From d349cd56a9d3b467a120a13aed804f4adf8bb163 Mon Sep 17 00:00:00 2001
From: Chao Wang <26245345+ChaoWao@users.noreply.github.com>
Date: Tue, 25 Aug 2026 20:38:52 -0700
Subject: [PATCH] Retire the PTO brand names, and hold the line with a hook
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

`.claude/rules/codestyle.md` rule 10 said the retirement was complete and that
"there is no backlog to work through". Two of its three claims held: no `PTO2`
*identifier* is left, and a new one is a defect. The third was false — the rule's
own grep, `PTO Runtime2?|PTO2|pto2_|pto_runtime2`, found 38 brand banners across
36 files in `src/`.

The claim had been measured with `PTO2|pto2_`, which cannot see a brand name with
a space in it. #1980's title was "finish the PTO2 retirement" and it finished
exactly that, verifiably — 62 remaining under its own pattern, reproducible today.
The sentence generalised from "PTO2 identifiers" to "the retirement".

## What changed

**The 38 banners**, following the style already in the tree —
`orchestrator_core/orchestrator.cpp` opens `* host_build_graph orchestrator
implementation`, so the runtime's directory name leads and the subsystem words are
lower case, with type names keeping their case:

    * PTO Runtime2 - TensorMap Interface   ->  * host_build_graph TensorMap interface
    * PTO Runtime2 - Ring Buffer Data …    ->  * tensormap_and_ringbuffer ring buffer data …

The four `PTO Runtime C API` banners are in the platform layer, which serves both
runtimes, so they take the name the canonical header already uses for itself:
`simpler host-runtime C API`.

**Eighteen comments naming a `pto_*` that does not exist.** These are
`doc-consistency.md` §3 defects rather than naming preferences — a reader who
greps the name finds nothing:

  - `pto_submit_task` x16 -> `rt_submit_task`, the actual orchestration entry in
    `orchestration/orchestration_api.h`.
  - `pto_runtime_c_api` x2 -> `runtime_c_api`, the actual file name.

`git grep -w` returning only comments is what established each was absent.

**`tests/lint/check_retired_names.py`**, wired into pre-commit. Rule 10 already
demanded that "the count only goes down"; nothing enforced it, and a count written
into prose cannot stay true. The hook fails on any new `PTO Runtime`,
`PTO Runtime2`, or bare `Runtime2`, so the rule can now point at it and drop the
number it could not keep current.

The hook is deliberately narrow, and the reason is the third population rule 10
lumped into one Tier A row.

## What is deliberately untouched

**Every live `pto_cpu_sim_*` / `pto_sim_*` hook** — 33 occurrences, all left
alone. `cpu_sim_context.cpp` exports them for "pto-isa via
`dlsym(RTLD_DEFAULT)`", and `device_runner_base.cpp` fetches
`pto_sim_register_hooks` by `dlsym`. Renaming one produces **no compile error** —
just a hook that is never found at run time. That is the "handful of Tier-C names
hiding in it" rule 10's no-sweep ban was written to protect, and it is real; it
just hides in the lowercase `pto_*` namespace, not in the banner namespace. So the
hook checks only the brand spellings, and rule 10's Tier A is split into A1
(brand prose, mechanically safe) and A2 (dangling `pto_*` references, grep first),
with the `dlsym` trap named in Tier C.

**Six mentions that named a retired variable only for history** — "the
now-retired `PTO2_RING_*` environment variables", "the process-wide `PTO2_RING_*`
env, since retired" — now state the current mechanism and what it enables
instead. They explained a design by contrast with something the reader cannot
find. (`per_task_runtime_env/README.md` also had "shared the process-wide
process-wide", a duplicated line from #1980's edit.)

`PTO2_*` is deliberately left out of the hook, because what remains of that
spelling is load-bearing in two ways the hook cannot distinguish:

  - Twelve occurrences belong to `warn_on_retired_ring_env()` in each
    `host/runtime_maker.cpp` — a `kRetired[]` array of env names and the comment
    explaining it — plus three doc sites that tell a reader what the warning they
    just saw means. The names cannot leave without the warning leaving, and that
    warning is one day old (#1980, 2026-08-25); rule 10 holds it up as the model
    for retiring a knob rather than silently falling back.
  - Eight are `PTO2_MANUAL_MAX_SEQ`, pypto-lib's own variable, which the qwen
    READMEs tell a user to `export` literally.

So banning the spelling would either delete a live diagnostic or break working
instructions.

## Verification

Comments and one new lint script; no declaration, signature or expression changes.

  - Full product build — both arches, sim and onboard, all four runtimes.
  - cpput 119/119.
  - The hook returns 0 over all 2294 tracked files, 1 on a probe containing
    `PTO Runtime2 - Something`, 1 on a bare `Runtime2`, and 0 on
    `codestyle.md` itself, which is exempt because a rule has to spell what it bans.
  - `clang-format --dry-run --Werror` clean on all 42 changed C++ files; every one
    of them is a matched a2a3/a5 pair.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---
 .claude/rules/codestyle.md                    | 45 ++++++----
 .pre-commit-config.yaml                       |  7 ++
 .../paged_attention_ringbuffer/README.md      |  6 +-
 .../test_paged_attention_ringbuffer.py        |  2 +-
 .../paged_attention_ringbuffer/README.md      |  6 +-
 .../test_paged_attention_ringbuffer.py        |  2 +-
 .../workers/l3/per_task_runtime_env/README.md |  6 +-
 .../workers/l3/per_task_runtime_env/main.py   |  2 +-
 .../platform/onboard/host/runtime_c_api.cpp   |  2 +-
 src/a2a3/platform/sim/host/runtime_c_api.cpp  |  2 +-
 .../host_build_graph/runtime/runtime_types.h  |  4 +-
 .../runtime/scheduler/scheduler.cpp           |  2 +-
 .../runtime/scheduler/scheduler.h             |  2 +-
 .../runtime/shared/shared_memory.cpp          |  2 +-
 .../runtime/shared/tensormap.cpp              |  2 +-
 .../host_build_graph/runtime/tensormap.h      |  4 +-
 .../runtime/host_build_graph/runtime/types.h  |  6 +-
 .../runtime/orchestrator.cpp                  |  2 +-
 .../runtime/orchestrator.h                    |  2 +-
 .../runtime/ring_buffer.cpp                   |  2 +-
 .../runtime/ring_buffer.h                     |  2 +-
 .../runtime/scheduler/scheduler.cpp           |  2 +-
 .../runtime/scheduler/scheduler.h             |  2 +-
 .../runtime/shared/shared_memory.cpp          |  2 +-
 .../runtime/shared/tensormap.cpp              |  2 +-
 .../runtime/shared_memory.h                   |  2 +-
 .../runtime/tensormap.h                       |  4 +-
 .../tensormap_and_ringbuffer/runtime/types.h  |  6 +-
 .../platform/onboard/host/runtime_c_api.cpp   |  2 +-
 src/a5/platform/sim/host/runtime_c_api.cpp    |  2 +-
 .../host_build_graph/runtime/runtime_types.h  |  4 +-
 .../runtime/scheduler/scheduler.cpp           |  2 +-
 .../runtime/scheduler/scheduler.h             |  2 +-
 .../runtime/shared/shared_memory.cpp          |  2 +-
 .../runtime/shared/tensormap.cpp              |  2 +-
 .../host_build_graph/runtime/tensormap.h      |  4 +-
 .../runtime/host_build_graph/runtime/types.h  |  6 +-
 .../runtime/orchestrator.cpp                  |  2 +-
 .../runtime/orchestrator.h                    |  2 +-
 .../runtime/ring_buffer.cpp                   |  2 +-
 .../runtime/ring_buffer.h                     |  2 +-
 .../runtime/scheduler/scheduler.cpp           |  2 +-
 .../runtime/scheduler/scheduler.h             |  2 +-
 .../runtime/shared/shared_memory.cpp          |  2 +-
 .../runtime/shared/tensormap.cpp              |  2 +-
 .../runtime/shared_memory.h                   |  2 +-
 .../runtime/tensormap.h                       |  4 +-
 .../tensormap_and_ringbuffer/runtime/types.h  |  6 +-
 .../platform/onboard/host/c_api_shared.cpp    |  2 +-
 .../onboard/host/device_runner_base.h         |  2 +-
 tests/lint/check_retired_names.py             | 83 +++++++++++++++++++
 51 files changed, 187 insertions(+), 84 deletions(-)
 create mode 100644 tests/lint/check_retired_names.py

diff --git a/.claude/rules/codestyle.md b/.claude/rules/codestyle.md
index 25684a8ca1..ac7411fbc3 100644
--- a/.claude/rules/codestyle.md
+++ b/.claude/rules/codestyle.md
@@ -127,28 +127,39 @@
     "PTO Runtime2", and a bare "Runtime2" are not names of anything** — the
     `2` never denoted a version any reader can identify.
 
-    **The retirement is complete** (snapshot 2026-08-24: 6.6k occurrences across
-    367 files on 2026-07-26 → 0 that this repo reads). Nothing here reads a
-    `PTO2` name any more: the last of them were the `PTO2_RING_*` ring-sizing
-    environment variables, retired in favour of per-task
-    `CallConfig.runtime_env`. What is left in the tree is this rule's own
-    examples, the warning that fires if a caller still exports a retired ring
-    variable, prose recording that these names are gone, and
-    `PTO2_MANUAL_MAX_SEQ` — a pypto-lib knob two example READMEs document and
-    this repo never reads. **So a new `PTO2` match is a defect** — there is no
-    backlog to work through. Find the surface with:
+    **No `PTO2` identifier is left.** The last of them were the `PTO2_RING_*`
+    ring-sizing environment variables, retired in favour of per-task
+    `CallConfig.runtime_env`; `git grep -Io -E "PTO2|pto2_"` now finds only this
+    rule's own examples, the warning that fires if a caller still exports a
+    retired ring variable, prose recording that these names are gone, and
+    `PTO2_MANUAL_MAX_SEQ` — a pypto-lib knob two example READMEs document and this
+    repo never reads. **So a new `PTO2` match is a defect.**
+
+    **The brand spellings are held by a hook, not by a count.**
+    `tests/lint/check_retired_names.py` fails pre-commit on any new
+    `PTO Runtime`, `PTO Runtime2`, or bare `Runtime2`. That hook exists because
+    this paragraph once asserted the whole surface was empty while the rule's own
+    grep found 38 banners across 36 files: the assertion had been measured with
+    `PTO2|pto2_`, which cannot see a brand name with a space in it. Do not put a
+    number here again — put it in the hook.
+
+    Find the surface with the rule's own pattern, which is wider than the hook's
+    on purpose (it also reaches the tiers below):
 
     ```bash
     grep -rIn -E "PTO Runtime2?|PTO2|pto2_|pto_runtime2" --include=* . | grep -v '^\./\.git/'
     ```
 
-    Each match falls in exactly one tier, and the tier decides what you owe:
+    Each match falls in exactly one tier, and the tier decides what you owe. Note
+    that **the first two tiers share the `pto_*` namespace and have opposite
+    risk** — that is the trap this table exists to spell out:
 
     | Tier | What | Policy |
     | ---- | ---- | ------ |
-    | **A — prose** | Brand mentions in docs, headings, skill descriptions, issue templates, and code comments (`# PTO Runtime2 Profiling Levels`, "the PTO Runtime consists of…") | **Fix on sight, unconditionally.** No compile risk, no contract. Say `simpler`, or name the actual component ("the AICPU orchestrator", "the `tensormap_and_ringbuffer` runtime") when that is what the sentence means. |
+    | **A1 — brand prose** | The brand itself in docs, headings, skill descriptions, issue templates, and code comments (`# PTO Runtime2 Profiling Levels`, "the PTO Runtime consists of…") | **Fix on sight, unconditionally**, and the hook will make you. No compile risk, no contract, and no Tier-C name can hide in a file banner. Say `simpler`, or name the actual component ("the AICPU orchestrator", "the `tensormap_and_ringbuffer` runtime"). Follow the banner style already in the tree: `orchestrator_core/orchestrator.cpp` opens `* host_build_graph orchestrator implementation`. |
+    | **A2 — comments naming a `pto_*` that does not exist** | e.g. `pto_submit_task` (the entry is `rt_submit_task`), `pto_runtime2_init` (the work is `SchedulerState::init_data_from_layout`) | **Fix on sight**, but this is a [`doc-consistency.md`](doc-consistency.md) §3 defect, not a naming preference: a reader who greps the name finds nothing. Confirm the symbol is absent before renaming it — `git grep -w <name>` returning only comments is the test. |
     | **B — internal identifiers** | `PTO2Foo` types, `pto2_*` functions, internal `PTO2_*` macros and enumerators, `pto_*.h` / `pto_runtime2*.cpp` file names | Rename **only when you are already modifying that code**, per rule 9, and finish the identifier you started (below). |
-    | **C — external contracts** | `runtime_env` knobs, `extern "C"` symbols in `runtime_c_api.h`, on-wire / serialized names | **Exempt until a migration ships.** Renaming these breaks callers in other repos. Ask the user before touching one; land it only with a compatibility alias or a coordinated cross-repo change. |
+    | **C — external contracts** | `runtime_env` knobs, `extern "C"` symbols in `runtime_c_api.h`, on-wire / serialized names, and **every live `pto_cpu_sim_*` / `pto_sim_*` hook** | **Exempt until a migration ships.** Renaming these breaks callers in other repos. The sim hooks are the worst case and the reason A2 above demands a grep first: `cpu_sim_context.cpp` exports them for "pto-isa via `dlsym(RTLD_DEFAULT)`" and `device_runner_base.cpp` fetches `pto_sim_register_hooks` by `dlsym`, so a rename produces **no compile error** — just a hook that is never found at run time. Ask the user before touching one; land it only with a compatibility alias or a coordinated cross-repo change. |
 
     An environment variable is the worst case in Tier C and the reason it
     exists: an unrecognised name is *ignored*, so the rename fails silently
@@ -172,9 +183,11 @@
       tensormap_and_ringbuffer}/` trees are near-duplicates, so a Tier-B
       rename in one of them must land in its siblings in the same commit.
       Verify with the grep above returning zero hits for that identifier.
-    - **The count only goes down.** Introducing a new `PTO2`/`PTO Runtime`
-      spelling anywhere — including by copying an existing `pto_*.h` to a
-      new arch — is a defect, not neutral. Rule 9 makes this unconditional.
+    - **The count only goes down**, and for the brand spellings
+      `tests/lint/check_retired_names.py` enforces it. Introducing a new
+      `PTO2`/`PTO Runtime` spelling anywhere — including by copying an existing
+      `pto_*.h` to a new arch — is a defect, not neutral. Rule 9 makes this
+      unconditional.
     - **Check the target name against three things, not one.** The bare name
       may be taken by the host orchestrator under `src/common/hierarchical/`
       (`TensorMap`, `ReadyQueue`, `TaskState`, `HeapRing`, `MAX_SCOPE_DEPTH`
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index c44dcc97b6..63c528a598 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -32,6 +32,13 @@ repos:
           language_version: python3
           files: ^(examples|tests/st)/(.*/)?test_[^/]*\.py$
 
+        - id: check-retired-names
+          name: check-retired-names
+          entry: python tests/lint/check_retired_names.py
+          language: python
+          language_version: python3
+          exclude: ^3rdparty/|vendor/
+
     - repo: https://github.com/pre-commit/pre-commit-hooks
       rev: v4.6.0
       hooks:
diff --git a/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md b/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md
index 82911af6aa..056e28e38b 100644
--- a/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md
+++ b/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md
@@ -29,9 +29,9 @@ referenced, the golden check fails or the orchestrator wedges.
 
 Two things this example is the reference for:
 
-- **Per-case ring sizing through `config.runtime_env`**, not the process-global
-  now-retired `PTO2_RING_*` environment variables. The rings are sized per task, so one
-  suite can mix a stress case with normally-sized ones.
+- **Per-case ring sizing through `config.runtime_env`.** The rings are sized per
+  task rather than per process, so one suite can mix a stress case with
+  normally-sized ones.
 - **Non-power-of-2 sizes are accepted.** 4 MiB is chosen to keep the stress
   intent compact, not because the runtime requires a round number.
 
diff --git a/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py b/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py
index e66f6e2e49..815431b671 100644
--- a/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py
+++ b/examples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py
@@ -10,7 +10,7 @@
 """Paged attention with small ring buffer sizes — stress test for ring rotation/reclamation.
 
 Drives per-case ring sizing through ``config.runtime_env`` (ring_task_window /
-ring_heap / ring_dep_pool) rather than the process-global PTO2_RING_* env it replaced, plus
+ring_heap / ring_dep_pool), which is per task rather than per process, plus
 INOUT tensors, bfloat16, and AIC+AIV mixed execution.
 """
 
diff --git a/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md b/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md
index 05deeb2be2..cf8fa2d86b 100644
--- a/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md
+++ b/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/README.md
@@ -29,9 +29,9 @@ referenced, the golden check fails or the orchestrator wedges.
 
 Two things this example is the reference for:
 
-- **Per-case ring sizing through `config.runtime_env`**, not the process-global
-  now-retired `PTO2_RING_*` environment variables. The rings are sized per task, so one
-  suite can mix a stress case with normally-sized ones.
+- **Per-case ring sizing through `config.runtime_env`.** The rings are sized per
+  task rather than per process, so one suite can mix a stress case with
+  normally-sized ones.
 - **Non-power-of-2 sizes are accepted.** 4 MiB is chosen to keep the stress
   intent compact, not because the runtime requires a round number.
 
diff --git a/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py b/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py
index e734e97048..49f559f067 100644
--- a/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py
+++ b/examples/a5/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.py
@@ -10,7 +10,7 @@
 """Paged attention with small ring buffer sizes — stress test for ring rotation/reclamation.
 
 Drives per-case ring sizing through ``config.runtime_env`` (ring_task_window /
-ring_heap / ring_dep_pool) rather than the process-global PTO2_RING_* env it replaced, plus
+ring_heap / ring_dep_pool), which is per task rather than per process, plus
 INOUT tensors, bfloat16, and AIC+AIV mixed execution.
 """
 
diff --git a/examples/workers/l3/per_task_runtime_env/README.md b/examples/workers/l3/per_task_runtime_env/README.md
index 5c5bd64631..d7f7318908 100644
--- a/examples/workers/l3/per_task_runtime_env/README.md
+++ b/examples/workers/l3/per_task_runtime_env/README.md
@@ -7,9 +7,9 @@ each need a different ring footprint.
 
 ## What it shows
 
-Before this knob, every L2 dispatched from one L3 shared the process-wide
-process-wide `PTO2_RING_*` env, since retired, and could not be sized independently. Now each
-`submit_next_level` gets its own `CallConfig`:
+Before this knob, every L2 dispatched from one L3 shared one process-wide ring
+sizing and could not be sized independently. Now each `submit_next_level` gets
+its own `CallConfig`:
 
 Each spec sets `ring_task_window` / `ring_heap` / `ring_dep_pool` to a scalar
 (broadcast to every ring) or a 4-entry list (per-ring). `_l2_config` preserves
diff --git a/examples/workers/l3/per_task_runtime_env/main.py b/examples/workers/l3/per_task_runtime_env/main.py
index ae268d7528..cc817ab5ed 100644
--- a/examples/workers/l3/per_task_runtime_env/main.py
+++ b/examples/workers/l3/per_task_runtime_env/main.py
@@ -14,7 +14,7 @@
 several heterogeneous L2 tasks in one launch, and each L2 needs a different
 ring footprint (a heavy task wants a big heap / wide window; a light one is
 fine with the default). Before this knob, all L2 tasks in one L3 launch shared
-the process-wide ``PTO2_RING_*`` env, since retired, and could not be sized independently.
+one process-wide ring sizing and could not be sized independently.
 
 The demo dispatches three L2 tasks: two use the scalar form (one ring value
 broadcast to every ring), and a third passes 4-entry lists for
diff --git a/src/a2a3/platform/onboard/host/runtime_c_api.cpp b/src/a2a3/platform/onboard/host/runtime_c_api.cpp
index d9bdb881c9..1e3c31679d 100644
--- a/src/a2a3/platform/onboard/host/runtime_c_api.cpp
+++ b/src/a2a3/platform/onboard/host/runtime_c_api.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime C API — a2a3 arch-specific entries
+ * simpler host-runtime C API — a2a3 arch-specific entries
  *
  * The shared c_api glue (simpler_init / simpler_register_callable / simpler_run /
  * device_*_ctx / etc.) lives in
diff --git a/src/a2a3/platform/sim/host/runtime_c_api.cpp b/src/a2a3/platform/sim/host/runtime_c_api.cpp
index 1ec1319bf0..6130331280 100644
--- a/src/a2a3/platform/sim/host/runtime_c_api.cpp
+++ b/src/a2a3/platform/sim/host/runtime_c_api.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime C API — a2a3 sim arch-specific entries.
+ * simpler host-runtime C API — a2a3 sim arch-specific entries.
  *
  * The shared c_api glue (simpler_init / simpler_register_callable / simpler_run /
  * device_*_ctx / etc.) lives in `src/common/platform/sim/host/c_api_shared.cpp`
diff --git a/src/a2a3/runtime/host_build_graph/runtime/runtime_types.h b/src/a2a3/runtime/host_build_graph/runtime/runtime_types.h
index f0dee16f41..766fd9b3b8 100644
--- a/src/a2a3/runtime/host_build_graph/runtime/runtime_types.h
+++ b/src/a2a3/runtime/host_build_graph/runtime/runtime_types.h
@@ -10,9 +10,9 @@
  */
 
 /**
- * PTO Runtime2 - Core Type Definitions
+ * host_build_graph core type definitions
  *
- * This header defines all fundamental types used by the PTO Runtime2 system:
+ * This header defines all fundamental types used by the host_build_graph runtime:
  * - Configuration constants
  * - Worker types and task states
  * - simpler::hbg::Tensor regions and task parameters
diff --git a/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.cpp b/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.cpp
index b54d7bd7b0..1d70651885 100644
--- a/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.cpp
+++ b/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Scheduler Implementation
+ * host_build_graph scheduler implementation
  *
  * Implements scheduler state management, ready queues, and task lifecycle.
  *
diff --git a/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.h b/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.h
index 8b8bafec66..0022102a45 100644
--- a/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.h
+++ b/src/a2a3/runtime/host_build_graph/runtime/scheduler/scheduler.h
@@ -10,7 +10,7 @@
  */
 
 /**
- * PTO Runtime2 - Scheduler Interface
+ * host_build_graph scheduler interface
  *
  * The Scheduler is responsible for:
  * 1. Maintaining per-resource-shape ready queues
diff --git a/src/a2a3/runtime/host_build_graph/runtime/shared/shared_memory.cpp b/src/a2a3/runtime/host_build_graph/runtime/shared/shared_memory.cpp
index a497349736..c78e584240 100644
--- a/src/a2a3/runtime/host_build_graph/runtime/shared/shared_memory.cpp
+++ b/src/a2a3/runtime/host_build_graph/runtime/shared/shared_memory.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Shared Memory Implementation
+ * host_build_graph shared-memory implementation
  *
  * Implements shared memory allocation, initialization, and management
  * for Orchestrator-Scheduler communication.
diff --git a/src/a2a3/runtime/host_build_graph/runtime/shared/tensormap.cpp b/src/a2a3/runtime/host_build_graph/runtime/shared/tensormap.cpp
index f75320d63d..adc92ae199 100644
--- a/src/a2a3/runtime/host_build_graph/runtime/shared/tensormap.cpp
+++ b/src/a2a3/runtime/host_build_graph/runtime/shared/tensormap.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - TensorMap Implementation
+ * host_build_graph TensorMap implementation
  *
  * Implements TensorMap with a fixed-capacity entry pool. Task completion does
  * not invalidate entries; dependency computation explicitly removes only
diff --git a/src/a2a3/runtime/host_build_graph/runtime/tensormap.h b/src/a2a3/runtime/host_build_graph/runtime/tensormap.h
index f08672a9ba..81aa5b24cf 100644
--- a/src/a2a3/runtime/host_build_graph/runtime/tensormap.h
+++ b/src/a2a3/runtime/host_build_graph/runtime/tensormap.h
@@ -10,11 +10,11 @@
  */
 
 /**
- * PTO Runtime2 - TensorMap Interface
+ * host_build_graph TensorMap interface
  *
  * TensorMap provides producer lookup for dependency discovery:
  * - Maps simpler::hbg::Tensor -> producer task ID
- * - Used by pto_submit_task() to find dependencies
+ * - Used by rt_submit_task() to find dependencies
  *
  * host_build_graph runs its orchestrator on the host, so this map is host-only
  * state: it owns its four arrays outright rather than addressing them as offsets
diff --git a/src/a2a3/runtime/host_build_graph/runtime/types.h b/src/a2a3/runtime/host_build_graph/runtime/types.h
index f110967f21..347d7c481e 100644
--- a/src/a2a3/runtime/host_build_graph/runtime/types.h
+++ b/src/a2a3/runtime/host_build_graph/runtime/types.h
@@ -13,7 +13,7 @@
  *
  * Standalone header defining orchestration-specific types for:
  * - TaskOutputTensors: Return value from submit containing materialized output ChipTensors
- * - Arg: Aggregated argument container for pto_submit_task API
+ * - Arg: Aggregated argument container for rt_submit_task API
  *
  * simpler::hbg::Tensor descriptor types (simpler::hbg::Tensor, PTOBufferHandle, TensorCreateInfo) are
  * defined in tensor.h.
@@ -137,7 +137,7 @@ class TaskOutputTensors {
 using TaskSubmitResult = TaskOutputTensors;
 
 // =============================================================================
-// Argument Types (for pto_submit_task API)
+// Argument Types (for rt_submit_task API)
 // =============================================================================
 
 // TensorArgType is defined in tensor.h (included via task_args.h above)
@@ -182,7 +182,7 @@ class TensorRef {
 };
 
 /**
- * Aggregated argument container for pto_submit_task
+ * Aggregated argument container for rt_submit_task
  *
  * Inherits storage from TaskArgsTpl<TensorRef, uint64_t, MAX_TENSOR_ARGS, MAX_SCALAR_ARGS, TensorArgType>.
  * Each tensor slot stores a TensorRef union (simpler::hbg::Tensor* or TensorCreateInfo)
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp
index 0f3427fc2a..399131a03c 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp
@@ -10,7 +10,7 @@
  */
 
 /**
- * PTO Runtime2 - Orchestrator Implementation
+ * tensormap_and_ringbuffer orchestrator implementation
  *
  * Implements orchestrator state management, scope handling, and task submission.
  *
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h
index 397442f2be..126fc56f0c 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Orchestrator Interface
+ * tensormap_and_ringbuffer orchestrator interface
  *
  * The Orchestrator is responsible for:
  * 1. Executing the orchestration function (Turing-complete control flow)
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp
index f76747cc3f..744a619ebc 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Ring Buffer Implementation
+ * tensormap_and_ringbuffer ring buffer implementation
  *
  * Implements DepListPool ring buffer for zero-overhead dependency management.
  * TaskAllocator methods are defined inline in ring_buffer.h.
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h
index 73e2ada70a..1230183b8b 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Ring Buffer Data Structures
+ * tensormap_and_ringbuffer ring buffer data structures
  *
  * Implements ring buffer designs for zero-overhead memory management:
  *
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp
index 6c5e42adf2..53b23794a5 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Scheduler Implementation
+ * tensormap_and_ringbuffer scheduler implementation
  *
  * Implements scheduler state management, ready queues, and task lifecycle.
  *
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h
index 3c5096066c..7013e5acf5 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h
@@ -10,7 +10,7 @@
  */
 
 /**
- * PTO Runtime2 - Scheduler Interface
+ * tensormap_and_ringbuffer scheduler interface
  *
  * The Scheduler is responsible for:
  * 1. Maintaining per-resource-shape ready queues
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp
index 8d41f3b657..bd693e3402 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Shared Memory Implementation
+ * tensormap_and_ringbuffer shared-memory implementation
  *
  * Implements shared memory allocation, initialization, and management
  * for Orchestrator-Scheduler communication.
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp
index a5ed7174e5..3680f9f0c4 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - TensorMap Implementation
+ * tensormap_and_ringbuffer TensorMap implementation
  *
  * Implements TensorMap with ring buffer pool, lazy invalidation,
  * and chain truncation optimization.
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h
index 2bf29330e9..6f3be40b6d 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Shared Memory Layout
+ * tensormap_and_ringbuffer shared-memory layout
  *
  * Defines the shared memory structure for Orchestrator-Scheduler communication.
  *
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/tensormap.h b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/tensormap.h
index 0d450bd385..25cc8b208d 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/tensormap.h
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/tensormap.h
@@ -10,11 +10,11 @@
  */
 
 /**
- * PTO Runtime2 - TensorMap Interface
+ * tensormap_and_ringbuffer TensorMap interface
  *
  * TensorMap provides producer lookup for dependency discovery:
  * - Maps simpler::tmr::Tensor -> producer task ID
- * - Used by pto_submit_task() to find dependencies
+ * - Used by rt_submit_task() to find dependencies
  *
  * Key design features:
  * 1. Ring buffer pool for entries (no malloc/free)
diff --git a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/types.h b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/types.h
index 5d8308da96..2bfd6158fa 100644
--- a/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/types.h
+++ b/src/a2a3/runtime/tensormap_and_ringbuffer/runtime/types.h
@@ -13,7 +13,7 @@
  *
  * Standalone header defining orchestration-specific types for:
  * - TaskOutputTensors: Return value from submit containing materialized output ChipTensors
- * - Arg: Aggregated argument container for pto_submit_task API
+ * - Arg: Aggregated argument container for rt_submit_task API
  *
  * simpler::tmr::Tensor descriptor types (simpler::tmr::Tensor, PTOBufferHandle, TensorCreateInfo) are
  * defined in tensor.h.
@@ -170,7 +170,7 @@ class TaskOutputTensors {
 };
 
 // =============================================================================
-// Argument Types (for pto_submit_task API)
+// Argument Types (for rt_submit_task API)
 // =============================================================================
 
 // TensorArgType is defined in tensor.h (included via task_args.h above)
@@ -215,7 +215,7 @@ class TensorRef {
 };
 
 /**
- * Aggregated argument container for pto_submit_task
+ * Aggregated argument container for rt_submit_task
  *
  * Inherits storage from TaskArgsTpl<TensorRef, uint64_t, MAX_TENSOR_ARGS, MAX_SCALAR_ARGS, TensorArgType>.
  * Each tensor slot stores a TensorRef union (simpler::tmr::Tensor* or TensorCreateInfo)
diff --git a/src/a5/platform/onboard/host/runtime_c_api.cpp b/src/a5/platform/onboard/host/runtime_c_api.cpp
index a2e777bf28..80afee91e8 100644
--- a/src/a5/platform/onboard/host/runtime_c_api.cpp
+++ b/src/a5/platform/onboard/host/runtime_c_api.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime C API — a5 arch-specific entries
+ * simpler host-runtime C API — a5 arch-specific entries
  *
  * The shared c_api glue (simpler_init / simpler_register_callable / simpler_run /
  * device_*_ctx / etc.) lives in
diff --git a/src/a5/platform/sim/host/runtime_c_api.cpp b/src/a5/platform/sim/host/runtime_c_api.cpp
index e1c410b78a..13a07f8c54 100644
--- a/src/a5/platform/sim/host/runtime_c_api.cpp
+++ b/src/a5/platform/sim/host/runtime_c_api.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime C API — a5 sim arch-specific entries.
+ * simpler host-runtime C API — a5 sim arch-specific entries.
  *
  * The shared c_api glue (simpler_init / simpler_register_callable / simpler_run /
  * device_*_ctx / etc.) lives in `src/common/platform/sim/host/c_api_shared.cpp`
diff --git a/src/a5/runtime/host_build_graph/runtime/runtime_types.h b/src/a5/runtime/host_build_graph/runtime/runtime_types.h
index 805fa02a5b..ceb06882df 100644
--- a/src/a5/runtime/host_build_graph/runtime/runtime_types.h
+++ b/src/a5/runtime/host_build_graph/runtime/runtime_types.h
@@ -10,9 +10,9 @@
  */
 
 /**
- * PTO Runtime2 - Core Type Definitions
+ * host_build_graph core type definitions
  *
- * This header defines all fundamental types used by the PTO Runtime2 system:
+ * This header defines all fundamental types used by the host_build_graph runtime:
  * - Configuration constants
  * - Worker types and task states
  * - simpler::hbg::Tensor regions and task parameters
diff --git a/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.cpp b/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.cpp
index b54d7bd7b0..1d70651885 100644
--- a/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.cpp
+++ b/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Scheduler Implementation
+ * host_build_graph scheduler implementation
  *
  * Implements scheduler state management, ready queues, and task lifecycle.
  *
diff --git a/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.h b/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.h
index 8b8bafec66..0022102a45 100644
--- a/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.h
+++ b/src/a5/runtime/host_build_graph/runtime/scheduler/scheduler.h
@@ -10,7 +10,7 @@
  */
 
 /**
- * PTO Runtime2 - Scheduler Interface
+ * host_build_graph scheduler interface
  *
  * The Scheduler is responsible for:
  * 1. Maintaining per-resource-shape ready queues
diff --git a/src/a5/runtime/host_build_graph/runtime/shared/shared_memory.cpp b/src/a5/runtime/host_build_graph/runtime/shared/shared_memory.cpp
index a497349736..c78e584240 100644
--- a/src/a5/runtime/host_build_graph/runtime/shared/shared_memory.cpp
+++ b/src/a5/runtime/host_build_graph/runtime/shared/shared_memory.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Shared Memory Implementation
+ * host_build_graph shared-memory implementation
  *
  * Implements shared memory allocation, initialization, and management
  * for Orchestrator-Scheduler communication.
diff --git a/src/a5/runtime/host_build_graph/runtime/shared/tensormap.cpp b/src/a5/runtime/host_build_graph/runtime/shared/tensormap.cpp
index f75320d63d..adc92ae199 100644
--- a/src/a5/runtime/host_build_graph/runtime/shared/tensormap.cpp
+++ b/src/a5/runtime/host_build_graph/runtime/shared/tensormap.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - TensorMap Implementation
+ * host_build_graph TensorMap implementation
  *
  * Implements TensorMap with a fixed-capacity entry pool. Task completion does
  * not invalidate entries; dependency computation explicitly removes only
diff --git a/src/a5/runtime/host_build_graph/runtime/tensormap.h b/src/a5/runtime/host_build_graph/runtime/tensormap.h
index f08672a9ba..81aa5b24cf 100644
--- a/src/a5/runtime/host_build_graph/runtime/tensormap.h
+++ b/src/a5/runtime/host_build_graph/runtime/tensormap.h
@@ -10,11 +10,11 @@
  */
 
 /**
- * PTO Runtime2 - TensorMap Interface
+ * host_build_graph TensorMap interface
  *
  * TensorMap provides producer lookup for dependency discovery:
  * - Maps simpler::hbg::Tensor -> producer task ID
- * - Used by pto_submit_task() to find dependencies
+ * - Used by rt_submit_task() to find dependencies
  *
  * host_build_graph runs its orchestrator on the host, so this map is host-only
  * state: it owns its four arrays outright rather than addressing them as offsets
diff --git a/src/a5/runtime/host_build_graph/runtime/types.h b/src/a5/runtime/host_build_graph/runtime/types.h
index f110967f21..347d7c481e 100644
--- a/src/a5/runtime/host_build_graph/runtime/types.h
+++ b/src/a5/runtime/host_build_graph/runtime/types.h
@@ -13,7 +13,7 @@
  *
  * Standalone header defining orchestration-specific types for:
  * - TaskOutputTensors: Return value from submit containing materialized output ChipTensors
- * - Arg: Aggregated argument container for pto_submit_task API
+ * - Arg: Aggregated argument container for rt_submit_task API
  *
  * simpler::hbg::Tensor descriptor types (simpler::hbg::Tensor, PTOBufferHandle, TensorCreateInfo) are
  * defined in tensor.h.
@@ -137,7 +137,7 @@ class TaskOutputTensors {
 using TaskSubmitResult = TaskOutputTensors;
 
 // =============================================================================
-// Argument Types (for pto_submit_task API)
+// Argument Types (for rt_submit_task API)
 // =============================================================================
 
 // TensorArgType is defined in tensor.h (included via task_args.h above)
@@ -182,7 +182,7 @@ class TensorRef {
 };
 
 /**
- * Aggregated argument container for pto_submit_task
+ * Aggregated argument container for rt_submit_task
  *
  * Inherits storage from TaskArgsTpl<TensorRef, uint64_t, MAX_TENSOR_ARGS, MAX_SCALAR_ARGS, TensorArgType>.
  * Each tensor slot stores a TensorRef union (simpler::hbg::Tensor* or TensorCreateInfo)
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp b/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp
index 0f3a7ae57a..52581bcc03 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.cpp
@@ -10,7 +10,7 @@
  */
 
 /**
- * PTO Runtime2 - Orchestrator Implementation
+ * tensormap_and_ringbuffer orchestrator implementation
  *
  * Implements orchestrator state management, scope handling, and task submission.
  *
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h b/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h
index 397442f2be..126fc56f0c 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/orchestrator.h
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Orchestrator Interface
+ * tensormap_and_ringbuffer orchestrator interface
  *
  * The Orchestrator is responsible for:
  * 1. Executing the orchestration function (Turing-complete control flow)
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp b/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp
index 4e959a83b1..982786daf4 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Ring Buffer Implementation
+ * tensormap_and_ringbuffer ring buffer implementation
  *
  * Implements DepListPool ring buffer for zero-overhead dependency management.
  * TaskAllocator methods are defined inline in ring_buffer.h.
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h b/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h
index e48a507832..d4d3c69302 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/ring_buffer.h
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Ring Buffer Data Structures
+ * tensormap_and_ringbuffer ring buffer data structures
  *
  * Implements ring buffer designs for zero-overhead memory management:
  *
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp b/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp
index 6c5e42adf2..53b23794a5 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Scheduler Implementation
+ * tensormap_and_ringbuffer scheduler implementation
  *
  * Implements scheduler state management, ready queues, and task lifecycle.
  *
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h b/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h
index eaf36a261b..ced25fe2bf 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/scheduler/scheduler.h
@@ -10,7 +10,7 @@
  */
 
 /**
- * PTO Runtime2 - Scheduler Interface
+ * tensormap_and_ringbuffer scheduler interface
  *
  * The Scheduler is responsible for:
  * 1. Maintaining per-resource-shape ready queues
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp b/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp
index 8d41f3b657..bd693e3402 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/shared_memory.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Shared Memory Implementation
+ * tensormap_and_ringbuffer shared-memory implementation
  *
  * Implements shared memory allocation, initialization, and management
  * for Orchestrator-Scheduler communication.
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp b/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp
index a5ed7174e5..3680f9f0c4 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared/tensormap.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - TensorMap Implementation
+ * tensormap_and_ringbuffer TensorMap implementation
  *
  * Implements TensorMap with ring buffer pool, lazy invalidation,
  * and chain truncation optimization.
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h b/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h
index 2bf29330e9..6f3be40b6d 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/shared_memory.h
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * PTO Runtime2 - Shared Memory Layout
+ * tensormap_and_ringbuffer shared-memory layout
  *
  * Defines the shared memory structure for Orchestrator-Scheduler communication.
  *
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/tensormap.h b/src/a5/runtime/tensormap_and_ringbuffer/runtime/tensormap.h
index 0d450bd385..25cc8b208d 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/tensormap.h
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/tensormap.h
@@ -10,11 +10,11 @@
  */
 
 /**
- * PTO Runtime2 - TensorMap Interface
+ * tensormap_and_ringbuffer TensorMap interface
  *
  * TensorMap provides producer lookup for dependency discovery:
  * - Maps simpler::tmr::Tensor -> producer task ID
- * - Used by pto_submit_task() to find dependencies
+ * - Used by rt_submit_task() to find dependencies
  *
  * Key design features:
  * 1. Ring buffer pool for entries (no malloc/free)
diff --git a/src/a5/runtime/tensormap_and_ringbuffer/runtime/types.h b/src/a5/runtime/tensormap_and_ringbuffer/runtime/types.h
index fefc31dcdc..cf5b54ba2b 100644
--- a/src/a5/runtime/tensormap_and_ringbuffer/runtime/types.h
+++ b/src/a5/runtime/tensormap_and_ringbuffer/runtime/types.h
@@ -13,7 +13,7 @@
  *
  * Standalone header defining orchestration-specific types for:
  * - TaskOutputTensors: Return value from submit containing materialized output ChipTensors
- * - Arg: Aggregated argument container for pto_submit_task API
+ * - Arg: Aggregated argument container for rt_submit_task API
  *
  * simpler::tmr::Tensor descriptor types (simpler::tmr::Tensor, PTOBufferHandle, TensorCreateInfo) are
  * defined in tensor.h.
@@ -171,7 +171,7 @@ class TaskOutputTensors {
 };
 
 // =============================================================================
-// Argument Types (for pto_submit_task API)
+// Argument Types (for rt_submit_task API)
 // =============================================================================
 
 // TensorArgType is defined in tensor.h (included via task_args.h above)
@@ -216,7 +216,7 @@ class TensorRef {
 };
 
 /**
- * Aggregated argument container for pto_submit_task
+ * Aggregated argument container for rt_submit_task
  *
  * Inherits storage from TaskArgsTpl<TensorRef, uint64_t, MAX_TENSOR_ARGS, MAX_SCALAR_ARGS, TensorArgType>.
  * Each tensor slot stores a TensorRef union (simpler::tmr::Tensor* or TensorCreateInfo)
diff --git a/src/common/platform/onboard/host/c_api_shared.cpp b/src/common/platform/onboard/host/c_api_shared.cpp
index 981f42dc64..81e08e5441 100644
--- a/src/common/platform/onboard/host/c_api_shared.cpp
+++ b/src/common/platform/onboard/host/c_api_shared.cpp
@@ -9,7 +9,7 @@
  * -----------------------------------------------------------------------------------------------------------
  */
 /**
- * Shared `pto_runtime_c_api` glue — the byte-identical part of every arch's
+ * Shared `runtime_c_api` glue — the byte-identical part of every arch's
  * onboard `runtime_c_api.cpp`. Linked into each arch's
  * `libhost_runtime.so` directly (not as a separate library) so all C ABI
  * symbols are exported from each `.so` for ChipWorker's `dlsym`.
diff --git a/src/common/platform/onboard/host/device_runner_base.h b/src/common/platform/onboard/host/device_runner_base.h
index e0861ca9d4..4a96d8d74a 100644
--- a/src/common/platform/onboard/host/device_runner_base.h
+++ b/src/common/platform/onboard/host/device_runner_base.h
@@ -511,7 +511,7 @@ class DeviceRunnerBase {
 
     // ---- Virtual entry points called by the shared c_api ----------------
     //
-    // The shared `pto_runtime_c_api` glue (`src/common/platform/onboard/host/
+    // The shared `runtime_c_api` glue (`src/common/platform/onboard/host/
     // c_api_shared.cpp`) works through `DeviceRunnerBase *` and dispatches
     // through these virtuals. Each arch's `DeviceRunner` overrides the
     // enqueue/poll/drain lifecycle and `finalize`; a2a3 and a5 both override
diff --git a/tests/lint/check_retired_names.py b/tests/lint/check_retired_names.py
new file mode 100644
index 0000000000..9ca361123b
--- /dev/null
+++ b/tests/lint/check_retired_names.py
@@ -0,0 +1,83 @@
+# Copyright (c) PyPTO Contributors.
+# This program is free software, you can redistribute it and/or modify it under the terms and conditions of
+# CANN Open Software License Agreement Version 2.0 (the "License").
+# Please refer to the License for details. You may not use this file except in compliance with the License.
+# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
+# INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
+# See LICENSE in the root of the software repository for the full text of the License.
+# -----------------------------------------------------------------------------------------------------------
+"""
+Script to check that the retired brand names do not come back.
+
+`.claude/rules/codestyle.md` rule 10 says "PTO Runtime", "PTO Runtime2" and a bare
+"Runtime2" are not names of anything, and that the count only goes down. That was a
+promise with nothing keeping it: the rule's prose claimed the surface was empty
+while its own grep found 38 banners across 36 files, because the number in the
+prose had been measured with a narrower pattern (`PTO2|pto2_`) than the rule
+prescribes. A count in prose cannot stay true; a hook can.
+
+Scope, and why it is this narrow:
+
+- Only the **brand** spellings are checked. `PTO2_*` still appears legitimately in
+  prose that records the retirement of a specific name ("the now-retired
+  `PTO2_RING_*` variables"), and in `PTO2_MANUAL_MAX_SEQ`, a pypto-lib knob this
+  repository never reads. Banning those would fail the sentences that explain them.
+- The lowercase `pto_*` identifier namespace is **not** checked, and must not be.
+  `pto_cpu_sim_bind_device`, `pto_sim_get_subblock_id`,
+  `pto_sim_get_pipe_shared_state` and `pto_sim_register_hooks` are live symbols at
+  the pto-isa boundary, resolved by `dlsym(RTLD_DEFAULT)`. Renaming one produces no
+  compile error — just a hook that is never found at run time.
+"""
+
+import argparse
+import re
+import sys
+from pathlib import Path
+
+# "PTO Runtime", "PTO Runtime2", "Runtime2" as a standalone word.
+RETIRED_BRAND = re.compile(r"PTO[ _-]Runtime2?\b|\bRuntime2\b")
+
+# The rule has to spell the names it bans, and this hook has to quote them to
+# explain itself. Paths are repo-relative and matched exactly.
+EXEMPT = frozenset(
+    {
+        ".claude/rules/codestyle.md",
+        "tests/lint/check_retired_names.py",
+    }
+)
+
+
+def offending_lines(path: Path) -> list[tuple[int, str]]:
+    try:
+        text = path.read_text(encoding="utf-8")
+    except (OSError, UnicodeDecodeError):
+        return []
+    return [(lineno, line.strip()) for lineno, line in enumerate(text.splitlines(), 1) if RETIRED_BRAND.search(line)]
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("files", nargs="*", help="files to check (pre-commit passes the staged set)")
+    args = parser.parse_args()
+
+    failures = []
+    for name in args.files:
+        if name in EXEMPT:
+            continue
+        for lineno, line in offending_lines(Path(name)):
+            failures.append(f"{name}:{lineno}: {line}")
+
+    if not failures:
+        return 0
+
+    print("Retired brand name reintroduced. The project is `simpler`; its runtimes are")
+    print("`host_build_graph` and `tensormap_and_ringbuffer`. Name the runtime, or the")
+    print("component the sentence actually means — see .claude/rules/codestyle.md rule 10.")
+    print()
+    for failure in failures:
+        print(f"  {failure}")
+    return 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())