agentic-dev-loop 0.9.0__tar.gz → 0.9.2__tar.gz

{agentic_dev_loop-0.9.0/src/agentic_dev_loop.egg-info → agentic_dev_loop-0.9.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-dev-loop
-Version: 0.9.0
+Version: 0.9.2
 Summary: Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.
 Author: Luke Wilson
 License-Expression: Apache-2.0
@@ -155,8 +155,6 @@ agentic-dev-loop pipeline.yaml --resume <thread-id> --max-attempts 5
 | `--dry-run` | Full load-and-validate pass, then print the resolved plan. No LLM, no Docker, no state writes, no API key. Exit `0` on a clean load. |
 | `--resume <thread-id>` | Continue the latest checkpoint of a previous run (crash, Ctrl-C, exhaustion) with all accumulated notes intact. |
 | `--max-attempts <n>` | Override the pipeline's `max_attempts`. |
-| `--refresh` | Force re-provision of every `setup:` hook (bypasses the stamp cache). |
-| `--clean-stamps` | Delete cached provision stamps and exit. |
 | `--no-viz` / `--viz-port <port>` | Suppress the live graph view / set a preferred port (default 8321; falls back to a free port when busy). |
 | extension flags | Document-loader flags (e.g. `--plan`, `--aidlc-unit`) appear once the pipeline's extensions are loaded - `agentic-dev-loop PIPELINE --help` shows them. |
 
@@ -261,8 +259,7 @@ steps:
 | `custom_prompt:` | Planned (planning-docs/040). Optional agent-step value: literal text, or a path whose file contents are read at load time, appended verbatim to the agent prompt at context assembly (after the prompt, before the task/artifacts). A value that looks like a path but names no file is a validation error. Agent steps only. |
 | `reasoning_effort:` | Optional `low` / `medium` / `high` / `xhigh` / `none`. Set on the `llm` block (pipeline-global) or per-step (overrides the block). Unset anywhere = the field is not passed and the SDK default (`high`) applies, so today's behavior is unchanged. Forwarded only for models the SDK/LiteLLM mark as supporting it; an unsupported value fails at the first LLM call. See [Reasoning effort](#reasoning-effort-opt-in). |
 | `on_pass:` / `on_fail:` | A step name, terminal `success`/`failure`, or `{goto: X, retry: true}`. No loops happen unless you write them. |
-| `env:` / `setup:` / `network:` | `env:` declares step vars (fixed safe base + declared vars only); `setup:` provisions the sandbox before the step runs (command or agent steps; network ON; stamp-cached, re-runs when the pipeline's lockfiles change); `network: true` lets a command/agent step reach the hosts its `egress:` allowlist names (default off) - see [Per-stage networking](#per-stage-networking). |
-| `setup_probe:` | Optional consumer-authored in-container probe run on a warm `setup:` stamp instead of the venv probe. Exit 0 trusts the stamp (skips); any nonzero re-provisions with network on (fail toward freshness). The probe text is NOT part of the stamp key, so a probe-only change needs `--refresh` or `--clean-stamps` to take effect. Example (asserting a warmed esbuild binary is Linux-shaped): `file frontend-editor/node_modules/esbuild/bin/esbuild | grep -q ELF`. |
+| `env:` / `setup:` / `network:` | `env:` declares step vars (fixed safe base + declared vars only); `setup:` runs fresh at every step boundary in a one-shot provision container targeting the export (command or agent steps; network ON; no stamping); `network: true` lets a command/agent step reach the hosts its `egress:` allowlist names (default off) - see [Per-stage networking](#per-stage-networking). |
 | `mounts:` / `egress:` | Per-step workspace isolation. `mounts:` lists `{path, mode}` entries (`rw`/`ro`, default `ro`) and is **strict-by-default** - empty/missing mounts nothing; only declared-rw paths sync back to the repo. `egress:` is `{class, presets, targets}` (`class: browser` = broad-but-logged; otherwise a strict allowlist). See [Per-stage networking](#per-stage-networking) and [docs/setup.md](docs/setup.md). |
 | `secrets:` (top-level) / step `secrets:` | Declares secret **refs only - never values**; each step opts in to the refs it needs. Resolved host-side and injected into that step's exec env only. See [Secrets](#secrets--refs-only-never-values). |
 | `isolation:` (optional) | Configures the sandbox - image override, resource caps, `allow_git_mutations`, `seccomp_profile`. It can never disable it. See [browser sandbox](docs/browser-sandbox.md). |
@@ -270,7 +267,7 @@ steps:
 | `extensions_dir` | Where consumer `extensions:` modules resolve - defaults to `~/.agentic-dev-loop/extensions`, **outside** the workspace. Workspace-resident extension/tool modules are refused at load. |
 | `deps_policy` | `locked` (default) or `open`. `locked` = the human-owned lockfile is the source of truth and the agent may not add dependencies; `open` = the bootstrap protocol (the agent may add exact-pinned manifest entries). See [Dependency policy](#dependency-policy-locked-by-default). |
 | `lockfiles` | The pipeline's declared lockfile names (workspace-relative), injected into agent context and named by the missing-dependency fail-fast. Required (non-empty) when `deps_policy: locked` - a `locked` pipeline with no lockfiles fails fast at load. |
-| `caches:` / `sync_excludes:` | Top-level run-wide lists. `caches:` names repo-relative toolchain cache dirs bind-mounted rw from the real workspace (auto-created if missing); a `setup:` hook can warm them (the provision container carries the same cache mounts); `sync_excludes:` names scratch paths skipped from both the export copy and sync-back (wildcard `*` spans separators, so `**/bin/**` matches a `/bin/` segment at any depth). Both default to `[]`. See [docs/setup.md](docs/setup.md). |
+| `caches:` / `sync_excludes:` | Top-level run-wide lists. `caches:` names repo-relative toolchain cache dirs bind-mounted rw from host-side stores under `{state_dir}/caches/<name>` (auto-created); a `setup:` hook can warm them (the provision container carries the same cache mounts); `sync_excludes:` names non-gitignored scratch paths skipped from both the export copy and sync-back (wildcard `*` spans separators, so `**/bin/**` matches a `/bin/` segment at any depth). Both default to `[]`. See [docs/setup.md](docs/setup.md). |
 | `merge_on_conflict:` | Top-level run-wide list of append-style logs (same path vocabulary as `sync_excludes:`, default `[]`). A concurrent host edit to a listed path is union-merged instead of raising: the host file wins and the sandbox's export-only lines are appended in order; both sides converge and the run continues. See [docs/setup.md](docs/setup.md). |
 
 ### Reasoning effort (opt-in)

{agentic_dev_loop-0.9.0 → agentic_dev_loop-0.9.2}/README.md

@@ -111,8 +111,6 @@ agentic-dev-loop pipeline.yaml --resume <thread-id> --max-attempts 5
 | `--dry-run` | Full load-and-validate pass, then print the resolved plan. No LLM, no Docker, no state writes, no API key. Exit `0` on a clean load. |
 | `--resume <thread-id>` | Continue the latest checkpoint of a previous run (crash, Ctrl-C, exhaustion) with all accumulated notes intact. |
 | `--max-attempts <n>` | Override the pipeline's `max_attempts`. |
-| `--refresh` | Force re-provision of every `setup:` hook (bypasses the stamp cache). |
-| `--clean-stamps` | Delete cached provision stamps and exit. |
 | `--no-viz` / `--viz-port <port>` | Suppress the live graph view / set a preferred port (default 8321; falls back to a free port when busy). |
 | extension flags | Document-loader flags (e.g. `--plan`, `--aidlc-unit`) appear once the pipeline's extensions are loaded - `agentic-dev-loop PIPELINE --help` shows them. |
 
@@ -217,8 +215,7 @@ steps:
 | `custom_prompt:` | Planned (planning-docs/040). Optional agent-step value: literal text, or a path whose file contents are read at load time, appended verbatim to the agent prompt at context assembly (after the prompt, before the task/artifacts). A value that looks like a path but names no file is a validation error. Agent steps only. |
 | `reasoning_effort:` | Optional `low` / `medium` / `high` / `xhigh` / `none`. Set on the `llm` block (pipeline-global) or per-step (overrides the block). Unset anywhere = the field is not passed and the SDK default (`high`) applies, so today's behavior is unchanged. Forwarded only for models the SDK/LiteLLM mark as supporting it; an unsupported value fails at the first LLM call. See [Reasoning effort](#reasoning-effort-opt-in). |
 | `on_pass:` / `on_fail:` | A step name, terminal `success`/`failure`, or `{goto: X, retry: true}`. No loops happen unless you write them. |
-| `env:` / `setup:` / `network:` | `env:` declares step vars (fixed safe base + declared vars only); `setup:` provisions the sandbox before the step runs (command or agent steps; network ON; stamp-cached, re-runs when the pipeline's lockfiles change); `network: true` lets a command/agent step reach the hosts its `egress:` allowlist names (default off) - see [Per-stage networking](#per-stage-networking). |
-| `setup_probe:` | Optional consumer-authored in-container probe run on a warm `setup:` stamp instead of the venv probe. Exit 0 trusts the stamp (skips); any nonzero re-provisions with network on (fail toward freshness). The probe text is NOT part of the stamp key, so a probe-only change needs `--refresh` or `--clean-stamps` to take effect. Example (asserting a warmed esbuild binary is Linux-shaped): `file frontend-editor/node_modules/esbuild/bin/esbuild | grep -q ELF`. |
+| `env:` / `setup:` / `network:` | `env:` declares step vars (fixed safe base + declared vars only); `setup:` runs fresh at every step boundary in a one-shot provision container targeting the export (command or agent steps; network ON; no stamping); `network: true` lets a command/agent step reach the hosts its `egress:` allowlist names (default off) - see [Per-stage networking](#per-stage-networking). |
 | `mounts:` / `egress:` | Per-step workspace isolation. `mounts:` lists `{path, mode}` entries (`rw`/`ro`, default `ro`) and is **strict-by-default** - empty/missing mounts nothing; only declared-rw paths sync back to the repo. `egress:` is `{class, presets, targets}` (`class: browser` = broad-but-logged; otherwise a strict allowlist). See [Per-stage networking](#per-stage-networking) and [docs/setup.md](docs/setup.md). |
 | `secrets:` (top-level) / step `secrets:` | Declares secret **refs only - never values**; each step opts in to the refs it needs. Resolved host-side and injected into that step's exec env only. See [Secrets](#secrets--refs-only-never-values). |
 | `isolation:` (optional) | Configures the sandbox - image override, resource caps, `allow_git_mutations`, `seccomp_profile`. It can never disable it. See [browser sandbox](docs/browser-sandbox.md). |
@@ -226,7 +223,7 @@ steps:
 | `extensions_dir` | Where consumer `extensions:` modules resolve - defaults to `~/.agentic-dev-loop/extensions`, **outside** the workspace. Workspace-resident extension/tool modules are refused at load. |
 | `deps_policy` | `locked` (default) or `open`. `locked` = the human-owned lockfile is the source of truth and the agent may not add dependencies; `open` = the bootstrap protocol (the agent may add exact-pinned manifest entries). See [Dependency policy](#dependency-policy-locked-by-default). |
 | `lockfiles` | The pipeline's declared lockfile names (workspace-relative), injected into agent context and named by the missing-dependency fail-fast. Required (non-empty) when `deps_policy: locked` - a `locked` pipeline with no lockfiles fails fast at load. |
-| `caches:` / `sync_excludes:` | Top-level run-wide lists. `caches:` names repo-relative toolchain cache dirs bind-mounted rw from the real workspace (auto-created if missing); a `setup:` hook can warm them (the provision container carries the same cache mounts); `sync_excludes:` names scratch paths skipped from both the export copy and sync-back (wildcard `*` spans separators, so `**/bin/**` matches a `/bin/` segment at any depth). Both default to `[]`. See [docs/setup.md](docs/setup.md). |
+| `caches:` / `sync_excludes:` | Top-level run-wide lists. `caches:` names repo-relative toolchain cache dirs bind-mounted rw from host-side stores under `{state_dir}/caches/<name>` (auto-created); a `setup:` hook can warm them (the provision container carries the same cache mounts); `sync_excludes:` names non-gitignored scratch paths skipped from both the export copy and sync-back (wildcard `*` spans separators, so `**/bin/**` matches a `/bin/` segment at any depth). Both default to `[]`. See [docs/setup.md](docs/setup.md). |
 | `merge_on_conflict:` | Top-level run-wide list of append-style logs (same path vocabulary as `sync_excludes:`, default `[]`). A concurrent host edit to a listed path is union-merged instead of raising: the host file wins and the sandbox's export-only lines are appended in order; both sides converge and the run continues. See [docs/setup.md](docs/setup.md). |
 
 ### Reasoning effort (opt-in)

{agentic_dev_loop-0.9.0 → agentic_dev_loop-0.9.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agentic-dev-loop"
-version = "0.9.0"
+version = "0.9.2"
 description = "Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase."
 readme = "README.md"
 requires-python = ">=3.12"

{agentic_dev_loop-0.9.0 → agentic_dev_loop-0.9.2}/src/agentic_dev_loop/core/config.py

@@ -16,9 +16,6 @@ from agentic_dev_loop.core.paths import _has_wildcards, path_excluded, relative_
 TERMINALS = frozenset({"success", "failure"})
 KNOWN_SECRET_PROVIDERS = frozenset({"env"})
 MOUNT_MODES = frozenset({"rw", "ro"})
-# Host-only dirs a mount path may never name (022): they are masked in
-# the sandbox with a read-only tmpfs, so declaring them would be a decoy.
-HOST_ONLY_MOUNT_DIRS = frozenset({".venv"})
 # The egress preset names the engine ships (BR-9). Config validates the
 # name here; the target data lives in engine/presets.py (preset data,
 # never mechanism - D-2).
@@ -52,8 +49,8 @@ def _validate_mount_path(path: str) -> str:
     """Validate one repo-relative mount path (BR-1.3).
 
     Rejects (loudly) an empty path, an absolute path, ``..`` traversal,
-    any ``.git`` component, and any host-only dir (``.venv``). The path
-    is normalised to forward-slash form and returned.
+    and any ``.git`` component. The path is normalised to forward-slash
+    form and returned.
     """
     if not isinstance(path, str) or not path.strip():
         raise ValueError("mount path must be a non-empty string")
@@ -70,9 +67,6 @@ def _validate_mount_path(path: str) -> str:
         if seg == ".git":
             raise ValueError(
                 f"mount path {path!r} must never name '.git'")
-        if seg in HOST_ONLY_MOUNT_DIRS:
-            raise ValueError(
-                f"mount path {path!r} names the host-only dir {seg!r}")
     return "/".join(parts) if parts else "."
 
 
@@ -80,7 +74,7 @@ def _validate_declared_path(path: str, *, allow_wildcards: bool) -> str:
     """Validate one declared ``caches:``/``sync_excludes:`` entry (028).
 
     Same repo-relative contract as mount paths: non-empty, no absolute paths,
-    no ``..`` traversal, no ``.git`` component, no host-only dir. Wildcard
+    no ``..`` traversal, no ``.git`` component. Wildcard
     entries (``sync_excludes:`` only) skip wildcard segments in the literal
     checks; the literal segments still obey the same rules. The normalised
     forward-slash form is returned.
@@ -102,9 +96,6 @@ def _validate_declared_path(path: str, *, allow_wildcards: bool) -> str:
         if seg == ".git":
             raise ValueError(
                 f"declared path {path!r} must never name '.git'")
-        if seg in HOST_ONLY_MOUNT_DIRS:
-            raise ValueError(
-                f"declared path {path!r} names the host-only dir {seg!r}")
     return "/".join(parts) if parts else "."
 
 
@@ -220,24 +211,32 @@ class SecretSpec(BaseModel):
 class IsolationConfig(BaseModel):
     """Optional `isolation:` section - configures the always-on sandbox (BR-2).
     Absence means opinionated defaults, never unsandboxed behaviour. Unknown
-    keys fail at load (BR-5). `state_dir` is HOST-ONLY (stamps + audit) and is
-    never mounted into the sandbox (Q1)."""
+    keys fail at load (BR-5). `state_dir` is HOST-ONLY (host-side caches +
+    audit) and is never mounted into the sandbox (Q1)."""
 
     model_config = ConfigDict(extra="forbid")
 
+    @model_validator(mode="before")
+    @classmethod
+    def _reject_removed_keys(cls, data: Any) -> Any:
+        """052: removed isolation keys fail loud with a migration message."""
+        if isinstance(data, dict):
+            if "sandbox_venv_dir" in data:
+                raise ValueError(
+                    "isolation.sandbox_venv_dir was removed: venvs are "
+                    "per-run, built by a setup hook into the export; remove "
+                    "this key")
+            if "refresh" in data:
+                raise ValueError(
+                    "isolation.refresh was removed: setup now runs fresh at "
+                    "every step entry with no stamping; remove this key")
+        return data
+
     image: str | None = None            # per-pipeline override (KD-2 ref rules)
-    refresh: bool = False               # force re-provision (NFR-5)
     memory: str | None = None           # override exec container memory
     cpus: float | None = None           # override exec container cpus
     allow_git_mutations: bool = False   # BR-6 knob
-    state_dir: str = "~/.agentic-dev-loop/state"  # stamps + audit (host-only)
-    # 022 relocation opt-in: an out-of-workspace host dir that is bind-mounted
-    # at ``{ws}/.venv-sandbox`` (rw) in both the exec and provision containers,
-    # keeping the workspace free of container venv artifacts. Unset keeps the
-    # legacy workspace-local ``.venv-sandbox`` unchanged. Must resolve outside
-    # the workspace - validated at startup, not load (the workspace is unknown
-    # here).
-    sandbox_venv_dir: str | None = None
+    state_dir: str = "~/.agentic-dev-loop/state"  # host-side caches + audit
     # 023/025: optional host path to a Docker seccomp profile JSON, or a
     # ``bundled:<name>`` sentinel resolved at load to a packaged profile
     # (e.g. ``bundled:chromium-userns``). When set, the exec container runs
@@ -402,8 +401,7 @@ class StepConfig(BaseModel):
     reasoning_effort: ReasoningEffort | None = None
     custom_prompt: str | None = None  # agent steps only (040); file path resolved at load
     env: dict[str, str | None] | None = None  # NFR-1: null = inherit host value
-    setup: str | None = None  # BR-13: command steps only
-    setup_probe: str | None = None  # 045: consumer probe replacing the venv probe on a warm stamp; requires `setup`; probe text is NOT part of the stamp key (a probe-only change needs --refresh/--clean-stamps)
+    setup: str | None = None  # command or agent steps; runs fresh at each step entry (052)
     forbidden_commands: list[str] = []  # banned-command regex deny-list (036 D1)
     network: bool = False  # per-stage egress (command/agent + sandbox actions; host-side actions reject at registry time)
     # unit-5: per-step mount granularity + egress policy. Empty mounts =
@@ -432,6 +430,16 @@ class StepConfig(BaseModel):
             return "command"
         return "action"
 
+    @model_validator(mode="before")
+    @classmethod
+    def _reject_removed_keys(cls, data: Any) -> Any:
+        """052: removed step keys fail loud with a migration message."""
+        if isinstance(data, dict) and "setup_probe" in data:
+            raise ValueError(
+                "step setup_probe was removed: setup now runs fresh at every "
+                "step entry with no stamping; remove this key")
+        return data
+
     @field_validator("produces", mode="before")
     @classmethod
     def _coerce_produces(cls, v: Any) -> Any:
@@ -464,13 +472,6 @@ class StepConfig(BaseModel):
             raise ValueError("custom_prompt must be a non-empty string")
         return v
 
-    @field_validator("setup_probe")
-    @classmethod
-    def _nonempty_setup_probe(cls, v: str | None) -> str | None:
-        if v is not None and not v.strip():
-            raise ValueError("setup_probe must be a non-empty string")
-        return v
-
     @model_validator(mode="after")
     def _check_shape(self) -> "StepConfig":
         for key in ("agent", "action", "command"):
@@ -566,15 +567,10 @@ class StepConfig(BaseModel):
             raise ValueError(
                 f"step {self.name!r}: 'custom_prompt' requires 'agent'"
             )
-        if (self.setup is not None and self.command is None
-                and self.agent is None and self.brief_inputs is None):
+        if self.setup is not None and self.command is None and self.agent is None:
             raise ValueError(
-                f"step {self.name!r}: 'setup' is only allowed on 'command', "
-                "'agent', or 'brief_inputs' steps"
-            )
-        if self.setup_probe is not None and self.setup is None:
-            raise ValueError(
-                f"step {self.name!r}: 'setup_probe' requires 'setup'"
+                f"step {self.name!r}: 'setup' is only allowed on 'command' or "
+                "'agent' steps (052)"
             )
         if self.secrets and self.action is not None:
             raise ValueError(
@@ -624,11 +620,10 @@ class PipelineConfig(BaseModel):
     # missing-dependency fail-fast.
     deps_policy: str = "locked"
     lockfiles: list[str] = []
-    # 028: pipeline-declared toolchain caches (rw bind-mounts from the real
-    # workspace) and run-wide sync-back excludes (scratch semantics: skipped
-    # from both the export copy and sync-back). Both default to [] - absent
-    # means "no toolchain caches beyond the engine's own sandbox venv" and
-    # "no sync-back excludes".
+    # 028/052: pipeline-declared toolchain caches (rw bind-mounts from the
+    # host-side cache dir ``{isolation.state_dir}/caches/<name>``) and
+    # run-wide sync-back excludes (scratch semantics: skipped from both the
+    # export copy and sync-back). Both default to [].
     caches: list[str] = []
     sync_excludes: list[str] = []
     # 029: append-style logs that sync-back union-merges on a concurrent
@@ -715,25 +710,6 @@ class PipelineConfig(BaseModel):
                         f"the host-only state_dir {self.state_dir!r}")
         return self
 
-    @model_validator(mode="after")
-    def _caches_avoid_state_dir(self) -> "PipelineConfig":
-        """028: a declared cache may never name (or sit under) the host-only
-        run-state dir - it would bind-mount the engine's own state into the
-        sandbox as a rw cache."""
-        sd = self.state_dir.strip().rstrip("/\\")
-        if not sd or sd in ("/", "."):
-            return self
-        sd_parts = relative_parts(sd)
-        if not sd_parts:
-            return self
-        for cache in self.caches:
-            cp = relative_parts(cache)
-            if cp[:len(sd_parts)] == sd_parts:
-                raise ValueError(
-                    f"cache path {cache!r} names the host-only state_dir "
-                    f"{self.state_dir!r}")
-        return self
-
     @model_validator(mode="after")
     def _mounts_avoid_caches(self) -> "PipelineConfig":
         """028/BR-1.3: a step mount equal to or under a declared cache is
@@ -799,21 +775,6 @@ class PipelineConfig(BaseModel):
                         f"{('/'.join(ep))!r}")
         return self
 
-    @model_validator(mode="after")
-    def _sandbox_venv_not_declared_cache(self) -> "PipelineConfig":
-        """028: the sandbox venv is engine infrastructure, never author data.
-        Declaring ``.venv-sandbox`` in ``caches:`` while the 022 relocation
-        (``isolation.sandbox_venv_dir``) is set is a contradiction."""
-        if self.isolation is None or self.isolation.sandbox_venv_dir is None:
-            return self
-        for cache in self.caches:
-            if relative_parts(cache) == (".venv-sandbox",):
-                raise ValueError(
-                    "declaring '.venv-sandbox' in 'caches:' contradicts "
-                    "'isolation.sandbox_venv_dir' - the sandbox venv is "
-                    "relocated outside the workspace (022)")
-        return self
-
     @model_validator(mode="after")
     def _warn_shadowed_artifacts(self) -> "PipelineConfig":
         """028: an artifact/produces path matching a sync-exclude would never

{agentic_dev_loop-0.9.0 → agentic_dev_loop-0.9.2}/src/agentic_dev_loop/engine/cli.py

@@ -14,8 +14,7 @@ from pathlib import Path
 
 from agentic_dev_loop.core.config import PipelineConfig, load_config
 from .containers import containers_report
-from .isolation import (clean_stamps, isolation_state_dir,
-                        reap_orphaned_containers)
+from .isolation import isolation_state_dir, reap_orphaned_containers
 from .loaders import mark_plan_completed
 from .registry import Registry, default_registry, load_extensions
 
@@ -82,15 +81,10 @@ def _core_parser() -> argparse.ArgumentParser:
                         help="preferred port for the live graph view "
                              "(default: 8321; falls back to a free port when "
                              "busy)")
-    parser.add_argument("--refresh", action="store_true",
-                        help="force re-provision of every setup: hook "
-                             "(bypasses the stamp cache)")
     parser.add_argument("--dry-run", action="store_true",
                         help="validate the pipeline and print a summary plan "
                              "without executing anything (no LLM, no "
                              "sandbox, no state writes)")
-    parser.add_argument("--clean-stamps", action="store_true",
-                        help="delete cached provision stamps and exit")
     _add_version_flag(parser)
     return parser
 
@@ -185,18 +179,12 @@ def main(argv: list[str] | None = None) -> int:
     for loader in registry.document_loaders:
         loader.add_cli_args(parser)
     args = parser.parse_args(argv)
-    if args.clean_stamps:
-        state = isolation_state_dir(cfg)
-        removed = clean_stamps(state)
-        print(f"Removed {removed} cached provision stamp(s) from "
-              f"{state / 'stamps'}", flush=True)
-        return 0
     if args.dry_run:
         from .dryrun import dry_run
         return dry_run(args.pipeline, args, registry)
     # The run path alone needs the heavy graph/SDK imports, and --dry-run
     # needs the dryrun import chain in-branch; defer both so `containers`,
-    # --clean-stamps, --help, and --version stay side-effect free. 042 D4: a
+    # --help, and --version stay side-effect free. 042 D4: a
     # SIGTERM here raises SystemExit(143) so graph.run_pipeline's finally
     # still closes the sandbox; a second SIGTERM hard-exits.
     previous = _install_sigterm_handler()

{agentic_dev_loop-0.9.0 → agentic_dev_loop-0.9.2}/src/agentic_dev_loop/engine/graph.py

@@ -160,15 +160,14 @@ def run_pipeline(cfg_path, args, *, viz_bus=None,
     if not state_dir.is_absolute():
         state_dir = base / state_dir
 
-    # Eager startup (Q2): probe -> image -> create+start exec container ->
-    # pre-provision all declared setups, BEFORE the graph builds. Zero infra
-    # operations mid-run; the only sandbox call during steps is run(request).
+    # Startup (052): probe -> image -> create+start exec container. No setup
+    # runs here: each step entry provisions its own setup hook, fresh, into
+    # the export.
     # 042 D3: startup is close-protected - a post-create provision failure
     # must still reach close() and reap the container it created.
     sandbox = None
     try:
         sandbox = startup_sandbox(cfg, workspace=Path.cwd(),
-                                  refresh=getattr(args, "refresh", False),
                                   state_dir=state_dir)
         return _run_pipeline(cfg, base, registry, state_dir, max_attempts,
                              args, viz_bus, sandbox, resolved_secrets,