/prompts/`, and `.agents/` on startup, parses the
@@ -958,18 +959,18 @@ standard `AgentBackend.invoke()` contract with these customisations:
    the tokens. This path does not wait 900s. It does not treat those
    tokens as stall liveness. EXECUTE stall stays 3600s.
 
-### 10.2.5 Project-Local `deviatdd` Skill (Single Skill, Write-Everywhere)
+### 10.2.5 Project-Local `deviatdd` Skill (Single Skill, Selected Agent)
 
 In addition to the 25 `deviate-*` slash commands under
 `<workdir>/.<agent>/commands/` and `<workdir>/.pi/prompts/`, `deviate setup`
 provisions exactly **one** project-local skill named `deviatdd` at
-`<workdir>/.<agent>/skills/deviatdd/SKILL.md` for every agent platform
-in `active_agents` (`claude`, `opencode`, `factory`, `pi`, `omp`).
-This mirrors `_install_commands_to_agents`'s write-everywhere policy:
-the skill body is identical across platforms, only the destination
-directory differs, and the write is unconditional — every operator
-using `--agent <platform>` gets the skill at the canonical skills
-directory for their platform.
+`<workdir>/.<agent>/skills/deviatdd/SKILL.md` for the selected agent
+only (`claude`, `opencode`, `factory`/`droid`, `pi`, `omp`). Codex
+receives the same skill at `<workdir>/.agents/skills/deviatdd/SKILL.md`
+plus one `.agents/skills/<command>/SKILL.md` per packaged slash command.
+`--agent` gates both command and skill install; `droid` normalizes to
+`.factory/`. The skill body is identical across platforms — only the
+destination directory differs.
 
 **Auto-discovery status per platform (informational, does not gate the
 write):**
@@ -987,6 +988,9 @@ write):**
   `~/.omp/agent/managed-skills/<name>/SKILL.md` and via a
   settings-driven `skills` array. Operators register the
   project-local file via OMP's `skills` array in settings.
+- `codex` — official project-local discovery is
+  `.agents/skills/<name>/SKILL.md`. Codex CLI 0.117+ dropped
+  `.codex/prompts` and `/prompts:`.
 
 **Source of truth:** `src/deviate/prompts/skills/deviatdd/SKILL.md`
 (package resource, loaded via `importlib.resources`).
@@ -1044,18 +1048,21 @@ field schemas live in `micro.py` itself, not duplicated here.
 **`.gitignore` exclusions:** `_ensure_root_gitignore` adds
 `*/skills/deviatdd/` to the entries tuple alongside
 `*/commands/deviate-*.md` and `*/prompts/deviate-*.md`. The
-single-level wildcard covers all five agent platforms (`.claude/`,
-`.opencode/`, `.factory/`, `.pi/`, `.omp/`) with one pattern. The
-single-level prefix (`*/`, not `**/`) is critical: it scopes the
-pattern to the project root, never matching the deviatdd project's
-own source at `src/deviate/prompts/skills/deviatdd/` (three
-directories deep).
-
-**Tests:** `TestInstallDeviatddSkill` (8 tests) in
-`tests/test_cli/test_init.py` covers install-to-all-five-agents,
-idempotence, gitignore entry presence + idempotence, the safety-gate
-fragments in the SKILL.md body, well-formed frontmatter, and the
-dispatch table's canonical slash-command references.
+single-level wildcard covers every selected-agent skill install
+(`.claude/`, `.opencode/`, `.factory/`, `.pi/`, `.omp/`, `.agents/`)
+with one pattern. `*/skills/deviate-*/` covers Codex per-command
+skill dirs. The single-level prefix (`*/`, not `**/`) is critical: it
+scopes the pattern to the project root, never matching the
+deviatdd project's own source at
+`src/deviate/prompts/skills/deviatdd/` (three directories deep).
+
+**Tests:** `TestInstallDeviatddSkill` in `tests/test_cli/test_init.py`
+and `TestSetupSelectedAgentIsolation` / `TestSetupCodex` in
+`tests/test_cli/test_setup.py` cover selected-agent-only install,
+Codex skills + `backend = "codex"`, idempotence, gitignore entry
+presence + idempotence, the safety-gate fragments in the SKILL.md
+body, well-formed frontmatter, and the dispatch table's canonical
+slash-command references.
 
 
 ### 10.3 Pi Sandbox Boundary

{deviatdd-2.23.0 → deviatdd-2.23.1}/specs/issues.jsonl

@@ -110,3 +110,14 @@
 {"issue_id": "ISS-ADH-032", "type": "adhoc", "title": "Judge prompt must inject the Judge-Feedback-stripped task card so prior feedback cannot mislead the judge into a COMPLETED evidence fail-close loop", "status": "BACKLOG", "source_file": "specs/adhoc/issues/032-judge-feedback-injection-fail-close.md", "blocked_by": [], "coordinates_with": ["ISS-ADH-020", "ISS-ADH-028"], "timestamp": "2026-08-25T12:56:30.723608+00:00", "created_at": "2026-08-25T12:56:30.723608+00:00", "flow_refs": []}
 {"issue_id":"ISS-ADH-031","type":"adhoc","title":"Micro Judge already-exists COMPLIANCE_PASS must complete instead of hard-crashing with ROLLBACK_BOUNDARY_MISSING","status":"SPECIFIED","source_file":"specs/adhoc/issues/031-judge-revert-boundary-no-failing-test.md","blocked_by":[],"coordinates_with":[],"timestamp":"2026-08-25T12:04:14.071361Z","created_at":"2026-08-25T12:02:23.091420Z","flow_refs":[]}
 {"issue_id":"ISS-ADH-031","type":"adhoc","title":"Micro Judge already-exists COMPLIANCE_PASS must complete instead of hard-crashing with ROLLBACK_BOUNDARY_MISSING","status":"COMPLETED","source_file":"specs/adhoc/issues/031-judge-revert-boundary-no-failing-test.md","blocked_by":[],"coordinates_with":[],"timestamp":"2026-08-26T01:22:58.997447Z","created_at":"2026-08-25T12:02:23.091420Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-005","type":"adhoc","title":"Per-Phase Model Configuration with Configurable Model Routing","status":"COMPLETED","source_file":"specs/adhoc/issues/005-per-phase-model-configuration.md","blocked_by":[],"coordinates_with":["ISS-001-005"],"timestamp":"2026-06-18T08:43:57Z","created_at":"2026-06-16T15:46:44.364472Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-009","type":"adhoc","title":"Pi Agent Backend Integration — First-Class Backend for Micro/Meso Layers","status":"COMPLETED","source_file":"specs/adhoc/issues/009-pi-agent-backend-integration.md","blocked_by":[],"coordinates_with":[],"timestamp":"2026-06-26T10:59:37Z","created_at":"2026-06-24T07:44:35.265840Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-021","type":"adhoc","title":"Escalate no_failing_test to RED; never GREEN without red_commit_sha","status":"COMPLETED","source_file":"specs/adhoc/issues/021-no-failing-test-escalate-invokes-green.md","blocked_by":[],"coordinates_with":[],"timestamp":"2026-08-21T19:31:47Z","created_at":"2026-08-21T13:11:40.290976Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-022","type":"adhoc","title":"already_satisfied RED cannot COMPLETE without declared regression tests","status":"COMPLETED","source_file":"specs/adhoc/issues/022-already-satisfied-red-requires-tests.md","blocked_by":[],"coordinates_with":["ISS-ADH-020","ISS-ADH-021"],"timestamp":"2026-08-21T21:40:45Z","created_at":"2026-08-21T19:45:40.426802Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-023","type":"adhoc","title":"Scope pinned micro run TASK_ID to the active issue","status":"COMPLETED","source_file":"specs/adhoc/issues/023-pinned-micro-run-issue-scoped.md","blocked_by":[],"coordinates_with":[],"timestamp":"2026-08-21T23:42:30Z","created_at":"2026-08-21T22:03:13.828791Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-024","type":"adhoc","title":"Re-key stale worktree session to the claimed branch issue","status":"COMPLETED","source_file":"specs/adhoc/issues/024-worktree-session-stale-issue-id.md","blocked_by":[],"coordinates_with":["ISS-ADH-023"],"timestamp":"2026-08-22T01:41:00Z","created_at":"2026-08-21T23:46:26.071257Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-025","type":"adhoc","title":"Treat stderr as diagnostic so GREEN stall raises AGENT_TIMEOUT","status":"COMPLETED","source_file":"specs/adhoc/issues/025-green-stderr-noise-stall-detector.md","blocked_by":[],"coordinates_with":[],"timestamp":"2026-08-22T03:43:44Z","created_at":"2026-08-22T01:47:07.268593Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-026","type":"adhoc","title":"Constrain Spawned Pi to Lean Tools and Surface tool_count_limit","status":"COMPLETED","source_file":"specs/adhoc/issues/026-pi-spawn-lean-tool-schema.md","blocked_by":[],"coordinates_with":["ISS-ADH-025"],"timestamp":"2026-08-22T05:43:21Z","created_at":"2026-08-22T03:48:03.494286Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-027","type":"adhoc","title":"Raise AGENT_TIMEOUT and roll back dirty RED when the agent never returns a manifest","status":"COMPLETED","source_file":"specs/adhoc/issues/027-red-hang-timeout-rollback.md","blocked_by":[],"coordinates_with":["ISS-ADH-025","ISS-ADH-023"],"timestamp":"2026-08-22T06:42:50Z","created_at":"2026-08-22T05:47:44.342373Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-028","type":"adhoc","title":"Scope TDD JUDGE evidence to this task and fail-close review on uncovered plan ACs","status":"COMPLETED","source_file":"specs/adhoc/issues/028-task-scoped-judge-review-coverage.md","blocked_by":[],"coordinates_with":["ISS-ADH-020"],"timestamp":"2026-08-22T13:36:39Z","created_at":"2026-08-22T11:20:26.754454Z","flow_refs":[]}
+{"issue_id":"ISS-ADH-032","type":"adhoc","title":"Judge prompt must inject the Judge-Feedback-stripped task card so prior feedback cannot mislead the judge into a COMPLETED evidence fail-close loop","status":"COMPLETED","source_file":"specs/adhoc/issues/032-judge-feedback-injection-fail-close.md","blocked_by":[],"coordinates_with":["ISS-ADH-020","ISS-ADH-028"],"timestamp":"2026-08-26T01:55:09Z","created_at":"2026-08-25T12:56:30.723608+00:00","flow_refs":[]}

{deviatdd-2.23.0 → deviatdd-2.23.1}/src/deviate/cli/__init__.py

@@ -55,8 +55,18 @@ _GOVERNANCE_MODULE = "deviate.prompts.governance"
 
 # User-facing agent platform choices (selectable via --agent and the
 # interactive init prompt). Order is intentional: factory/droid (Droid
-# ecosystem) come first, then the third-party CLIs.
-AGENT_CHOICES: tuple[str, ...] = ("factory", "droid", "claude", "opencode", "pi", "omp")
+# ecosystem) come first, then the third-party CLIs. ``codex`` is the
+# ChatGPT Codex CLI — a first-class meso/micro backend that installs
+# skills under ``.agents/skills/`` rather than ``.codex/prompts``.
+AGENT_CHOICES: tuple[str, ...] = (
+    "factory",
+    "droid",
+    "claude",
+    "opencode",
+    "pi",
+    "omp",
+    "codex",
+)
 
 # Map a user-facing agent name to the underlying backend that meso/micro
 # layers invoke. ``factory`` is the Factory Droid IDE — the meso/micro
@@ -600,12 +610,25 @@ def _apply_governance(workdir: Path) -> None:
             _upsert_governance_block(t, libref_content)
 
 
+def _normalize_install_agent(agent: str) -> str:
+    """Map a user-facing agent name to the install-directory identity.
+
+    ``droid`` and ``factory`` both write ``.factory/``. ``codex`` and
+    every other name pass through unchanged.
+    """
+    if agent == "droid":
+        return "factory"
+    return agent
+
+
 def _get_agent_command_dir(agent_name: str, workdir: Path) -> Path | None:
     """Resolve the slash-command directory for a given agent platform.
 
     Factory, Claude, OpenCode discover slash commands from
     ``<workdir>/.{agent}/commands/`` (flat top-level only). Pi and OMP use
     ``<workdir>/.{agent}/prompts/`` per their platform conventions.
+    Codex CLI 0.117+ dropped custom prompts — return ``None`` so setup
+    never writes ``.codex/prompts`` or ``.codex/commands``.
     """
     if agent_name in ("claude", "opencode", "factory"):
         return workdir / f".{agent_name}" / "commands"
@@ -617,17 +640,19 @@ def _get_agent_command_dir(agent_name: str, workdir: Path) -> Path | None:
 
 
 def _install_commands_to_agents(workdir: Path, agents: list[str]) -> None:
-    """Install the command library into every supported agent directory.
+    """Install the command library into the selected agent directories.
 
     Output is aggregated per-agent — one summary line per agent instead of
     one line per (command × agent) — to keep ``deviate setup`` output
-    readable when 32 commands are written to four agent directories
-    (128 lines per invocation under the legacy per-command format).
+    readable when 32 commands are written to a single selected agent.
     """
     commands = discover_commands()
     if not commands:
         return
     for agent in agents:
+        if agent == "codex":
+            _install_codex_command_skills(workdir)
+            continue
         target_dir = _get_agent_command_dir(agent, workdir)
         if target_dir is None:
             console.print(f"  [yellow]SKIP[/] Unknown agent: {agent}")
@@ -649,6 +674,41 @@ def _install_commands_to_agents(workdir: Path, agents: list[str]) -> None:
             )
 
 
+def _install_codex_command_skills(workdir: Path) -> None:
+    """Install each packaged slash command as a Codex project skill.
+
+    Codex CLI 0.117+ dropped ``~/.codex/prompts`` and ``/prompts:``.
+    Official project-local discovery is ``.agents/skills/<name>/SKILL.md``
+    (scanned from CWD up to the repo root). Reuse the composed command
+    bodies via :func:`install_command` — do not invent new prompt text.
+    """
+    commands = discover_commands()
+    if not commands:
+        return
+    installed = 0
+    skipped = 0
+    skills_root = workdir / ".agents" / "skills"
+    for command_name in commands:
+        if install_command(
+            command_name,
+            skills_root / command_name,
+            workdir=workdir,
+            agent="codex",
+            target_filename="SKILL.md",
+        ):
+            installed += 1
+        else:
+            skipped += 1
+    if installed and not skipped:
+        console.print(f"  [green]INSTALL[/] {installed} commands → codex")
+    elif skipped and not installed:
+        console.print(f"  [yellow]SKIP[/] {skipped} commands → codex")
+    else:
+        console.print(
+            f"  [green]INSTALL[/] {installed}, [yellow]SKIP[/] {skipped} → codex"
+        )
+
+
 def _resolve_skill_source() -> str | None:
     """Load the deviatdd SKILL.md body from package resources."""
     try:
@@ -666,11 +726,10 @@ def _resolve_skill_source() -> str | None:
 def _get_agent_skill_dir(workdir: Path, agent: str) -> Path | None:
     """Return the project-local skills directory for *agent*.
 
-    Mirrors ``_install_commands_to_agents``'s "write everywhere" pattern:
-    every agent platform that ``deviate setup`` provisions commands
-    for also receives the ``deviatdd`` skill at
-    ``<workdir>/.<agent>/skills/deviatdd/SKILL.md``. The skill body is
-    identical across platforms — only the destination directory differs.
+    Setup installs the ``deviatdd`` skill only for the selected agent
+    (``droid`` is normalized to ``factory`` before this helper runs).
+    The skill body is identical across platforms — only the destination
+    directory differs.
 
     Auto-discovery status per platform:
 
@@ -690,16 +749,19 @@ def _get_agent_skill_dir(workdir: Path, agent: str) -> Path | None:
       user-level ``~/.omp/agent/managed-skills/<name>/SKILL.md`` and
       via a settings-driven ``skills`` array, with no project-local
       auto-discovery. The file is still written to
-      ``<workdir>/.omp/skills/deviatdd/SKILL.md`` for consistency with
-      the other four platforms; operators can register it via
-      OMP's ``skills`` array in settings or copy it to the user-level
-      path.
+      ``<workdir>/.omp/skills/deviatdd/SKILL.md`` so operators can
+      register it via OMP's ``skills`` array in settings or copy it
+      to the user-level path.
+    - ``codex`` — official project-local discovery is
+      ``<workdir>/.agents/skills/<name>/SKILL.md``. Codex CLI 0.117+
+      dropped ``.codex/prompts`` / ``/prompts:``.
     - ``droid`` — normalized to ``factory`` at the command-install
       layer; not iterated separately here.
 
-    Returns ``None`` only for unknown agent names not in the
-    ``active_agents`` set.
+    Returns ``None`` for unknown agent names.
     """
+    if agent == "codex":
+        return workdir / ".agents" / "skills"
     if agent in ("claude", "opencode", "factory", "pi", "omp"):
         return workdir / f".{agent}" / "skills"
     return None
@@ -713,6 +775,9 @@ def _install_deviatdd_skill(workdir: Path, agents: list[str]) -> None:
         return
     for agent in agents:
         target_dir = _get_agent_skill_dir(workdir, agent)
+        if target_dir is None:
+            console.print(f"  [yellow]SKIP[/] Unknown agent: {agent}")
+            continue
         target = target_dir / "deviatdd" / "SKILL.md"
         if target.exists() and target.read_text(encoding="utf-8") == body:
             console.print(f"  [yellow]SKIP[/] {target.relative_to(workdir)}")
@@ -756,7 +821,7 @@ def setup(
     agent: str | None = typer.Option(
         None,
         "--agent",
-        help="Override auto-detected agent platform",
+        help="Agent platform to install and persist as [agent].backend",
         callback=_validate_agent_choice,
     ),
     no_claim_remote: bool = typer.Option(
@@ -804,21 +869,19 @@ def setup(
 
     _apply_governance(workdir)
 
-    # DeviaTDD commands are installed into ALL agent directories regardless
-    # of ``--agent``. ``--agent`` only drives the ``[agent].backend`` value
-    # written to ``.deviate/config.toml`` — that value is consumed by the
-    # meso/micro layers to dispatch agent invocations, never to gate which
-    # agents receive commands. ``droid`` is normalised to ``factory`` —
-    # both names map to the Factory Droid IDE commands directory
-    # (``.factory/commands/``); ``droid`` is the underlying backend binary.
-    # ``pi`` uses ``.pi/prompts/`` per the platform's documented convention;
-    # ``omp`` uses ``.omp/prompts/`` per the OMP platform convention; the
-    # other three use ``commands/``. No global ``~/.pi/agent/`` writes,
+    # Install commands + the packaged skill only for the selected agent.
+    # ``--agent`` (or the existing ``[agent].backend``, or the interactive
+    # prompt) is the install target as well as the meso/micro backend.
+    # ``droid`` is normalised to ``factory`` so both names write
+    # ``.factory/``. Codex is a first-class backend that writes skills
+    # under ``.agents/skills/`` (Codex CLI 0.117+ dropped custom prompts).
+    # ``pi`` uses ``.pi/prompts/``; ``omp`` uses ``.omp/prompts/``; the
+    # remaining CLIs use ``commands/``. No global ``~/.pi/agent/`` writes,
     # no ``settings.json`` generation — the operator's Pi config is out of
     # scope.
-    active_agents = ("claude", "opencode", "factory", "pi", "omp")
-    _install_commands_to_agents(workdir, list(active_agents))
-    _install_deviatdd_skill(workdir, list(active_agents))
+    install_agent = _normalize_install_agent(selected_agent)
+    _install_commands_to_agents(workdir, [install_agent])
+    _install_deviatdd_skill(workdir, [install_agent])
 
     _ensure_gitignore(workdir)
     _ensure_root_gitignore(workdir)
@@ -885,16 +948,18 @@ def _ensure_root_gitattributes(workdir: Path) -> None:
 def _ensure_root_gitignore(workdir: Path) -> None:
     """Update the project-root ``.gitignore`` to exclude DeviaTDD-installed
     artifacts and worktrees across all agent platforms.
-    Three artifact families are installed and must not be committed:
+    Artifact families are installed and must not be committed:
     - ``deviate-*`` commands under ``<agent>/commands/`` and
       ``<agent>/prompts/`` — the core DeviaTDD command library.
     - The ``deviatdd`` skill under ``<agent>/skills/deviatdd/``.
+    - Codex per-command skills under ``.agents/skills/deviate-*/``.
     - ``.worktrees/`` — isolated task worktrees managed by DeviaTDD.
     """
     entries = (
         "*/commands/deviate-*.md",
         "*/prompts/deviate-*.md",
         "*/skills/deviatdd/",
+        "*/skills/deviate-*/",
         ".worktrees/",
     )
     gitignore_path = workdir / ".gitignore"

{deviatdd-2.23.0 → deviatdd-2.23.1}/src/deviate/cli/meso.py

@@ -430,7 +430,7 @@ def _setup_mise(worktree_path: Path | None = None) -> None:
         console.print(f"[yellow]MISE_WARN[/] setup step failed — {e}")
 
 
-_AGENT_DIRS = (".claude", ".opencode", ".factory", ".pi", ".omp")
+_AGENT_DIRS = (".claude", ".opencode", ".factory", ".pi", ".omp", ".agents")
 
 _WORKTREE_SYNC_FILES = (".env",)
 
@@ -439,8 +439,8 @@ def _sync_worktree_assets(repo_root: Path, worktree_path: Path) -> None:
     """Copy agent skill directories and config files from repo root to worktree.
 
     This ensures worktrees have the same skills (.claude/, .opencode/,
-    .factory/, .pi/, .omp/) and environment files (.env) as the main
-    repository so deviate commands work inside the worktree without
+    .factory/, .pi/, .omp/, .agents/) and environment files (.env) as the
+    main repository so deviate commands work inside the worktree without
     re-running ``deviate setup`` or losing local configuration.
     """
     for agent_dir in _AGENT_DIRS:

{deviatdd-2.23.0 → deviatdd-2.23.1}/src/deviate/core/agent.py

@@ -45,7 +45,7 @@ def _truncate_prompt(prompt: str) -> str:
     return f"{prompt[:head_size]}{marker}{prompt[-tail_size:]}"
 
 
-BackendName = Literal["opencode", "claude", "droid", "pi", "omp", "stub"]
+BackendName = Literal["opencode", "claude", "droid", "pi", "omp", "codex", "stub"]
 
 
 class EvidenceItem(BaseModel):
@@ -170,6 +170,15 @@ BACKEND_COMMANDS: dict[str, str] = {
     # as a first-class backend, not an alias for ``pi`` — model flag,
     # timeout, and YAML manifest extraction all apply.
     "omp": "omp -p",
+    # ChatGPT Codex CLI (non-interactive). Official ``codex exec`` reads
+    # the prompt from stdin when no positional prompt is given — omit the
+    # ``-`` sentinel so ``MODEL_FLAGS`` can append ``--model`` at the end
+    # without it being swallowed as prompt text. Default ``codex exec``
+    # sandbox is read-only; ``--sandbox workspace-write`` plus
+    # ``--ask-for-approval never`` is the documented unattended analog of
+    # ``claude -p --permission-mode auto``. Do not use ``--full-auto``
+    # (deprecated) or ``--dangerously-bypass-approvals-and-sandbox``.
+    "codex": "codex exec --sandbox workspace-write --ask-for-approval never",
     "stub": "stub",
 }
 
@@ -186,6 +195,7 @@ AGENT_TO_BACKEND: dict[str, str] = {
     "opencode": "opencode",
     "pi": "pi",
     "omp": "omp",
+    "codex": "codex",
 }
 
 
@@ -193,8 +203,8 @@ def resolve_agent_to_backend(agent: str) -> str:
     """Return the canonical backend for *agent*.
 
     User-facing aliases (``factory``) are mapped to their underlying
-    backend binary. Already-canonical names (``opencode``, ``claude``,
-    ``droid``, ``pi``, ``omp``) pass through unchanged. Unknown values
+    backend binary.     Already-canonical names (``opencode``, ``claude``,
+    ``droid``, ``pi``, ``omp``, ``codex``) pass through unchanged. Unknown values
     are returned unchanged so the caller can surface a validation error
     against :class:`~deviate.state.config.AgentConfig`'s ``backend``
     Literal.
@@ -283,6 +293,7 @@ MODEL_FLAGS: dict[str, list[str] | None] = {
     "opencode": ["--model"],
     "droid": ["--model"],
     "omp": ["--model"],
+    "codex": ["--model"],
 }
 
 # Backends whose CLI expects the prompt as a positional argument rather