Normalize incoming reasoning at the shared heading boundary and completed
extraction, and flatten auxiliary content and reasoning before accumulation.
Reuse the existing text flattener with no implicit fragment separators.
Combine the earliest related work from zsuroy (#85791), the diagnosis and
patch from 2025hcsmile2010-hue (#104711, #104848), and completed extraction
work from liuhao1024 (#104717) as a slim redo, not a verbatim cherry-pick.
Two invariant tests exercise the real SDK and local HTTP fixture across
main streaming, Relay collection, auxiliary sync/async and completed output.
The standalone matrix improves from 32/84 to 84/84, preserving answers.
Co-authored-by: suroy <suroy@qq.com>
Co-authored-by: 2025hcsmile2010-hue <2025hcsmile2010@gmail.com>
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
fallback_providers entries using the "google" alias for the gemini
profile were falling through to the generic OpenAI-SDK client because
the native-client gate only matched the literal string "gemini". That
client posts straight to the raw REST endpoint, sending thinking_config
as an unnested top-level field, which Gemini rejects with:
Invalid JSON payload received. Unknown name "thinking_config": Cannot find field.
Broaden the check to the same alias set the gemini profile itself
registers (mirrors _GEMINI_NATIVE_PROVIDER_NAMES already used for this
in auxiliary_client.py).
Fixes#104583
The Sep 2026 decomposition (PR #102117) makes internal import paths a non-API: names now live in
the focused modules that define them. This commit is the ONLY thing keeping the old paths alive,
so external plugins have time to update. It is deliberately a single, unsquashed commit:
git revert <this sha>
removes every shim, stub and manifest at once on the announced date. Nothing in-tree may depend on
these pointers: scripts/check_compat_pointers.py (wired into lint.yml) fails CI if it does.
What it adds (see COMPAT_MANIFEST.md, compat_manifest.json):
- 332 facade modules get one delimited `PLUGIN-COMPAT` block appended at the end of the file
- 1,172 moved names resolved lazily via a module `__getattr__` (PEP 562) — never a top-level import,
so no import cycles; facades that already had `__getattr__` get a chained one
- 592 third-party/stdlib names the old modules used to expose, with their original import statements
- 266 public definitions that had been deleted as unused, restored byte-for-byte from the pre-decomposition
tree (+40 private helpers and 16 imports pulled in only because a restored definition needs them)
- 3 deleted modules recreated as re-export stubs (gateway/startup_watchdog, hermes_cli/observability/
relay_runtime, tools/environments/modal_utils)
- private names (`_x`) get no pointer: they were never API (3,792 skipped)
Verified: all 335 touched modules import under a fresh HERMES_HOME and every manifest name resolves;
the lint reports zero in-tree uses; ruff clean; targeted suites unchanged.
No runtime consumer read the proxy (terminal_tool/environments call is_interrupted()/set_interrupt()
directly); its only users were tests patching tools.interrupt._interrupt_event, which had no effect on
the code under test. tools/terminal_tool.py's own re-export of the name is owned by another worker.
run_agent.py: delete the `# noqa: F401` re-export block (agent.process_bootstrap
OpenAI/_SafeWriter/_get_proxy_*, model_tools get_tool_definitions/
handle_function_call/check_toolset_requirements, FailoverReason,
_qwen_portal_headers/_routermint_headers, session_persistence names,
estimate_request_tokens_rough, ContextCompressor + friends, jittered_backoff,
prompt_builder names, message_sanitization names, tool_dispatch_helpers
names) — 41 names run_agent never used itself — and the `_STREAM_DIAG_HEADERS`
back-compat class alias (no in-tree reader). run_agent now imports only what
it uses (get_toolset_for_tool, is_local_endpoint, coalesce/uniquify tool-call
ids, cleanup_vm/get_active_env from terminal_tool_lifecycle).
agent/*: `_ra().X` late-binds that only reached a re-export now import the
defining module directly (agent_runtime_helpers -> process_bootstrap.OpenAI,
model_tools.handle_function_call, session_persistence._safe_session_filename_component;
agent_init -> model_tools.get_tool_definitions/check_toolset_requirements,
_lazy_headers("agent.client_lifecycle", ...) for qwen/routermint;
system_prompt -> agent.prompt_builder / model_tools directly, dropping its
own _ra() shim and the `_r` parameter threading). `_ra()` stays for
run_agent-resident names (logger, AIAgent, _hermes_home, _set_interrupt, ...).
toolsets.py: remove resolve_multiple_toolsets (shim-only, restored by
34abf954bd); tests/test_toolsets.py pins the same union behavior via
resolve_toolset over each name.
providers/__init__.py: drop the OMIT_TEMPERATURE re-export (no callers via the
package); ProviderProfile stays because __init__ uses it for annotations —
2 tests repointed to providers.base.
agent/iteration_budget.py: drop the "run_agent re-exports the class"
docstring pointer; 4 tests import IterationBudget from its home.
model_tools.py (arg_coercion names), agent/tool_executor.py, and
hermes_cli/cli_session_mixin.py repoints landed via a sibling commit on this
shared worktree.
Callers repointed: gateway/run.py, hermes_cli/cli_chat_turn_mixin.py,
hermes_cli/cli_tui_mixin.py, tui_gateway/session_workdir.py,
agent/transports/codex.py (one-line imports) + comment pointers in
tools/file_state.py, tools/schema_sanitizer.py, scripts/tool_search_livetest.py.
Tests: patch("run_agent.X") / monkeypatch.setattr(run_agent, "X") /
`from run_agent import X` -> defining module across 99 test files.
Adolanium review §3 (Medium/Low). BASE shape at every steer/redirect/persist/agent-cache
lock site was: lock = getattr(obj, "_x_lock", None); if lock is not None: with lock: <direct
attribute read>; else: <getattr fallback for object.__new__ test stubs>. The refactor rewrote
several of these as 'with getattr(...) or nullcontext(): getattr(slot, None)', which (a) turned a
missing slot under the lock from a loud AttributeError into silent None and (b) in the gateway
peek helper read the cache without any lock when the lock attribute was absent.
Restored BASE semantics at:
- agent/agent_runtime_helpers.py::_requeue_pending_steer
- agent/interrupt_control.py: steer, redirect, clear_interrupt, _has_pending_redirect,
_drain_pending_redirect, _drain_pending_steer (new _ic_slot helper: direct read under lock)
- agent/session_persistence.py::_persist_lock (explicit None check + BASE rationale)
- gateway/slash_commands.py::_cached_agent_for (BASE callers read ONLY under the lock; no lock -> None)
- gateway/run_agent_cache.py::_evict_cached_agent (BASE: self._agent_cache direct under lock)
- agent/client_lifecycle.py::_is_openai_client_closed: BASE body + docstring verbatim (outer
is_closed first; inner _client.is_closed only when _client exists; else False)
- agent/stream_delivery.py::_ensure_stream_writer_state: restore BASE rationale that the lock is
created unconditionally in agent_init (_STREAM_STATE) and the lazy path is stub-only
A/B (/tmp/rf/rev/ab_lock_fallbacks.py, ab_client_closed.py) is byte-identical BASE vs HEAD on
the reviewer's inputs + edge cases. tests/agent/test_lock_fallback_base_semantics.py pins it
(7 of 25 cases fail on the pre-fix tree).
For each issue anchor present in BASE 63279301bc non-test .py and absent on HEAD, the BASE comment/docstring block was re-attached at the HEAD location of the code it explained (matched by the distinctive code line / enclosing def). Sentences already covered by an existing HEAD comment were deduped; the issue number always survives. Insert-only: no code lines changed.
GLM-style models serialize tool calls as XML in the text channel; when the
stream drops mid-serialization with finish_reason=stop, the orphan
<arg_key>/<arg_value> fragment (or a bare unclosed <tool_call> opener)
matched neither the complete-block stripper nor the partial-stream guard
and was stored and displayed as ordinary assistant content.
strip_think_blocks (storage boundary) and the CLI display copy now strip
an unterminated block-boundary tool-call opener, or any line carrying
stray argument markup, to end of text. The response then reads as empty
and flows through the existing empty-retry path. Complete blocks and
inline prose mentions are unchanged.
A fan-out of 30 delegated children built 183 httpx.HTTPTransport objects
(each with its own httpcore pool + parsed SSL context): 3 per agent x
(primary + aux clients). A profiled session with ~130 children held 107 TLS
sockets to one provider. Peak RSS for the 30-child bench drops 286 -> 195 MB;
live HTTPTransports 183 -> 2, ConnectionPools 183 -> 7.
What is shared: the sync `HTTPTransport` (pool + SSL context) per
(scheme, verify, proxy, happy-eyeballs) identity, in a bounded module dict.
What is NOT shared: the per-agent `httpx.Client` wrapper. Each client mounts
a `_SharedTransport` view whose `close()` marks only that view closed and
never touches the pool, so the #10933 contract (close client A, build client
B, B works) holds unchanged — the pinning tests in
test_create_openai_client_reuse.py / test_sequential_chats_live.py pass as-is.
Safety for cross-thread aborts: `_SharedTransport.handle_request` stamps its
id into `request.extensions`; `_iter_pool_sockets` now only shuts down a
shared pool's in-flight requests carrying the calling client's stamp and
never its idle connections, so interrupting child A cannot sever child B's
stream (#29507 / #72975 walker semantics preserved for unshared pools).
Also:
- `resolve_httpx_verify` caches one SSLContext per CA-bundle path. With
SSL_CERT_FILE/HERMES_CA_BUNDLE set, every agent used to parse the bundle
again and — because the share key is context identity — get a private pool.
- The client no longer builds a third, unused default transport; its
default transport is the https view.
- Mounted transports now actually receive pool limits (Client-level
`limits=` never reached them, so mounts ran on httpx defaults with a 5 s
keepalive_expiry). The shared pool uses 50 keepalive / 1000 max so one
pool covers a whole concurrent fan-out.
- `close_shared_transports()` really closes the pools (tests / shutdown).
Async clients (`async_mode=True`) stay unshared: an httpcore async pool is
bound to the event loop that first uses it. Proxy-backed clients keep
httpx's per-client proxy transport.
``create_openai_client`` was a hardcoded if-ladder: copilot-acp builds an ACP
stdio shim, gemini builds a native client, everything else gets an
``openai.OpenAI``. There was no extension point, so a provider whose wire
protocol is not OpenAI-over-HTTP could only be added by editing this function —
which is exactly why an ACP provider cannot ship outside this tree today, even
though ``providers/__init__.py`` has discovered out-of-tree profiles from
``~/.hermes/plugins/model-providers/`` and pip entry points for a while.
``ProviderProfile.create_client(**client_kwargs)`` closes that gap. It returns
``None`` by default, so every provider that wants the standard client is
unaffected and the existing ladder still runs as the fallback. copilot-acp is
migrated onto it — its hardcoded branch is gone and its profile supplies the
client in three lines, which is the same three lines an external package writes.
Resolution goes by provider name first, then by ``base_url`` prefix, so a
runtime configured only by URL still reaches its profile — matching what the
replaced ``startswith("acp://copilot")`` branch did. A profile that raises is
logged and skipped: a third-party plugin can fail to provide a client, but it
cannot take the turn down.
Also replaces the two ``isinstance`` checks in ``agent/auxiliary_client.py``
that mean "this client is complete, do not wrap it" with capability flags the
client class declares — ``HERMES_SKIP_TRANSPORT_WRAP`` and
``HERMES_SKIP_ASYNC_WRAP``, mirroring ``SUPPORTS_HERMES_TOOL_CALLS`` in
``background_review.py``. Two in-tree consumers (the ACP shim and the Gemini
native client), an out-of-tree client is covered by the same declaration, and
the hot path no longer imports those modules just to type-test.
Co-Authored-By: Junie <junie@jetbrains.com>
Review follow-ups:
- Strip the tool_call id when populating the call-name map so it matches the
stripped lookup (and pass 1's result_call_ids). A padded id previously
skipped realignment silently.
- Log which names were rewritten, not just how many.
- Note in the comment that a result whose assistant call frame was pruned is
already dropped by the orphan pass, so it cannot reach the provider with a
stale name; cover that with a test.
- Rename test_sanitize_leaves_matching_and_unpaired_tool_result_names_alone,
which only ever exercised the matching case, and add the padded-id case.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Google matches functionResponse.name against functionCall.name and rejects
a mismatch with HTTP 400 INVALID_ARGUMENT. #72089 fixed this for the native
Gemini adapter, where _translate_tool_result_to_gemini() now prefers
tool_name_by_call_id over the result message's internal name.
Requests that reach Gemini through an OpenAI-compatible gateway (OpenRouter,
Vertex/LiteLLM proxies) never run that translation, so they still put the
unwrapped internal tool name on the wire: the model calls the tool_search
bridge tool `tool_call`, make_tool_result_message() labels the result
`mcp__strava__get_recent_activities`, and the next turn 400s with a bare
"Provider returned error". The bad pair stays in the transcript, so every
later request in that session fails too.
Hold the same invariant at the final pre-API chokepoint instead of in the
OpenAI-compat serializer: Gemini arrives under many model strings and base
URLs, so sniffing for "is this really Google?" is unreliable, while every
other provider either ignores the field or already agrees with the call
name. Only a name that is present and disagrees is rewritten, so clean
transcripts still pass through byte-identical for prompt caching, and the
rewrite lands on the per-call copy so the stored trajectory keeps the real
tool name for the session DB and UI. No-op for the native Gemini path.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Builds the escalation layer on top of HexLab98's heal-log windowing
(salvaged from PR #96916):
- Per-session heal counters (heal events + messages healed) tracked by the
repair path in agent_runtime_helpers.py, session totals preserved across
10-minute log windows.
- Threshold escalation: after N heals in a session window (default 3,
configurable via agent.sanitizer_heal_escalation_threshold in
config.yaml, 0 = off) log ONE ERROR carrying session id + heal pattern
(events/messages/window/threshold), then stay quiet.
- ONE-TIME out-of-band user notice queued at the threshold and delivered by
the conversation loop through _emit_warning (status callback -> gateway
status message / CLI print). Never injected into conversation context or
the wire copy: prompt caching, role alternation, and durable history are
untouched. Never re-arms on a new window; scoped per session.
- Counters visible in diagnostics: get_sanitizer_heal_stats() rendered in
the /debug share // hermes debug report, and the config key surfaced in
hermes dump overrides. errors.log carries the ERROR line for `hermes logs
errors`.
Fill empty non-final user/assistant turns on the wire copy during send-time projection so the sanitizer does not re-heal the same poisoned row every call. When a caller still hits the owner, log WARNING then one ERROR per session window instead of flooding errors.log.
Keep model-switch callers compatible with result objects created before runtime_capabilities was added, and do not roll back minimal agents that lack optional LM Studio helpers. Preserve rollback for real helper failures.
Use a distinct runtime_capabilities field on agents, preserve compatibility with earlier snapshots, and resolve the canonical direct OpenAI endpoint when a cross-provider switch omits base_url. Keep ambiguous proxy routes fail-closed.
Stage destination native-compaction capabilities until the complete runtime and context setup succeeds, and restore them with primary and fallback runtimes. Keep native compaction default-deny across live switches and session reconstruction.\n\nVerification: uv run --with pytest --with pyyaml python -m pytest tests/run_agent/test_switch_model_context.py tests/run_agent/test_native_compaction.py tests/run_agent/test_native_compaction_switch_capabilities.py tests/run_agent/test_switch_model_rollback.py tests/run_agent/test_fallback_reasoning_override.py tests/run_agent/test_primary_runtime_restore.py tests/run_agent/test_provider_fallback.py -q -o 'addopts='; uv run --with ruff ruff check <touched files>; git diff --check
Follow-up hardening on the two cherry-picked contributor commits:
- try_activate_fallback: replace the blanket request_overrides.pop('extra_body')
with KEY-SCOPED removal — only keys the OLD provider's custom_providers
entry contributed (value unchanged since the init-time merge) are dropped.
Caller/profile-provided extra_body keys survive the swap, matching the
caller-over-provider precedence in agent_init._merge_custom_provider_extra_body.
The fallback provider's own extra_body is then merged back in.
- switch_model: the live _primary_runtime snapshot it rebuilds now carries
request_overrides, so a post-switch transport recovery or fallback restore
reinstates the switched-to identity's overrides instead of dropping them.
- Tests: activation-level stale-key removal + caller-override preservation
(test_provider_fallback.py), switch-then-recover / switch-then-restore
(test_primary_runtime_restore.py).
Cache-safety: none of these paths mutate past context or rebuild the system
prompt — only outbound request kwargs change.
Fixes#75091
Teknium