Claude Code OAuth refresh tokens are single-use; Claude Code refreshes on
its own schedule, so by the time Hermes notices an expired token Claude
Code may have already rotated it. Re-read live credential sources first and
adopt a valid token rather than POSTing a possibly-stale refresh token.
Ports the _refresh_oauth_token hardening from PR #40107 (chazmaniandinkle)
on top of the keychain/file reconciliation from PR #21112 (nodejun).
Adds AUTHOR_MAP entry for nodejun.
read_claude_code_credentials() previously returned the macOS Keychain
entry as soon as one existed, even if its OAuth token was already
expired. Callers then ran is_claude_code_token_valid() on the result
and got False, so resolve_anthropic_token() returned None — surfacing
the misleading 'No Anthropic credentials found' error even when
~/.claude/.credentials.json held a perfectly valid token.
Now reads both sources and prefers the non-expired one. When both are
valid (or both expired), prefers the later expiresAt so any subsequent
refresh uses the freshest refresh_token.
Adds TestReadClaudeCodeCredentialsDesync covering the four reconciliation
cases. The existing 'keychain wins' priority test still passes because
both fixtures share the same expiresAt and the tiebreaker is >=.
Eager fallback previously fired only on rate_limit/billing. A stale-
detector-killed hung stream classifies as FailoverReason.timeout
(retryable=True) and the retry loop re-hit the same dead primary until
the budget exhausted -- 3 x ~180-300s stale kills compounding into a
15+ min silent hang while the configured fallback chain sat idle.
Extend the existing eager-fallback gate to also cover timeout and
overloaded, but only after one real retry (retry_count >= 2) so genuine
transient hiccups still recover on the primary. Reuses the same
pool-recovery guard and state-reset as the rate_limit branch -- no new
config flag, no change to the rate-limit intent.
Salvaged from PR #50228 by @linyubin. Closes#22277.
Co-authored-by: Hermes Agent <127238744+teknium1@users.noreply.github.com>
_try_openrouter() returned (None, None) whenever an OpenRouter credential
pool existed but was exhausted (_select_pool_entry -> (True, None)), making
the OPENROUTER_API_KEY env-var fallback unreachable. Auxiliary tasks
(compression, vision, web_extract) silently failed even with a valid env key.
Now the pool-present branch only returns early when it successfully builds a
client; an exhausted pool falls through to the env-var path. The final
failure (pool exhausted AND no env var) still marks the provider unhealthy.
Fixes#23452.
Co-authored-by: ambition0802 <noreply@github.com>
When the primary provider returns 401 and the auth-refresh path is
unavailable or fails, both call_llm() and async_call_llm() reached the
should_fallback gate without _is_auth_error in the condition, so the
auxiliary task (e.g. compression) was dropped silently — losing message
history. Add _is_auth_error to should_fallback (NOT is_capacity_error) in
both sync and async paths, plus an 'auth error' reason branch.
Auth stays a non-capacity error: it falls back in auto mode via the
is_auto gate, but on an explicitly-configured provider it still respects
the user's choice and raises rather than silently switching providers.
The agent's image-rejection fallback strips images and retries text-only when
a provider rejects image content, which is what lets the gateway drain its
queued messages. The fallback only fires on a hardcoded phrase list, and the
OpenRouter wording — HTTP 404 'No endpoints found that support image input' —
was missing. For OpenRouter-routed non-vision models the fallback never fired,
the retry loop re-sent the same rejected request until exhaustion, and every
subsequent message (including plain text) stayed queued behind the stuck turn.
Add the phrase to _IMAGE_REJECTION_PHRASES (the 404 already passes the 4xx
gate). Add a positive test and a guard test so the sibling OpenRouter
'no endpoints ... data policy / guardrail' 404s do NOT get their images
stripped.
Fixes#21160. Reported by @liu14goal14-ux; PR #21198 by @ygd58.
Follow-up to #53791 addressing review feedback: the footgun checker treated
capture_output=/stdout=/stderr=/check_output as proof a subprocess can't pop a
Windows console. That invariant is false — stream redirection controls where a
child's output goes, not whether a console is allocated. From a console-less
parent (Desktop/Electron, pythonw.exe, detached gateway/cron) a console-subsystem
child still flashes a window even when fully captured.
- check-windows-footguns.py: capture/redirect/check_output is no longer a blanket
safe-pass. Added _WINDOWS_FLASHING_PROGRAMS (git/gh/npm/node/python/uv/ffmpeg/
docker/powershell/…); calls to those are flagged even when captured. Non-flashing
programs keep the capture exemption (no 271-site noise). _subprocess_compat.run/
popen calls are inherently safe (wrapper injects CREATE_NO_WINDOW).
- Routed the 35 genuine flashing git/gh/npm/uv/ffmpeg/docker spawns through the
_subprocess_compat.run/popen chokepoint (Brooklyn's wrapper from #53810) — the
durable fix, not per-site annotations. cmd.exe /c start stays # ok (intentional).
- Updated tests + CONTRIBUTING.md rule #17 to the corrected invariant.
On a MoA session, auxiliary tasks (title generation, compression, vision, …)
ran through _resolve_auto with provider='moa' / model='<preset>', which sent
the preset name (e.g. 'opus-gpt') as the model id to resolve_provider_client —
producing 'HTTP 400: opus-gpt is not a valid model ID' on every turn (visible
as the title-generation warning).
MoA is a virtual provider with no real HTTP endpoint; aux tasks don't need the
reference fan-out. _resolve_auto now resolves a 'moa' main provider to the
preset's aggregator slot (its acting model) and continues Step 1 with that real
provider+model, dropping the virtual moa://local base_url + placeholder key so
the aggregator resolves via its own provider credentials. Mirrors the MoA
context-length resolution.
Verified live: a MoA turn no longer emits the 'not a valid model ID' warning.
Test: tests/agent/test_auxiliary_main_first.py (19 pass).
* fix(windows): stop subprocess console-window popups + add CI guard
The single biggest source of Windows 'terminal popup' bug reports was bare
subprocess.run/Popen calls spawning a console window. The compat helpers
(windows_hide_flags / windows_detach_popen_kwargs) already existed but the
footgun checker had no rule to stop new bare calls from reintroducing the flash.
- scripts/check-windows-footguns.py: new AST-based rule flagging subprocess
calls that can create a new console — output-redirection-aware (capture/
redirect/check_output exempt) and POSIX-only-program-aware (launchctl/
systemctl/brew/etc. exempt). Comprehensive on real popups, no annotation
burden on calls that can't flash.
- Swept all genuine window-spawning sites through windows_hide_flags()/
windows_detach_popen_kwargs(); marked intentionally-visible launches
(editor/terminal/foreground re-exec) with '# windows-footgun: ok'.
- tests/scripts/test_windows_footgun_subprocess_rule.py: behavior-contract
tests + full-repo cleanliness invariant.
- CONTRIBUTING.md: documents the rule + the helper pattern.
* test: accept creationflags kwarg in psutil_android fake_subprocess_run
The Windows no-window sweep added creationflags=windows_hide_flags() to
install_psutil_android.py's subprocess.run call; the test's fake stub had a
fixed (cmd) signature and raised TypeError on the new kwarg.
When a MoA preset is selected, each reference model's answer now renders in the
CLI as a thinking-style block labelled with its source model, BEFORE the
aggregator responds — so the mixture-of-agents process is visible instead of a
silent pause. The aggregator's response (and its tool actions) follow as normal.
Mechanism (shared seam, all surfaces):
- MoAChatCompletions/MoAClient take an optional reference_callback and emit
'moa.reference' (index/count/label/text) per reference, then 'moa.aggregating'
(aggregator label) once. agent_init wires this to the agent's
tool_progress_callback, which every surface already consumes — so the events
reach CLI/TUI/desktop/gateway with no new plumbing.
- CLI _on_tool_progress renders 'moa.reference' as a labelled '┊ ◇ Reference
i/n — <model>' header + a thinking-style preview (reusing _emit_reasoning_
preview), and 'moa.aggregating' as a spinner transition. Display-only; never
touches message history (cache-safe).
Turn-scoped reference cache: the agent loop calls the facade once per tool-loop
iteration, but the advisory message view is identical across iterations within a
turn, so references are now run AND displayed once per user turn (keyed by the
advisory view's signature) instead of re-running/re-spamming on every iteration.
This also cuts reference API cost from O(iterations) back to O(turns).
Verified live via interactive PTY on the opus-gpt preset (gpt-5.5 + opus refs):
reference blocks render once per turn, labelled by model, before the aggregator;
fresh blocks on each new turn; aggregator tool actions still execute.
Follow-up: TUI/desktop rich rendering + gateway batched-summary already receive
the events via tool_progress_callback; their surface-specific renderers are a
separate change.
A MoA session's model is the preset name (e.g. 'opus-gpt') and its base_url is
the virtual local endpoint, so get_model_context_length() missed every probe
and fell through to the 256K fallback — even when the aggregator is a 1M-context
model. The acting model in MoA IS the aggregator, so resolve the context window
from the aggregator slot's real provider+model.
- model_metadata.get_model_context_length: when provider=='moa', resolve the
preset's aggregator slot through resolve_runtime_provider and recurse with the
aggregator's real provider/model/base_url. Explicit model.context_length still
wins (checked first); falls through to the generic default if resolution fails.
Tests: opus-gpt preset now reports 1M (the aggregator window), config override
still honored.
The secret redactor only matched uppercase env-style keys ([A-Z0-9_]),
so config-file assignments like spring.datasource.password=secret,
app.api.key=xyz, and YAML password: secret leaked verbatim when the
agent ran cat/grep on application.properties or .env files (issue #16413).
Adds three case-insensitive config-key matchers that run only in a
config-file context, preserving the existing #4367 (lowercase code/prose)
and web-URL-passthrough carve-outs:
- _CFG_DOTTED_RE: namespaced keys (contain a dot) — unambiguously config
- _CFG_ANCHORED_RE: bare secret-word keys at line start (incl. export)
- _YAML_ASSIGN_RE: unquoted colon config (password: value)
Value capture stops at whitespace and '&' so form bodies stay pair-wise;
the '://' guard keeps intentional web-URL query-param passthrough intact.
Reported-by: Murtaza1211
MoA was calling reference and aggregator models through a bare
call_llm(provider=slot["provider"], model=slot["model"]) with a forced
temperature and a forced max_tokens (the preset's hardcoded 4096). That left
base_url/api_key/api_mode unresolved — so the auxiliary auto-detector guessed
the API surface instead of using the provider's real runtime, and the 4096 cap
truncated long aggregator syntheses.
A MoA slot is just a model selection and must be called the same way any model
is called elsewhere. Each slot is now resolved through resolve_runtime_provider
(the canonical provider→api_mode/base_url/api_key resolver the CLI, gateway, and
delegate_task all use) via a new _slot_runtime() helper, and the resolved
endpoint is passed into call_llm. So a reference/aggregator gets its provider's
actual API surface — MiniMax → anthropic_messages, GPT-5/o-series →
max_completion_tokens, custom endpoints → their base_url — identical to how that
model is handled as the acting model.
MoA also no longer imposes its own output cap: max_tokens defaults to None
(omitted → the model's real maximum) for references and is passed through from
the caller for the aggregator. The preset's hardcoded 4096 is gone. The
max_tokens preset config field is left in place (config/web/desktop unchanged);
it is simply no longer applied as a forced cap.
Tests: slots route through resolve_runtime_provider with resolved base_url/
api_key; resolution errors fall back to bare provider/model; neither call
carries an output cap even when the preset config still contains max_tokens.
When automatic fallback activates a provider that differs from the
primary, try_activate_fallback() cleared the primary's pool (to avoid
cross-provider base_url contamination, #33163) but never loaded the
fallback provider's own pool. The fallback then ran with no pool, so
rate_limit/billing/auth recovery couldn't rotate its credentials.
After clearing a mismatched pool, load_pool(fb_provider) and attach it
when it has credentials, so provider-specific rotation continues to
work on the fallback target.
switch_model() swapped model/provider/base_url/api_key but never
refreshed agent._credential_pool, which stays bound to the original
provider. recover_with_credential_pool() then sees a pool.provider !=
agent.provider mismatch and short-circuits — so a 429/401 on the new
provider gets no rotation and falls through to fallback instead.
Reload load_pool(new_provider) inside switch_model when the provider
changes (or the pool is missing). The reload is inside the protected
swap block and the pool is added to the rollback snapshot, so a failed
client rebuild restores the original pool.
Fixes#16678, #52727.
Z.AI / Zhipu reuse HTTP 429 for server-wide overload. The 429 status
path classified these unconditionally as rate_limit with
should_rotate_credential=True, so an overloaded provider exhausted the
credential pool after two errors — fatal for a single-key user, who has
nothing to rotate to.
The credential is valid; the server is just busy. Disambiguate the 429
body against a shared _OVERLOADED_PATTERNS list and route overload
language to FailoverReason.overloaded (retryable, no rotation), matching
the existing 503/529 path and the message-only path (#52890). Genuine
rate limits (no overload language) still rotate.
Extracted the inline overloaded tuple #52890 added into the shared
_OVERLOADED_PATTERNS constant so the status-code and message paths use
one list.
Closes#14038.
The error raised when a model's context window is below the 64K minimum
advertised "or set model.context_length in config.yaml to override" — but
the guard intentionally has no sub-64K escape hatch. Sub-64K models are
rejected by design (tool schemas + system prompt need the headroom).
The misleading clause invited a cluster of dup PRs (#11097, #11110, #8962,
#9142, #37548) all trying to wire an override that we don't want. Reword to
state the real options: pick a >=64K model, or — if your local server
under-reports its true window — declare the real value (which must itself
be >=64K). Guard behavior is unchanged.
The 'whatsapp' and 'signal' PLATFORM_HINTS told the agent 'Please do not
use markdown as it does not render' — factually wrong. Both adapters
actively convert markdown to native formatting:
- whatsapp_common.format_message(): **bold**, ~~strike~~, # headers,
links, code blocks -> WhatsApp native syntax
- signal_format.markdown_to_signal(): same conversions via bodyRanges,
plus '- item' / '* item' bullets -> '• ' Unicode bullets
The wrong hint made the agent strip bullets and bold the adapter would
have rendered (#12224). Rewrote both hints to mirror whatsapp_cloud:
markdown is auto-converted, bullet lists work, tables are not supported.
Added a contract test asserting markdown-converting platforms never
forbid markdown in their hint.
The verify-on-stop guard fired too eagerly — including on doc/markdown/skill
edits with nothing to verify, where it pushed a pointless /tmp verification
script. Three changes:
1. Default OFF for new installs: agent.verify_on_stop defaults to false
(was the "auto" surface-aware sentinel). _config_version bumped 30 -> 31.
2. One-time migration (v30 -> v31): existing installs are switched off once,
but only when the value is missing or still the "auto" sentinel — an
explicit true/false the user set is preserved.
3. Path filter: build_verify_on_stop_nudge() now drops documentation/prose
paths (.md/.mdx/.rst/.txt/LICENSE/CHANGELOG/...) so even when explicitly
enabled, a doc-only turn never nudges. Mixed doc+code turns still nudge on
the code paths.
The legacy "auto" sentinel is still honored when set explicitly (ON for
interactive coding surfaces, OFF for messaging). HERMES_VERIFY_ON_STOP env
override unchanged.
- Use os.pathsep instead of literal ':' so Windows paths (C:\dir) and
the Windows separator ';' work correctly.
- Add 9 tests covering multi-root behavior: writes inside first/second
root, writes outside all roots, trailing/leading/double separators,
all-separators edge case, static deny priority, duplicate dedup.
- Update hermes_cli/tips.py tip string to mention multiple paths.
- Update docs to mention os.pathsep / ; on Windows.
Follow-up for salvaged PR #49557.
The verify-on-stop guard (#52296) printed '↻ Verification required before
finishing' to the terminal on every internal nudge turn, adding noise to
CLI/gateway sessions whenever code was edited without fresh passing checks.
Demote the user-facing status emit to a logger.debug breadcrumb — the loop
still nudges the model to verify before finishing, just silently.
When operator config has provider=anthropic with model.base_url pointing
at a non-Anthropic host (e.g. https://openrouter.ai/api/v1 with provider=anthropic),
the auxiliary Anthropic path was unconditionally applying that override.
Main-session traffic routed correctly because the main path attaches the
right credential for the actual destination, but every side-channel call
(memory extractors, reflection, vision, title generation, janus
extractor/promise) sent ANTHROPIC_API_KEY to the foreign host and 401'd.
Gate the override on hostname == api.anthropic.com. Operators routing main
through a non-Anthropic provider must use that provider's own auxiliary
client; the Anthropic aux path now stays pointed at api.anthropic.com.
Regression tests cover openrouter, openai, anthropic-with-path, empty, and
anthropic-default-base_url cases.
Wire get_reasoning_stale_timeout_floor() into both stale detectors so known
reasoning models (Nemotron 3 Ultra, OpenAI o1/o3, Opus 4.x thinking, DeepSeek
R1, Qwen QwQ, Grok reasoning) tolerate multi-minute thinking phases instead of
the upstream gateway idle-killing the socket (BrokenPipeError) before first
token. Applied as max(default, floor) — never overrides explicit user config,
never lowers an existing threshold.
The reasoning_timeouts.py allowlist module already landed on main via #52795,
so this salvage carries only the wiring + tests (the duplicate module and the
stale-base MoA reverts from the original PR branch are dropped).
Salvaged from #52238. Fixes#52217.
The salvaged #51875 added a background-review write guard in skill_manage
that refuses mutations to skills.external_dirs skills — but it only fires
when is_background_review() is true. The curator's LLM review fork ran with
the default _memory_write_origin='assistant_tool', so the guard never
triggered during the exact curation pass it exists to protect against
(GH-47688).
- Set _memory_write_origin='background_review' on the curator review fork so
turn_context binds it onto the write-origin ContextVar and the guard fires.
- Add a regression test asserting the fork runs under the background_review
origin (the invariant linking the fork to the guard).
- AUTHOR_MAP: map yu-xin-c for the salvaged commit.
Force redact_sensitive_text(force=True) on the browser_type text arg so
recognized credentials (API keys, tokens, JWTs) are masked in tool
progress, previews, callbacks, and return payloads even when the global
security.redact_secrets opt-out is set — a typed credential reaching chat
history is a security boundary, not log hygiene. Normal typed text matches
no pattern and stays fully readable for debuggability.
Tests assert the API-key-shaped secret is masked across every surface and
that normal text passes through unchanged.
Stopping a turn while the model is streaming (stop/esc to redirect) raised
InterruptedError, set final_response to the throwaway "waiting for model
response" sentinel, and persisted messages WITHOUT the assistant text that
was already streamed to the screen. The next turn then had no record of the
half-finished reply, so the model appeared to "forget" what it just said.
Recover the on-screen text from _current_streamed_assistant_text in the
InterruptedError branch and append it as the assistant turn (and surface it
as final_response). The metadata sentinel is kept only when nothing was
streamed yet, preserving the ACP/client suppression behavior.
Completes the partial-stream recovery from 397eae5d9 (which wired the same
_current_streamed_assistant_text salvage into the connection-failure twin
but missed the user-interrupt path). The lossy handler dates to c98ee9852.
CredentialPool._sync_device_code_entry_to_auth_store rotated single-use
OAuth refresh tokens but wrote the new chain only into the active profile
store. When a profile resolves a grant from the global-root fallback
(read_credential_pool, #18594) and the pool then refreshes it, root was
left holding a now-revoked refresh token — every other profile reading the
stale root grant subsequently died with refresh_token_reused / invalid_grant
once its access token expired.
This is the credential-pool analog of #43589 (which fixed the non-pool xAI
refresh path in _save_xai_oauth_tokens). Detect the read-from-root case
(profile lacks its own providers.<id> block) BEFORE the profile save and,
after it, write the rotated chain back to the global root via a best-effort,
seat-belted write-through. A profile that genuinely shadows root (owns the
block) is untouched; classic mode (profile == root) is a no-op; a failed root
write never breaks the profile's own save. Covers openai-codex (reported),
xai-oauth, and nous through the shared sync path.
Two-part fix:
Part 1 (classifier override at agent/error_classifier.py:720-738):
A transport disconnect on a reasoning model — even on a large session —
now routes to FailoverReason.timeout instead of context_overflow. Without
this, large-session reasoning-model disconnects route to the compression
branch and silently delete conversation history on a phantom
context-length error. The override is strictly targeted: non-reasoning
models (gpt-4o, claude-3-5-sonnet, llama-3.3-70b, etc.) still route to
context_overflow on large sessions — the existing intentional behavior
for chat models whose proxy doesn't idle-kill during prefill/generation.
Part 2 (new agent/thinking_timeout_guidance.py + integration at
agent/conversation_loop.py:3488-3567):
New is_thinking_timeout() and build_thinking_timeout_guidance() helpers.
When a known reasoning model (NVIDIA Nemotron 3 Ultra, OpenAI o1/o3,
Anthropic Opus 4.x thinking, DeepSeek R1, Qwen QwQ, xAI Grok reasoning)
hits a transport-kill on a small session (classifier says timeout
directly) or after Part 1 routes correctly (large session), the user
now sees reasoning-specific guidance with three actionable workarounds
in priority order:
1. Set providers.<provider>.models.<model>.stale_timeout_seconds: 900
in ~/.hermes/config.yaml (Hermes's built-in floor is already 600s
for known reasoning models; raise further if upstream is even
tighter).
2. Lower reasoning_budget or set reasoning_effort: medium on this
model if the provider supports it.
3. Use a smaller / faster reasoning model if the task doesn't
require deep thinking.
The new guidance takes precedence via if/elif over the existing
_is_stream_drop block, so a reasoning-model user with a transport-kill
message sees actionable advice instead of the misleading "try
execute_code with Python's open() for large files" advice (which is
correct for the unrelated large-file-write stream-drop case but
actively wrong for the thinking-timeout case).
Verified:
- 478 tests passing across 9 directly-relevant files (49 new + 429
existing, zero regressions).
- Ruff lint clean on all 4 modified/new files.
- Negative test: 6 parametrized regression guards confirm non-reasoning
models still route to context_overflow on large sessions; 4
parametrized gates confirm non-timeout classifier reasons never
trigger the guidance; 5 parametrized cases confirm non-transport
messages never trigger it.
- Regression guard: new guidance message does NOT contain
"execute_code" or "open()" — the misleading advice is fully
replaced, not appended alongside.
- Cross-vendor dual review via agy -p:
- Gemini 3.5 Flash (Medium) — passed: true, zero blockers, one
SHOULD-FIX (vprint block duplication — fixed by extracting
detection into a helper module).
- GPT-OSS 120B (Medium) — passed: true, zero blockers, two nits
(test placement — adopted at tests/agent/test_thinking_timeout_guidance.py;
primary-model capture — accepted as non-issue per Flash's nit).
Dependency note for maintainers:
This PR includes agent/reasoning_timeouts.py (the reasoning-model
allowlist module from PR #52238) because the Layer 1 override is
load-bearing on get_reasoning_stale_timeout_floor(). After PR #52238
lands on main, this PR's duplicate agent/reasoning_timeouts.py should
be rebased away. Either PR can land first; the other rebase is
mechanical.
Fixes#52271.
The session database records billing_provider and billing_base_url using
COALESCE(column, ?) in update_token_counts(), making them write-once.
When a user switches models mid-session via /model, the runtime (agent.provider,
agent.base_url) updates correctly, but the session row never reflects the new
provider. This causes the dashboard Models page to display a stale provider
badge and misattributes token usage / cost analytics.
Fix: add update_session_billing_route() that unconditionally sets
billing_provider, billing_base_url, and billing_mode (no COALESCE), and call
it from switch_model() in agent_runtime_helpers.py after the swap succeeds.
This follows the same pattern as update_session_model() which already
unconditionally updates the model column (added for the identical COALESCE
problem on the model field).
Closes#48248
* feat(moa): expose MoA presets as selectable virtual models
Reconstructed onto current main (PR #46081's base had diverged with no common
ancestor, marking the PR dirty so CI never dispatched). MoA is now a virtual
provider: each named preset is a selectable model under provider 'moa', and the
preset's aggregator is the acting model that answers and calls tools.
Reference models fan out in parallel via a bounded ThreadPoolExecutor (the same
batch pattern delegate_task uses) — all references dispatched at once, collected
when every one finishes, then handed to the aggregator. Output order is
preserved, failures and the MoA-recursion guard stay isolated per reference.
- Removed the old mixture_of_agents model tool and moa toolset.
- Added moa as a virtual provider in the provider/model inventory.
- /moa is shortcut behavior over model selection (default preset / named preset
/ one-shot prompt).
- Dashboard + Desktop manage named presets; presets appear in model pickers.
- Parallel reference fan-out in agent/moa_loop.py with regression test.
* fix(moa): thread moa_config through _run_agent to _run_agent_inner
The reconstructed gateway MoA wiring declared moa_config on _run_agent (the
profile-scoping wrapper) and used it inside _run_agent_inner, but the wrapper
never forwarded it — _run_agent_inner had no such parameter, so the runtime hit
NameError: name 'moa_config' is not defined on the compression-failure session
sync path. Add moa_config to _run_agent_inner's signature and forward it from
both wrapper call sites (multiplex and non-multiplex). Caught by
tests/gateway/test_compression_failure_session_sync.py on CI shard test(4).
* fix(moa): classify moa as a virtual provider in the catalog
The moa virtual provider has no PROVIDER_REGISTRY/ProviderProfile entry, so
provider_catalog() fell through to the default auth_type="api_key" with no
env vars — tripping two catalog invariants:
- test_provider_catalog: api_key providers must expose a credential env var
- test_provider_parity: every hermes-model provider must be desktop-configurable
moa already declares auth_type="virtual" in HERMES_OVERLAYS; consult that
overlay as an auth_type fallback so the catalog reports moa as virtual (no real
credential, no network endpoint). Exempt virtual providers from the desktop
parity union check the same way 'custom' is exempt — derived from the catalog,
not a hardcoded slug, so future virtual providers are covered too.
The salvaged context-window screen (#52392) skips fallback candidates that
are too small, and the rate-limit/403 fixes skip candidates that are at
capacity. A third hard failure remained uncovered: a fallback that builds a
client fine but returns a 400 because it structurally cannot run the model.
The canonical case is a configured openai-codex / ChatGPT-account fallback
asked to compress a glm-5.2 conversation:
400 - {'detail': "The 'glm-5.2' model is not supported when using
Codex with a ChatGPT account."}
This is a request-validation error, so should_fallback was False and the
explicit-provider gate blocked it — the auxiliary task (compression) aborted
every turn, dropping middle turns without a summary and churning the session,
which is exactly what destroys the prompt cache.
Adds _is_model_incompatible_error() (400 + capability phrasing, excluding
not-found and billing 400s which the sibling predicates own) and treats it as
a fallback-worthy capacity error in both sync and async call_llm, so the chain
skips the incapable route and continues to the next viable candidate.
The runtime auxiliary fallback chain (_try_configured_fallback_chain and
_try_main_fallback_chain) returned the first reachable candidate without
checking whether the candidate's context window was large enough for the
task. For task='compression' this meant a reachable but undersized
fallback (e.g. 32K) could be selected and then fail, even when a later
larger-context fallback was available.
This adds two small helpers:
_task_minimum_context_length(task)
Returns MINIMUM_CONTEXT_LENGTH (64K) for compression, None for
other tasks (vision, web_extract, etc.).
_candidate_context_window(provider, model, ...)
Thin wrapper around get_model_context_length that returns None on
probe failure so unknown/custom endpoints pass through unchanged
(preserves the existing fallback surface).
Both fallback loops now skip reachable candidates whose resolved context
is below the task minimum and continue iterating. The success path
(first viable candidate wins) is unchanged. Return shape and ordering
for healthy candidates are preserved.
Six regression tests cover:
L2 configured chain skips too-small candidate
L2 chain continues after skipping, returns last viable
L3 main chain skips too-small candidate
L4 unknown-context candidate passes through
L5 non-compression task is not filtered
L6 minimum constant matches MINIMUM_CONTEXT_LENGTH (64K)
3/6 fail on upstream/main without the production change (verified); all
6 pass with the fix. Full test_auxiliary_client.py suite (231 tests)
and related compression tests (130 tests) remain green.
When an explicit aux provider cannot build a client before any request is
sent (missing raw env key, exhausted/unavailable OAuth or credential-pool
auth, resolver returning (None, None)), call_llm raised a misleading
"no API key was found" error and bypassed the configured fallback_chain
entirely. A provider authenticated through Hermes auth / the credential
pool (e.g. ollama-cloud) whose pool entry is exhausted hit this path, so
compression failed instead of routing to the configured fallback.
Adds _try_configured_fallback_for_unavailable_client() and wires it into
both sync and async call_llm before the raise, and into the startup
compression feasibility check.
Salvaged from #51835 by @herbalizer404.
