Three surfaces start updates against one checkout: a terminal
"hermes update", the dashboard's Update button (which spawns that same
command detached), and the desktop's, which hands off to the Tauri
updater. Only the Tauri updater published the in-progress marker, and
only Electron read it -- to gate backend startup, not to stop a second
updater. So a dashboard-spawned update and an installer-driven git
checkout could mutate the same tree concurrently, rewriting source under
a live interpreter.
Claim the same marker from cmd_update rather than adding a second
mechanism: same path, same pid+started_at payload the Rust and Electron
readers already parse. A marker only counts as live when its pid is alive
and it is inside the shared age ceiling, so a crashed updater self-heals
instead of wedging every future update. Release only removes a marker we
still own, leaving a handoff partner's claim intact.
Refusing exits 2, matching the existing concurrent-instance contract the
Tauri updater already recognizes.
hermes-setup.exe bakes its build-time commit into the binary
(BUILD_PIN_COMMIT) and passes it as -Commit on every install-mode run,
including the retry the desktop's "Update didn't finish" screen kicks
off. The repository stage checked that SHA out unconditionally, so an
installer built months earlier rewound a current managed checkout to its
build commit -- 9,160 commits in the reported case -- leaving ancient
source against a current venv. npm then failed on workspaces that did not
exist yet at that commit, and every later update ran against the wrong
tree.
Skip the pin when its target is already an ancestor of HEAD. Fresh clones
have no such ancestry so reproducible/CI pinning is unchanged, and
--force-commit / -ForceCommit still rolls back on purpose.
- Remove tests/-shadowing sys.path.insert(dirname/'..') from 11 test files:
it prepended the tests/ dir itself to sys.path, so 'import agent' /
'import hermes_cli' resolved to the test packages and collection died
with ModuleNotFoundError depending on import order (2 files failed in
every full-suite run; 9 more were latent).
- Patch call_llm in 5 context-compressor tests that called compress()
unmocked: each burned ~50s attempting live LLM traffic through the
relay before falling back (572s file — the slowest in the suite, and
flaky under the 300s per-file timeout). File now runs in ~5s.
- agent/redact.py: fix two catastrophically-backtracking regexes hit by
the compressor's redaction pass on large payloads —
_STRICT_URL_USERINFO_RE anchors on the mandatory '//' (optional-scheme
prefix backtracked O(n^2): ~55s on a 320KB payload, now sub-ms;
output-equivalence fuzz-verified on 20k random strings), and the
_CFG_DOTTED_RE/_CFG_ANCHORED_RE subs gain an exact linear keyword
pre-gate so secret-free text skips the quadratic pattern entirely.
- tests/gateway/test_feishu.py: version-guard the extra_ua_tags SDK
signature check; the repo pins lark-oapi==1.6.8 but stale local
installs (1.5.3) fail the assertion — skip below the pin.
- tests/tools/test_managed_browserbase_and_modal.py: stub
agent.redact + agent.credential_persistence in the fake agent package
(empty __path__ blocks all real agent.* imports added since the fake
was written).
- tests/gateway/test_startup_restart_race.py: raise wait_for timeouts
2s -> 30s; 2s wall-clock on a loaded 40-worker box flaked in the
baseline run (passes instantly when the box is quiet).
_stop_mcp_loop() stopped and closed the background loop without reaping
the tasks still on it. A task left suspended is resumed later by the GC,
whose finalizer drives its cleanup against the now-closed loop:
Exception ignored in: <coroutine object MCPServerTask.run ...>
File "tools/mcp_tool.py", line 2947, in run
parked = await self._wait_for_reconnect_or_shutdown(
File "tools/mcp_tool.py", line 2161, in _wait_for_reconnect_or_shutdown
t.cancel()
RuntimeError: Event loop is closed
shutdown_mcp_servers() only reaps servers held in _servers, so a server
that parked after exhausting its initial-connect budget — never inserted
there, because start() raises _error before the caller registers it — has
no owner to signal it and stays suspended until the loop is gone.
Drain the loop the way asyncio.run() does: cancel the remaining tasks and
gather them while the loop is still open, so each runs its own finally.
Cancel alone is not enough — Task.cancel() only schedules the throw.
This resolves the reported traceback, but not the ownership bug that
strands the task in the first place; that needs a follow-up. Deliberately
not using "Fixes" so #60197 stays open for it.
Addresses #60197
Addresses #66113
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Salvaged from #31671 (@Shizoqua). The config-cache half of that PR was
superseded on main (9b8b054c2d gave _load_config_safe a readonly path),
but this cron-scanner half is still live: _strip_cron_safe_constructs
used re.search + a single str.replace, which only scrubbed occurrences
IDENTICAL to the first match. A cron job loading several GitHub skills
carries heterogeneous auth-header curl forms (-H vs --header, quoting,
token var names) — every non-identical block tripped the
exfil_curl_auth_header detector on every tick, blocking legitimate
GitHub cron jobs.
Now re.sub scrubs every occurrence; the trailing [^\n]* consumes the
URL path so no dangling fragment remains. Sabotage-verified: the old
implementation false-blocks the heterogeneous two-skill prompt the new
regression test pins; exfil to a non-GitHub host is still blocked.
79/79 cron tool tests green.
Follow-up to the #68246 salvage. The backend permission-mode resolution
only checked the DB session_id the tool path passes, but gateway /yolo
keys approval bypass off the gateway session_key (contextvar). Consult
both namespaces so /yolo works on messaging platforms, not just CLI/TUI.
Adds a regression test driving the real approval contextvar + yolo
toggle path E2E.
The earlier scrub covered adapter.py; nine internal QA-campaign tracker IDs
remained in the two new test files, including a module docstring and an
assertion message. They mean nothing to a future reader — describe the
behavior instead. Comments only, no assertion changes.
Both relay Slack knobs read their value through bool(), while the native
adapter they mirror uses str(raw).strip().lower() in {"1","true","yes","on"}.
A YAML-quoted string diverges:
dm_top_level_threads_as_sessions: "false" → relay True, native False
Non-empty strings are truthy, so the escape hatch is silently ignored in
exactly the shape an operator writes to switch it OFF. reply_in_thread has the
same defect and gates reply placement, session keying and run.py's progress
resolver, so one quoted "false" misfires three ways.
Route both through a shared _coerce_flag mirroring native's predicate. Real
booleans pass through untouched; None falls back to the default. Contract §8
documents the accepted spellings.
Tests: both knobs parametrized over the true/false spellings native accepts,
plus the absent-key default.
The DM thread-anchor contract was resolved only in send(). _send_media() —
backing send_image, send_image_file, send_voice, send_video and send_document
— passed reply_to straight to the frame and never touched metadata, so
attachments egressing through the same connector-side Slack sender got both
failure shapes this branch set out to remove:
flat mode → reply_to survives, the image threads UNDER the user's DM
message (the original reported symptom)
thread mode → no metadata.thread_id, and threadTs() never reads reply_to,
so the image lands in the home channel instead of the
per-message thread
Both are reachable: gateway/run.py delivers agent artifacts through
send_voice/send_document.
Extract the three steps that must always happen together (mode gate, mirrored
reply_to_message_id strip, metadata promotion) into
_apply_slack_thread_anchor and route BOTH lanes through it, so text and media
cannot drift again. The media lane copies caller metadata rather than mutating
it — these helpers are called in loops with a shared mapping.
Also fold send_typing/stop_typing's duplicated status-anchor blocks into
_with_status_thread_anchor. They had already drifted (stop_typing omitted the
platform check) and the clear must target the thread the heartbeat set or the
status line sticks until Slack's own timeout.
Tests: media lane pinned in both modes plus the channel and
no-caller-mutation cases; verified as real by reverting the fix and watching
them fail.
Three provably-safe optimizations for O(n)-per-iteration history walks:
1. sanitize_tool_call_arguments: optional identity-keyed cursor (strong
refs to the exact validated message objects) skips re-json.loads-ing
already-validated history each loop iteration. Any list rewrite
(compression, repair, undo, steer) breaks the identity prefix match
and forces re-scan from the divergence point. Wired via a per-agent
cursor dict in conversation_loop.
2. estimate_messages_tokens_rough: per-message memo keyed on a deep
identity fingerprint (strings pinned by strong reference so id()
aliasing is impossible; scalars by value; dicts/lists structurally
with key order). Equal fingerprints imply identical str(shadow)
bytes, hence identical estimates. Unfingerprintable shapes fall
through to direct compute. Bounded FIFO cache (4096 entries).
3. _flush_messages_to_session_db_unlocked: bounded scan that skips the
identity-matched prefix of the previous successful flush's snapshot.
Snapshot only taken on full success; cleared on exception. Compression
rewrites use fresh copies, breaking identity and forcing full re-scan.
Parity proven in tests/agent/test_cursor_optimizations_parity.py:
500-message synthetic histories with tool calls, malformed args, unicode,
element-wise old==new across 3 iterations incl. simulated compression.
Measured (median of 5): sanitize 0.097ms->0.011ms, tokens 1.145ms->0.853ms,
persist-scan 179.5us->10.0us at 500 messages.
The test passed on dev boxes where a cua-driver binary is on PATH but
failed in hermetic CI: _call_tool_via_cli hit resolve_cua_driver_cmd()'s
install-hint early exit before reaching the spawn-env assertion. Pin the
resolver so the test exercises the code path it actually asserts.
Follow-up to the #62821 salvage: the _cua_driver_supports_no_overlay
--help probe is another Windows-reachable spawn; give it the same
windows_hide_flags() treatment. Also adjust the status test to stub
_resolve_driver_cmd (permissions.py resolves via that helper, not
shutil.which).
A Windows-installed cua-driver can return an absolute
``C:\Users\...\cua-driver.exe`` mcp_invocation.command to a Hermes
process running inside WSL. POSIX spawning can't use the raw Windows
string even though the binary is reachable through DrvFS. Translate
``<drive>:\...`` to ``/mnt/<drive>/...`` in _resolve_mcp_invocation
(before the path-separator check, since backslash is not a separator
on POSIX), only when actually running under WSL.
Salvaged from #63532 by @motoblurr (original commit carried a
placeholder 'Hermes Agent <hermes@local>' identity; re-authored).
Fixes#63938 premise.
Apply windows_hide_flags() (CREATE_NO_WINDOW; 0 on POSIX) at the
Windows-reachable cua-driver subprocess boundaries: manifest probe,
update checker, CLI fallback transport, doctor health-report spawn,
and the permissions/status runner. Prevents OpenConsole/Windows
Terminal windows flashing into the foreground when spawned from
GUI-backed Gateway/Desktop processes.
The env-probe half of the original PR was already implemented on main
and is not re-applied here.
Salvaged from #62821 by @ZundamonnoVRChatkaisetu (original commits
carried a placeholder 'Claude Code Enterprise' identity; re-authored
to the contributor's GitHub identity).
Detect a missing cua-driver-serve scheduled task after the installer runs
and retry registration via Start-Process -FilePath/-ArgumentList instead of
interpolating the binary path into a PowerShell command string (which splits
at the first space in a username-space path).
Salvaged from #60880 by @embwl0x. Related: #60808.
Same sibling-mock class as the relay-metrics runtime file — this test
stubs the telemetry gate's config read, which now goes through
read_raw_config_readonly(). Swept the whole test tree for remaining
read_raw_config stubs: all others target consumers that still use the
mutable reader (browser config, url_safety, inventory) and carry no
telemetry keys.
enabled() now reads via read_raw_config_readonly(); the 7 monkeypatch/
patch sites in test_relay_shared_metrics_runtime.py that stubbed
hermes_cli.config.read_raw_config no longer intercepted the read,
failing 18 tests on CI slice 7/8. Repro'd locally, retargeted the
mocks; 147 passed + 2 skipped across both relay metrics files.
Four hot-path consumers paid a full config deepcopy per read:
- telemetry gate relay_shared_metrics.enabled() — runs 2-3x per agent
turn (2x per API call from lifecycle hooks + 1x per tool call) and
called read_raw_config(), which deepcopies the whole raw config every
call. New read_raw_config_readonly() serves the cached dict directly:
248 us -> 4.6 us per call (54x) on Teknium's real 77-key config.
- interruptible_streaming_api_call local-endpoint stale-timeout branch
called load_config() once per API call for every local-model user.
- gateway get_inbound_media_max_bytes() + _get_ephemeral_system_ttl_default()
called load_config() on per-message paths. All three switched to
load_config_readonly() (345 us -> 12 us; PR #28866 lineage).
Together these account for ~90% of the ~1,900 deepcopy primitives per
turn measured in the 26-call stubbed-LLM profile.
read_raw_config_readonly() keeps the (mtime_ns, size) freshness key so
config edits are picked up next call, and preserves the identity
invariant (cache-miss returns the same object later hits serve) —
regression-tested with 'is', per the PR #28866 identity-bug lesson.
The mutable read_raw_config() is unchanged for save-path callers.
581 targeted tests green (config, relay metrics x2, ephemeral reply,
platform base, new readonly suite).
_load_approval_mode now delegates to tools.approval._get_approval_mode,
which reads config via hermes_cli.config.load_config — that path resolves
HERMES_HOME from the environment, not the server module's _hermes_home
attribute. The four approval-mode tests only monkeypatched the module
attribute, so the resolver silently read the developer/CI real config
(default 'smart') instead of the temp fixture. Behavior assertions are
unchanged (invalid → manual fail-safe, YAML off-bool → 'off', three-way
persist + live emit); the fixtures now also set HERMES_HOME so the
canonical read path sees the same temp config.
TUI (tui_gateway/server.py _load_approval_mode): now delegates to
tools.approval._get_approval_mode instead of re-reading config raw via
_load_cfg + _deep_merge(DEFAULT_CONFIG, ...) and normalizing locally.
Behavior fix, not pure refactor: the canonical load_config path applies
managed-scope config overlays and ${VAR} env expansion, plus a legacy
max_turns lift, which the TUI's raw YAML read bypassed — under a managed
config that sets approvals.mode, the TUI previously reported/toggled a
different mode than the approval gate actually enforced. Both surfaces
now agree by construction. Name/signature and the mode-vocabulary clamp
are preserved.
Codex (agent/transports/codex_app_server_session.py): read confirmed the
_decide_exec_approval/_decide_apply_patch_approval paths carry NO
Hermes-side mode/timeout reads — the Hermes resolution already flows in
from agent/codex_runtime.py via tools.approval.is_approval_bypass_active()
(auto_approve_* routing) and via the shared approval-gate callback. So no
code extraction was needed; added docstrings pinning that invariant and a
cross-reference on the protocol-semantic choice mapping
(_approval_choice_to_codex_decision), which intentionally stays local.
Adds tests/tools/test_approval_mode_parity.py: cross-surface invariant
test asserting the core resolver, the TUI path, and the codex bypass
derivation agree for synthetic configs (unset defaults, global mode set,
YAML-bool off, malformed values, whitespace/case), plus a delegation-seam
test proving the TUI has no independent config read left.
Note: gateway/run.py has sibling raw reads but is intentionally untouched
(multiple in-flight PRs); flagged as follow-up.
The old assertion read _drive_health_report's source text for the
_sanitized_cua_env() call — a banned source-reading test that broke when
the spawn moved into _open_mcp with identical runtime behavior. Now
intercepts subprocess.Popen at the _open_mcp seam and asserts the env it
actually receives strips secrets and applies the telemetry opt-out.
cua-driver 0.10.0 marks health_report as risk.class=unclassified and denies
the MCP call with isError. Hermes doctor previously treated the bare
{exit_code:1} structuredContent as a real report and printed
"cua-driver ? on ? — ?" with exit 1.
Detect isError / non-schema payloads, raise HealthReportUnavailable, and
compose a schema_version=1 report from working probes (check_permissions,
list_apps, CLI --version/doctor). Prefer real health_report when present.
Tests cover unclassified denial, schema preference, and overall mapping.
`_canon_key_combo` (the `_BLOCKED_KEY_COMBOS` gate in
`handle_computer_use`) split key strings on `+` only, but the cua-driver
backend's `_parse_key_combo` splits on both `+` and `-`. So a model could
issue `{"action":"key","keys":"ctrl-alt-delete"}` (or `alt-f4`,
`cmd-shift-q`): the gate saw a single unknown token and let it through
while the backend executed the real destructive shortcut.
Split the gate on both `+` and `-` so it canonicalizes combos the same
way the backend does. Non-destructive hyphen combos (`cmd-c`) and the
literal `-` zoom key (`cmd+-`) are unaffected.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
cua-driver 0.7.x can return list_windows/list_apps payloads under
structuredContent.windows, data.windows, data._legacy_windows, or
top-level windows/_legacy_windows (direct CLI responses). The wrapper
only read structuredContent.windows, so discovery came back empty
(capture 0x0, list_apps []) while raw cua-driver calls worked.
- add _windows_from_tool_result(): walks the known envelope shapes in
priority order, skipping empty higher-priority envelopes
- route _load_windows() (MCP + CLI re-fetch paths) through the helper,
covering capture() and focus_app()
- harden _ingest_windows(): skip non-dict members, normalize untrusted
app_name/title/z_index fields
- list_apps(): prefer structuredContent.apps, fall through populated
data/top-level envelopes, derive unique apps from window-shaped
payloads via _apps_from_windows(), keep the text-line fallback last
- tests for every envelope shape, precedence, malformed records, and
app derivation
Salvaged from #63037 (Reaper-Legion), which itself preserved the
original implementation from #57961 (kohoj); #73007 (umi008)
independently proposed the same normalization later.
Fixes#57905
Co-authored-by: Reaper <248977840+Reaper-Forge@users.noreply.github.com>
Co-authored-by: Ulises Millan Guerrero <ulises.millanguerrero@gmail.com>
The disease: ~15 scattered raw yaml.safe_load(config.yaml) reads that
silently miss managed-scope overlay, ${ENV_VAR} expansion, profile-aware
pathing, and root-model normalization. Every new config feature needed an
N-site sweep (incident chain 9cbcc0c9c8 → 732293cf87 → b0e47a98f9 →
1928aa0443). This commit assigns every raw read to an owner and adds a
lint-guard test so the class cannot regrow.
New primitive (additive-only change to hermes_cli/config.py):
read_user_config_raw(path=None) — reads the user file EXACTLY as
written; docstring states it is ONLY legal for write-back round-trips
and raw-file diagnostics. Behavioral reads must use
load_config()/load_config_readonly().
BEHAVIOR FIXES (class-a sites migrated to a canonical loader — these
previously read values that could DIFFER from the effective config):
gateway/run.py _try_resolve_fallback_provider → _load_gateway_runtime_config
keys: fallback_providers/fallback_model (provider, model, base_url,
api_key). Drift fixed: a managed-pinned fallback chain was ignored;
an api_key of "${OPENROUTER_API_KEY}" reached the resolver unexpanded.
gateway/run.py GatewayRunner._load_provider_routing → same loader
key: provider_routing. Drift fixed: managed-pinned routing prefs and
${VAR} templates were ignored.
gateway/run.py GatewayRunner._load_fallback_model → same loader
keys: fallback chain. Same drift as above.
gateway/run.py GatewayRunner._refresh_fallback_model
keeps the raw primitive (its last-known-good-on-parse-failure contract
forbids the fail-open loader, which returns {} on a torn write) but now
applies managed overlay + env expansion inline. Drift fixed: chain
edits under managed scope / env templates were previously frozen out.
tui_gateway/server.py _load_cfg (72 behavioral call sites)
now = raw read + managed overlay (pre-existing) + NEW ${VAR} expansion,
split from a new _load_cfg_raw() write-back primitive. Drift fixed:
e.g. custom_prompt: "hello ${VAR}", agent.system_prompt, model,
api_key/base_url templates reached sessions unexpanded. DEFAULT_CONFIG
is deliberately NOT merged (callers treat missing keys as unset;
`_load_cfg() == {}` sentinels and _save_cfg round-trips depend on it).
tui_gateway/server.py _profile_configured_cwd
keys: terminal.cwd of a NON-launch profile. Drift fixed: managed
overlay + ${VAR} expansion now apply (load_config() would resolve the
wrong profile's home, so the raw primitive + inline pipeline is used).
plugins/platforms/telegram/adapter.py _reload_dm_topics_from_config
→ load_config_readonly(). keys: platforms.telegram.extra.dm_topics.
Drift fixed: managed overlay + profile-aware pathing + expansion.
plugins/memory/holographic _load_plugin_config → load_config_readonly().
keys: plugins.hermes-memory-store.*. Same drift class.
WRITE-BACK ROUND-TRIPS (class-b: stay raw BY DESIGN via read_user_config_raw;
merging defaults/overlay would pollute the saved user file):
gateway/slash_commands.py: model persist x2, _save_gateway_config_key,
memory/skills write_approval toggles
gateway/platforms/yuanbao.py auto-sethome
tui_gateway/server.py _write_config_key + all cfg→_save_cfg blocks
(reasoning show/hide/full/clamp, details_mode[.section], prompt)
→ new _load_cfg_raw()
plugins/memory/holographic save_config
RAW-FILE DIAGNOSTICS + presence-sensitive bridges (class-c: stay raw,
now via the shared primitive with an explanatory comment):
hermes_cli/doctor.py x5 (model validation, stale-root-keys, .env drift,
deprecation sweep, memory-provider probe — the latter two keep their
inline managed overlay where they had one)
gateway/run.py _bridge_max_turns_from_config and the module-level
TERMINAL_*/HERMES_* env bridge (bridging merged defaults would export
all of DEFAULT_CONFIG into the environment; both keep their inline
overlay + expansion)
hermes_cli/send_cmd.py env bridge (same presence-sensitivity)
hermes_cli/gateway.py multiplex-conflict probe (reads the DEFAULT root's
config, not the active profile's — load_config is the wrong owner)
hermes_cli/profiles.py / hermes_cli/web_server.py / tools/wake_word.py
multi-profile reads (load_config targets only the ACTIVE profile home)
cron/jobs.py _resolve_default_model_snapshot and cron/scheduler.py
run_job config read keep their existing inline overlay+expansion but
now share the primitive (their fail-open + last-value semantics and
the deliberate no-defaults merge are preserved exactly).
Failure-semantics audit: every migrated site preserves its exact previous
behavior on missing file ({} / early return) and parse failure (raise into
the caller's existing except, warn, last-known-good, or fail-open) —
read_user_config_raw intentionally mirrors bare open()+safe_load semantics
(raises on parse errors, {} only on FileNotFoundError/non-dict root).
Guard: tests/hermes_cli/test_config_read_guard.py scans the tree for
yaml.safe_load within 6 lines of a 'config.yaml' reference outside an
explicit ALLOWLIST (hermes_cli/config.py, gateway/config.py, gateway/run.py
fallback path, hermes_cli/managed_scope.py which reads the MANAGED file,
gateway/readiness.py parse-health probe) and fails on new offenders.
E2E: tests/hermes_cli/test_config_loader_e2e.py runs a subprocess with a
temp HERMES_HOME (config.yaml containing ${E2E_PROMPT_SUFFIX}) plus a
HERMES_MANAGED_DIR overlay pinning agent.reasoning_effort, asserting
tui _load_cfg resolves "hello world"/"high" while _load_cfg_raw +
_save_cfg round-trip the template and user value verbatim with no
managed/default leakage.
The TTL-expiry test aged only the in-process probe cache; with the new
disk L2 the fresh disk verdict (correctly) served 'ollama' and the swap
to lm-studio wasn't re-detected. In real time-flow the 300s disk TTL
always lapses before the 1h in-proc TTL — the test now compresses both
expiries, matching the scenario it describes. 25/25 pass.
Local-model users paid a fresh probe waterfall on EVERY CLI cold start
inside AIAgent.__init__: detect_local_server_type (up to 4 HTTP GETs,
2s timeout each on a hung server) + /api/show (3s timeout). The
existing caches were in-process only, so back-to-back invocations
(chat -q, cron ticks, subagents) re-paid the network every time.
- New 300s-TTL disk L2 at HERMES_HOME/cache/local_endpoint_probes.json
for detect_local_server_type verdicts and query_ollama_num_ctx
results. Only SUCCESSFUL probes persist (a down server never pins a
negative verdict); stale entries pruned on write; corrupted cache
degrades to a miss; atomic writes. 300s is strictly fresher than the
1h in-process TTL that already accepts server-swap staleness.
- models.dev fetch timeout 15 -> (5, 10) connect/read tuple: a
blackholed connect stalled the first-turn critical path 15s; now
fails in 5s (matches the OpenRouter fetch convention, #46620).
- _auto_detect_local_model timeout 5 -> (2, 3): runs inside
_get_model_config() at startup against a LOCAL endpoint; a hung local
server cost 5s before the banner.
E2E (real HTTP server, two fresh subprocesses, isolated HERMES_HOME):
proc1 = 2 HTTP hits, proc2 = 0 HTTP hits, identical results
(ollama/131072), probe wall 74.5 -> 35.5 ms. 222 targeted tests green
incl. 9 new disk-L2 contract tests.
