Direct tool HTTP calls already identified as Hermes-Agent, but the main
OpenAI-SDK chat path still sent OpenAI/Python. Set Hermes-Agent/<ver> for
api.x.ai clients (xai + xai-oauth) so normal text traffic is attributed correctly.
Every fallback/dedup/skip decision asks one question — 'is this candidate
the same backend as the one that failed, along the axis that failure
invalidated?' — but it was re-implemented inline at six sites across four
subsystems, each comparing whatever string was locally convenient. Each
incident fixed one site while the others kept the bug: #22548, #70893,
#59561, #72468, #62984/#54250/#57584.
agent/backend_identity.py now owns the concept: BackendIdentity (provider /
model / base_url axes), FailureScope (MODEL / CREDENTIAL / ENDPOINT — each
failure class invalidates a different axis), and should_skip_candidate().
Unknown axes never manufacture a skip (over-skipping strands failover; a
wrong try costs one RTT).
Migrated sites:
- chat_completion_helpers.try_activate_fallback: replaces the provider+model
early-exit (the #62984 bug: ignored base_url, stranding multi-endpoint
pools) AND _fallback_entry_is_same_backend_by_base_url (deleted)
- auxiliary_client._try_configured_fallback_chain +
_try_main_agent_model_fallback: replace label/model comparisons; auth and
payment map to CREDENTIAL scope, keeping the #59561 carve-out
- hermes_cli/fallback_cmd add: primary-match + duplicate checks now identity-
aware (#54250/#57584): same provider+model on a different explicit
base_url is a pool entry, not a duplicate
_mark_provider_unhealthy stays label-keyed deliberately: its only triggers
are confirmed 402s, which ARE credential-scoped.
Owner-level tests pin each incident's semantics by number; sabotage-verified
(removing the base_url axis fails the #62984 test).
Widen okalentiev's failed_model narrowing (#59561) to
_try_main_agent_model_fallback. The safety-net layer still skipped on a
provider-label match alone, so single-provider users whose aux compression
model and main model share one custom endpoint had ZERO fallbacks: the aux
model timing out exhausted the chain in one hop and compression aborted.
Real incident (0.19.0 debug dump): aux zai-org/glm-5.2 hung 324s and timed
out while main mindai/macaron-v1-venti on the SAME endpoint was serving
448K-token turns — the label-only skip discarded the one viable summarizer,
the session wedged over threshold, and the anti-thrash breaker tripped.
Same convention as the chain fix: model-specific failures (timeout,
connection, rate limit) pass failed_model so only the exact failed model is
skipped; provider-wide failures (auth 401 / payment 402) pass None and keep
the whole-provider skip. Both sync and async call_llm sites pass it.
Sabotage-verified: the new regression test fails on the provider-only skip.
Follow-up to the same-provider fallback fix: narrowing the configured-chain
skip to the exact failed model is only correct for model-specific failures.
Auth (401) and payment (402) errors are provider-wide — every model on the
provider shares the same broken credentials/account — so trying a sibling
model can't recover and merely burns another doomed request before the
aux task fails. Worse, returning that sibling client bypasses the
main-agent-model safety net that a provider-wide skip would have reached.
Only forward failed_model to _try_configured_fallback_chain for
model-specific failures (timeout, connection, rate limit, model-incompatible,
invalid response). Auth/payment keep failed_model=None (whole-provider skip),
preserving the pre-existing safety-net behaviour for credential/billing
failures.
Adds an integration test that a timeout forwards the failed model, and
updates the payment-error test to assert failed_model=None.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
_try_configured_fallback_chain skipped every fallback_chain entry whose
provider matched the one that just failed. A chain that intentionally lists
several models under the same provider (e.g. two more NVIDIA NIM models
after the primary NIM model times out) was therefore skipped wholesale,
falling straight through to the main-agent-model safety net instead of
trying the other configured models on that provider.
Add failed_model so the skip narrows to the exact (provider, model) pair
that failed. Callers that only know the provider (client-build failures,
where the whole provider is unreachable regardless of model) keep the old
provider-wide skip; the two runtime request-error call sites (call_llm,
async_call_llm) now pass the model that just failed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Some OpenAI-compatible endpoints — notably Tencent Copilot
(copilot.tencent.com) — only accept streaming chat requests; any
non-streaming call returns HTTP 400 (code 11101, 'Non-stream chat
request is currently not supported'). The main conversation loop already
streams, so interactive chat works, but every auxiliary task (title
generation, compression, web extraction) used the non-streaming path and
failed on each call.
_provider_requires_stream() detects stream-only endpoints
(copilot.tencent.com built in, plus user-configurable
auxiliary.stream_only_base_urls substring markers in config.yaml).
Matching sync auxiliary calls route through _create_with_progress
(force_stream=True) and async calls through the new
_acreate_with_stream, aggregating the chunk stream — including tool-call
deltas and reasoning deltas — into a complete response via the shared
_ChatStreamAccumulator.
Salvaged from PR #60686 by @kudi88 onto the progress-aware streaming
machinery from #71508, addressing both sweeper-review gaps: the async
path now consumes the stream with 'async for' (awaiting create() and
iterating synchronously raised on AsyncOpenAI streams), and tool-call
deltas are reassembled instead of dropped (MCP passes tools= through
call_llm). Under force_stream there is no silent non-streaming retry —
a stream-only provider rejects those by definition, so the original
error surfaces to the normal recovery chains.
The gateway's pre-agent session-hygiene compression killed the summary
call at a fixed 30s wall-clock deadline (compression.hygiene_timeout_seconds),
regardless of whether the summary model was hung or merely slow. A reasoning
model happily streaming a large summary was cut off mid-generation, the user
got '⚠️ Context compression timed out after 30.0s', and a 300s failure
cooldown left the session oversized — a doom loop for slow-but-healthy
auxiliary models.
Timeouts are now liveness-based instead of wall-clock-based:
- agent/auxiliary_client.py: new thread-local aux_progress_hook. When
installed (only by context compression today), the primary call_llm
attempt streams (stream=True) and aggregates chunks back into a complete
response, ticking the hook per chunk. The configured timeout then acts
per stream read (idle) instead of as a total budget. Providers that
reject streaming fall back to the plain non-streaming call; auth/payment/
rate-limit/transport errors propagate unchanged into the existing
recovery chains. Codex Responses (per SSE event) and Anthropic Messages
(per stream event, via the new create_anthropic_message on_stream_event
callback) tick the same hook from inside their wire adapters.
- agent/conversation_compression.py: CompressionCommitFence gains
touch_progress()/seconds_since_progress(); compress_context() installs
fence.touch_progress as the progress hook around the compress call.
- gateway/run.py: the hygiene wait loop treats hygiene_timeout_seconds as
an INACTIVITY budget — while the fence reports fresh progress the wait
extends, bounded by the new compression.hygiene_total_ceiling_seconds
(default 600s, clamped >= the idle budget) so a degenerate trickle
stream still dies. The timeout warning now says the summary model
produced no output, which is the only case that still triggers it.
- config/docs: hygiene_total_ceiling_seconds added to DEFAULT_CONFIG and
configuration.md; hygiene_timeout_seconds documented as inactivity-based.
Tests: tests/agent/test_aux_progress_streaming.py (hook plumbing, stream
aggregation incl. tool-call deltas and reasoning deltas, rejection
fallback, ceiling kill, fence progress surface); two new gateway tests
prove a slow-but-streaming worker survives past the fixed timeout
(sabotage-verified: fails with the old fixed deadline) and a
forever-trickling worker is still cut off at the ceiling.
Path.read_text() without an explicit encoding uses the platform's
default encoding. On Windows this is typically cp1252 or mbcs, which
causes UnicodeDecodeError or silent data corruption when reading
UTF-8 content (JSON files, user text, config with non-ASCII chars).
This is the read-side companion to the write_text() encoding fix.
Fixed the most critical locations that read JSON data, user content,
and config files across 14 files with 31 call sites.
Pattern: .read_text() → .read_text(encoding='utf-8')
json.loads(path.read_text()) → json.loads(path.read_text(encoding='utf-8'))
OpenAI documents GPT-5.5 / GPT-5.5 Pro as extended-cache-only: in-memory
prompt cache retention is not available for them, and only
prompt_cache_retention: "24h" is supported. Responses requests that omit
the field see near-zero cached_tokens even with a stable prompt_cache_key
and identical prefixes (observed on an OpenAI-compatible Responses relay:
0 cached across repeated identical calls before; 97% cache reads after).
Send the field for the gpt-5.5 model family (bare and namespaced ids like
openai.gpt-5.5) on OpenAI-compatible Responses routes, mirrored in the
auxiliary Codex adapter, and pass it through preflight normalization.
Skipped for xAI, GitHub/Copilot, and the chatgpt.com Codex backend, which
reject or ignore body-level cache fields.
The Vertex AI provider (added same-day, commit c73e74386) was never added to
either of the two provider registries that agent/auxiliary_client.py and the
MoA slot-resolution chain depend on, breaking Vertex outside the main
conversation loop:
1. hermes_cli/auth.py::PROVIDER_REGISTRY had no "vertex" entry. The
plugin-auto-extend loop that normally fills gaps explicitly skips
non-api_key auth types (`if _pp.auth_type != "api_key": continue`), and
Vertex was never hand-declared like "bedrock" is. Because
resolve_provider_client() in agent/auxiliary_client.py gates everything
on `pconfig = PROVIDER_REGISTRY.get(provider)` and returns (None, None)
immediately when pconfig is None, its `elif pconfig.auth_type == "vertex"`
branch was permanently dead code — every auxiliary Vertex call (vision,
title generation, reflection, context compression, MoA reference/
aggregator slots) failed outright, not just a MoA-specific edge case.
2. hermes_cli/providers.py::HERMES_OVERLAYS also had no "vertex" entry, so
hermes_cli.providers.get_provider("vertex") returned None. This backs
_preserve_provider_with_base_url() in agent/auxiliary_client.py, which a
MoA slot's resolved (base_url, api_key) pair needs to keep its "vertex"
identity instead of silently collapsing to "custom" — losing the
identity _refresh_provider_credentials() needs to re-mint an expired
OAuth2 token (~1h lifetime) on a 401, and permanently breaking every
subsequent call in that MoA preset for the rest of the session.
Fix mirrors the existing "bedrock"/aws_sdk entries in both registries
exactly, plus adds a "vertex" branch to _refresh_provider_credentials() (it
had branches for openai-codex/nous/anthropic/xai-oauth but not vertex,
so a 401 fell through to `return False` without evicting the stale cached
client).
- hermes_cli/auth.py: hand-declared vertex ProviderConfig(auth_type="vertex")
in PROVIDER_REGISTRY, matching bedrock's shape.
- hermes_cli/providers.py: vertex HermesOverlay(auth_type="vertex") in
HERMES_OVERLAYS + "Google Vertex AI" label override.
- agent/auxiliary_client.py: vertex branch in _refresh_provider_credentials
that re-mints the token via get_vertex_config() and evicts the stale
cached client.
- 8 new regression tests across tests/hermes_cli/test_vertex_provider.py and
tests/agent/test_auxiliary_client.py: registry membership, end-to-end
resolve_provider_client("vertex", ...) building a working client (proving
the previously-dead branch is now reachable), and the 401-refresh/cache-
eviction path.
_build_call_kwargs omitted max_tokens for every provider except
anthropic-compat endpoints and NVIDIA NIM. Gemini's native
generateContent maps max_tokens -> maxOutputTokens and, when it is
omitted, applies a fixed 65,535-token ceiling (not "the model's full
budget"), so dropping the value made MoA's reference_max_tokens a
silent no-op for gemini advisors — they ran effectively uncapped
(observed ~2900 output tokens against a configured cap of 600),
inflating per-turn MoA latency.
Forward max_tokens for the gemini-native path (provider name or native
base_url). Gemini supports maxOutputTokens, so the cap is safe here;
providers that reject max_tokens (Copilot, GPT-5 max_completion_tokens,
ZAI vision) are unaffected — they still omit it as before.
Per review feedback from teknium1: reference_max_tokens is an advisors-only
contract. The aggregator is the acting model and must not be capped by the
reference budget. Changed _is_moa from startswith('moa_') to exact match on
'moa_reference'. Added regression test proving aggregator does NOT receive
max_tokens.
Copilot review pointed out that hardcoding kwargs['max_tokens'] would
400 on models requiring max_completion_tokens (GPT-5 family, Copilot).
The existing auxiliary_max_tokens_param() helper already selects the
correct parameter name per model — use it instead of hardcoding.
Test updated to parametrize expected_key so the Copilot gpt-5.5 case
correctly asserts max_completion_tokens instead of max_tokens.
Addresses Copilot review comments on both files.
PR #56756 added reference_max_tokens to cap MoA advisor output and cut
turn latency. The value is correctly threaded through five layers of MoA
code (moa_config → conversation_loop → aggregate_moa_context →
_run_references_parallel → _run_reference → call_llm(task='moa_reference',
max_tokens=800, ...)).
However, _build_call_kwargs() in auxiliary_client.py silently drops
max_tokens for all OpenAI-compatible providers (PR #34845, which fixed
endpoints and NVIDIA NIM keep it. This means reference_max_tokens never
reached the API for the vast majority of providers.
The bug affects every OpenAI-compatible MoA reference/aggregator slot:
Z.AI (coding plan), OpenRouter, OpenAI, GitHub Copilot, and local
providers. Only Anthropic-compat endpoints (MiniMax, /anthropic URLs)
worked — by coincidence, not MoA-aware design.
Fix: thread the 'task' parameter through all six _build_call_kwargs()
call sites. When task starts with 'moa_', max_tokens is always included
in the request kwargs regardless of provider. Non-MoA auxiliary tasks
(compression, titles, vision, etc.) keep PR #34845 behavior unchanged.
Verified end-to-end:
- Z.AI GLM-5.2 with max_tokens=50 → returned exactly 50 tokens
- Z.AI GLM-5.2 with max_tokens=20 → returned exactly 20 tokens
- Z.AI GLM-5.2 uncapped → returned 315 tokens
- 7 new regression tests covering 4 providers, Anthropic wire, non-MoA
tasks, and prefix-matching boundary
- 288 auxiliary_client tests pass (was 281, +7 new), 84 MoA tests pass
- Zero regressions
'auto' is a sentinel meaning "inherit from main runtime / auto-detect",
not a literal model id -- already handled for cfg_model (config-derived)
in _resolve_task_provider_model, but not for the explicit `model` kwarg.
MoA reference/aggregator slots (agent/moa_loop.py's _slot_runtime) forward
a preset's `model:` field as this explicit argument rather than through
auxiliary.<task> config, so a MoA preset configured with `model: auto`
(a natural thing to try given the existing auxiliary.*.model: auto
convention) reached this function as the explicit `model` arg and took
the `model or cfg_model` branch, bypassing the cfg_model-only sentinel
check entirely -- sending the literal string "auto" to the wire as a
model id.
Normalize both the explicit `model` and `cfg_model` the same way, fixing
this at the single chokepoint every caller (MoA included) already goes
through, rather than patching moa_loop.py separately.
Follow-up to srojk34's explicit-provider unwrap (PR #56691):
- Extract _resolve_moa_aggregator() as the single preset->aggregator
resolver shared by _resolve_auto(), _resolve_task_provider_model(),
and resolve_provider_client() so preset lookup/validation can't drift.
- When the main provider is moa, the aggregator model is now the default
for every UNSET auxiliary model: _read_main_model_for_aux() substitutes
the preset's acting (aggregator) model wherever fallback chains
pre-filled from _read_main_model() (router prefill, custom-endpoint
fallback, named-custom default, external-process default,
_try_main_agent_model_fallback).
- Unwrap moa at the resolve_provider_client() chokepoint so direct
callers (vision auto-detect, plugin code) can't dead-end in the
unknown-provider branch, and unwrap the vision auto-detect main
provider before capability probes run against the preset name.
- Real-config tests: temp HERMES_HOME + actual config.yaml exercising
the genuine load_config()/resolve_moa_preset() boundary.
_resolve_task_provider_model() returned an explicit provider="moa" override
(from a caller-passed arg, or auxiliary.<task>.provider: moa in config.yaml)
verbatim, with no MoA-preset unwrap. Only the *implicit* "main provider is
moa" path inside _resolve_auto() unwraps to the aggregator slot (#53827) —
this function never goes through _resolve_auto() at all, so the explicit
case was never covered.
MoA is a virtual provider with no real HTTP endpoint: resolve_provider_client()
looks "moa" up in PROVIDER_REGISTRY (no such entry), falls to the
unknown-provider dead end, and call_llm surfaces a nonsensical "Provider
'moa' is set in config.yaml but no API key was found. Set the MOA_API_KEY
environment variable..." error for a provider that was never meant to be
reached over the wire.
Fix mirrors #53827's aggregator-resolution approach exactly: when either the
explicit `provider` arg or the config-derived `cfg_provider` is "moa",
resolve the named (or default) MoA preset via resolve_moa_preset() and
continue with its aggregator's real provider+model, dropping any explicit
base_url/api_key (the moa:// virtual endpoint and placeholder key belong to
the facade, not the aggregator's real provider). If the preset can't be
resolved (renamed/deleted), degrades gracefully to the pre-fix behavior
instead of raising harder.
- agent/auxiliary_client.py: _unwrap_moa_provider() helper + call sites for
both the explicit-arg and config-derived provider="moa" cases in
_resolve_task_provider_model(). Also tightened base_url/api_key parameter
types to Optional[str] (matching their actual None-accepting behavior),
which incidentally resolved 5 pre-existing ty diagnostics at call sites.
- 5 new regression tests in tests/agent/test_auxiliary_client.py: explicit
arg unwrap, config-derived unwrap, default-preset fallback when no model
is configured, graceful degradation on preset-resolution failure, and a
non-moa regression guard.
_resolve_task_provider_model() read api_key from the auxiliary task
config but never consulted key_env (or api_key_env). When a user
configured an auxiliary task with key_env instead of a plaintext
api_key, the resolved API key was None, causing 401 on every call.
Add the same key_env → os.getenv() resolution pattern already used in
_fallback_entry_api_key() and named custom provider resolution.
Closes#66641
Review follow-ups on the cherry-picked #36043 commit:
1. Guard the custom:<name> passthrough with a _get_named_custom_provider
lookup. The PR unconditionally kept the full custom:<name> string, which
broke config-less runtime custom providers (#34777 regression — entries
that exist only in the live runtime, not config.yaml): the named arm
found no entry and resolution fell through to Step 2. Now custom:<name>
only takes the named arm when a config entry actually exists; otherwise
it collapses to the anonymous-custom arm with the runtime endpoint,
preserving pre-PR behavior.
2. Drop the dead 'explicit_api_key = runtime_api_key' assignment (and its
misleading comment) in the named-entry branch. resolve_provider_client's
named-custom arm derives the key exclusively from the entry's
api_key/key_env and never reads explicit_api_key, so the assignment was
a no-op. Wiring precedence in was not justified: for a named custom
provider the runtime key IS the entry's key (set_runtime_main sources it
from the same config), so deletion is the honest option.
3. Tighten the Palantir Bearer-auth check from a loose substring match
('palantirfoundry' in normalized) to a hostname match via
base_url_host_matches(..., 'palantirfoundry.com'), so path segments or
lookalike domains containing the string no longer trigger Bearer auth.
Tests: named-custom anthropic_messages end-to-end routing (full name kept,
AnthropicAuxiliaryClient at the original /anthropic URL, no /v1 rewrite)
plus Palantir Bearer-auth positive and substring-false-positive cases.
When the user's main provider is a named custom_providers entry exposing an
Anthropic Messages surface (e.g. Palantir Foundry's
/api/v2/llm/proxy/anthropic, custom LiteLLM/Bedrock proxies), auxiliary
tasks (title generation, compression, web extract, session search, etc.)
returned HTTP 404 NOT_FOUND for every call.
Root cause: `_resolve_auto` collapsed any `custom:<name>` main provider
to plain `"custom"` and passed runtime_base_url as explicit_base_url.
This landed in `resolve_provider_client`'s anonymous-custom arm
(`if provider == "custom":`), which unconditionally calls
`_to_openai_base_url` — that helper strips a trailing `/anthropic` and
substitutes `/v1` (designed for MiniMax/ZAI which expose both surfaces).
The result for Palantir is `/api/v2/llm/proxy/v1`, which does not exist
on the proxy — every auxiliary call 404s. The runtime `api_mode=
anthropic_messages` flag was discarded by this arm.
Fix: split the conditional so only the literal `"custom"` provider takes
the anonymous-custom path; `custom:<name>` keeps its full `custom:<name>`
string when handed to `resolve_provider_client`, where the
named-custom-provider arm (added in earlier work) honours the entry's
`api_mode` and routes through `AnthropicAuxiliaryClient` against the
original `/anthropic` URL.
Also: extend `_requires_bearer_auth` in `anthropic_adapter.py` to
recognise palantirfoundry hosts so the SDK sends `Authorization: Bearer`
instead of the default `x-api-key` (Palantir's proxy rejects x-api-key
with 401).
Verified end-to-end against a live Palantir Foundry deployment with both
claude-4-6-opus and claude-4-7-opus models — `generate_title` returns
real titles instead of 404ing. Regression-tested:
- anonymous `custom` (with base_url) still routes to OpenAI wire
- built-in NVIDIA provider unchanged
- custom-without-base_url still falls through to Step-2 chain
* feat(analytics): record auxiliary model usage per task in session accounting
Auxiliary LLM calls (vision, compression, title_generation, web_extract,
session_search, ...) discarded their token usage, leaving dashboard
analytics blind to aux model spend (issue #23270).
- hermes_state.py: session_model_usage gains a task PK dimension
(''=main loop) via v22 table-rebuild migration (SQLite can't alter a
PK); record_auxiliary_usage() writes per-(model,provider,task) deltas
WITHOUT touching sessions counters (gateway overwrites those with
absolute main-loop totals — folding aux in would double-count or be
clobbered). Aux rows never inherit the session's main-loop route.
- agent/aux_accounting.py: ContextVar ambient accounting context
(mirrors the portal_tags conversation context); record_aux_usage()
normalizes usage via usage_pricing.normalize_usage, estimates cost,
and is strictly best-effort. moa_reference/moa_aggregator excluded —
conversation_loop already folds MoA usage+cost into the main delta.
- agent/auxiliary_client.py: _validate_llm_response is the recording
chokepoint — every successful non-streaming aux response passes
through it exactly once, sync and async, including fallback paths
(model read from the response itself stays accurate across
fallbacks).
- run_agent.py: run_conversation publishes/resets the accounting
context; agent/title_generator.py republishes on its bare thread.
- hermes_cli/web_server.py: /api/analytics/usage folds aux rows into
by_model (aux-only models finally appear) and adds a by_task
summary; /api/analytics/models surfaces aux rows on the Models page.
Design per review of PR #62850 by @eeksock (thread-local + separate
auxiliary_usage table): rebuilt on ContextVar (async-safe — thread-local
cross-attributes concurrent coroutines on one event loop) and the
existing session_model_usage table instead of a parallel accounting
path, extended beyond vision to every aux task, and wired the analytics
endpoints so the dashboard actually shows it. Credit to @eeksock for
the approach and @tboatman for the detailed root-cause analysis.
* test(moa): match _validate_llm_response mock to new accounting-hint signature
* test(aux): accept accounting-hint kwargs in remaining _validate_llm_response mocks
Fixes#62452. Two amplifiers turned one slow auxiliary route into a
per-turn multi-minute stall:
1. Fallback candidates inherited the exact effective_timeout the primary
was called with. When the primary's deadline was short (tuned or
already burned), an independently healthy fallback died on the same
clock — the reporter's 163k-token compression needed ~90s on the
fallback and got the primary's 30s, every turn. fallback_chain
entries may now declare their own 'timeout' (seconds); both fallback
candidate call sites (sync + async) resolve it via
_fallback_entry_timeout, label-scoped so only configured-chain
candidates are affected. No entry timeout → task-level timeout,
preserving existing behavior.
2. A session whose transcript structurally cannot be summarized within
the deadline re-attempted every 60s, re-burning the full timeout on
every subsequent turn. Consecutive timeout-class failures now
escalate the cooldown 60s → 300s → 900s (capped); any successful
summary or session reset clears the streak. Timeout classification
takes precedence over the streaming-closed 30s rung ('timed out'
also matches _is_connection_error) and now recognizes the SDK's
'Request timed out.' phrasing.
Fail-safe behavior is unchanged: all messages are preserved when every
candidate fails; the cooldown only spaces out retries.
Follow-up on the salvaged fallback: silent degradation is how #64333 went
unnoticed (jobs dead on arrival, only errors.log knew). Warn once with a
resync hint, and cover both the skewed and healthy paths with tests.
Two related bugs in _AnthropicCompletionsAdapter.create() in
agent/auxiliary_client.py silently discard caller-supplied
reasoning_config and extra_body on the Anthropic-Messages
auxiliary-protocol path:
* Bug A: reasoning_config=None was hardcoded at L1000, so the
reasoning_config parameter on build_anthropic_kwargs was
unreachable for any auxiliary task. The main agent path
(agent/transports/anthropic.py) already reads
reasoning_config from caller params; this PR aligns the
auxiliary adapter with the same pattern.
* Bug B: create(**kwargs) accepts an OpenAI-style kwargs
payload from the caller but only forwards a hand-picked
subset to self._client.messages.create(). Any caller-supplied
extra_body (e.g. thinking control, metadata, service_tier,
vendor-specific fields) was dropped on the floor. The
codex/responses transport in the same file already merges
extra_body; the Anthropic branch is the gap.
This unlocks the caller-supplied extra_body path so auxiliary
callers can set per-vendor request fields (including
thinking: {type: "disabled"} for Anthropic-compatible vendors
that require an explicit disable on the wire), and lets the
reasoning_config kwarg flow into build_anthropic_kwargs like the
main agent does. Both changes are backward-compatible for
callers that don't pass the affected kwargs.
Affected providers (all routed through _AnthropicCompletionsAdapter
via _maybe_wrap_anthropic): anthropic (native), minimax /
minimax-cn, kimi-coding / kimi-coding-cn, z.ai / GLM, and any
custom /anthropic-suffixed endpoint. See PR description for
related issues (#35566, #7209, #16533, #32813, #29248).
The just-merged auxiliary.<task>.reasoning_effort shorthand applied
ensemble-wide to MoA (one value for every advisor) — wrong granularity.
Per-slot preset config supersedes it:
moa:
presets:
deep_review:
reference_models:
- {provider: ..., model: ..., reasoning_effort: low}
- {provider: ..., model: ..., reasoning_effort: xhigh}
aggregator:
{provider: ..., model: ..., reasoning_effort: high}
- Remove reasoning_effort from the moa_reference/moa_aggregator
DEFAULT_CONFIG blocks; _get_task_extra_body now warns-and-ignores the
key on MoA tasks, pointing at the preset config
- Guard tests: MoA aux blocks must not regrow the key; task-level value
is rejected with the pointer warning
- Docs: configuration.md notes the MoA exception and links the MoA page
Every auxiliary task block (vision, web_extract, compression,
title_generation, curator, background_review, moa_reference, ...) now
accepts a reasoning_effort shorthand:
auxiliary:
compression:
reasoning_effort: low
vision:
reasoning_effort: none
_get_task_extra_body() folds it into extra_body.reasoning, which every
auxiliary wire already translates: chat.completions passes it through,
the Codex Responses adapter maps it to top-level reasoning/include, and
the Anthropic auxiliary adapter now forwards it into
build_anthropic_kwargs(reasoning_config=...) (previously hardcoded None).
An explicit extra_body.reasoning on the same task wins over the
shorthand. Invalid levels are ignored with a warning. Empty string
(the shipped default) is a no-op — zero behavior change.
Config: reasoning_effort added to all 16 auxiliary task blocks in
DEFAULT_CONFIG (no version bump — deep-merge handles new keys).
