Review follow-ups on the model_overrides feature:
- ONE canonical override schema everywhere. get_model_info previously
merged the override dict raw into the models.dev catalog shape
({**raw, **override}), so the documented context_window/supports_*
keys silently did nothing on that path (cost guard, inventory) while
working in capabilities/context paths — same config key, two
incompatible schemas. Overrides are now translated into the catalog
shape at the get_model_info boundary (_override_to_catalog_shape),
and sub-dicts (limit, modalities) are MERGED, not clobbered — an
override setting only context_window no longer wipes the catalog's
limit.output.
- _default is now a FILL-GAP default, not an override: it applies only
to models the catalog does not know (the #8731/#84482 self-unblock
path) and never displaces catalog data. A
_default: {context_window: 128000} can no longer clamp every model
of a provider. Explicit per-provider+model entries keep their
win-over-catalog semantics.
- Early-chain _override_context_window (model_metadata step 0b) is
explicit-only, so a _default can never preempt custom_providers
per-model settings or live probes; fill-gap defaults apply at the
lookup_models_dev_context catalog-miss boundary (step 5f) instead.
This fixes the precedence inversion where a provider/global _default
silently overrode an explicit per-endpoint per-model context_length.
- Provider keys accept BOTH id spaces (Hermes id and models.dev id:
copilot/github-copilot both work) and model ids match
case-insensitively, mirroring catalog lookup.
- Malformed override values (context_window: '512k') log a one-shot
warning instead of being silently swallowed.
- DEFAULT_CONFIG comment: removed the false family/dated-snapshot
inheritance claim, documented the recognized field list, fill-gap
semantics, and the id-space rule.
- Tests: rewritten for the new contracts (fill-gap invariants,
dual-id-space keys, sub-dict merge preservation, one-shot warning);
added a real-config-yaml e2e plumbing test (mutation-checked: fails
when the config key wiring is broken).
Add a unified model_overrides config section that lets users manually
declare context_window, max_output_tokens, capabilities, cost, and
family for any provider+model — winning over models.dev, OpenRouter, and
hardcoded defaults.
Resolution order (first hit wins):
1. model_overrides.<provider>.<model_id> (per-provider+model)
2. model_overrides.<provider>._default (per-provider default)
3. model_overrides._default (global default)
4. Normal catalog resolution
Key subtlety: an unknown model id (not in the
catalog) derives base metadata from sensible defaults before patching,
so overriding a model the catalog doesn't know yet is the supported
self-unblock path. This is exactly the #84482 scenario (Upstage
solar-pro4/syn-pro wrong context) and the #8731 scenario (custom/local
models with manual capability declaration).
Wired into:
- get_model_capabilities() — patches capability fields; unknown models
get safe defaults (tools on, vision/reasoning off) before patching
- lookup_models_dev_context() — context_window override, checked before
catalog lookup so it works even for providers not in PROVIDER_TO_MODELS_DEV
- get_model_info() — merges override dict onto catalog entry (shallow
merge); for unknown models, the override is the sole source of metadata
- get_model_context_length() — step 0b in the resolution pipeline,
before custom_providers (0c) and before any network probe
Config example:
model_overrides:
upstage:
solar-pro4:
context_window: 524288
syn-pro:
context_window: 65536
custom:my-local-vllm:
my-llava-model:
context_window: 8192
supports_vision: true
supports_reasoning: false
supports_tools: true
_default:
context_window: 128000
Fixes#8731Fixes#84482
Refs #47247
save_context_length() and _invalidate_cached_context_length() did an
unguarded read-modify-write into $HERMES_HOME/context_length_cache.yaml.
The plain `open(path, "w")` truncates the file before the dump runs. If
the process is killed mid-dump, the file is left empty or partial. The
next _load_context_cache() swallows the YAML error and returns {} —
silently wiping every persisted context length. A concurrent process
reading between truncate and dump-complete also sees a torn file.
After the cache is lost, every model re-probes the network, and when a
probe fails it falls back to the generic 256K default — so a user on a
1M-window model ends up with a wrong, short context window.
Hermes routinely runs several processes against one shared $HERMES_HOME
(a cron agent plus an interactive session, multiple gateway sessions),
so this is hit in normal use.
Switch both writers to the existing utils.atomic_yaml_write helper
(temp file + fsync + os.replace, symlink- and mode-preserving). The real
file is only ever swapped from a fully written temp file, so an
interrupted write leaves the previous cache intact and readers never see
a partial file. Matches the atomic-write pattern already used for
auth.json, config.yaml, and other persisted state.
Makes the persistent model context-length cache write crash-safe. The
old non-atomic write could truncate or wipe the entire cache on an
interrupted or concurrent write, which then forces models onto the wrong
fallback context window. The fix routes both cache writers through the
repo's atomic temp-file + os.replace helper.
N/A
- [x] 🐛 Bug fix (non-breaking change that fixes an issue)
- [ ] ✨ New feature (non-breaking change that adds functionality)
- [ ] 🔒 Security fix
- [ ] 📝 Documentation update
- [ ] ✅ Tests (adding or improving test coverage)
- [ ] ♻️ Refactor (no behavior change)
- [ ] 🎯 New skill (bundled or hub)
- `agent/model_metadata.py`: `save_context_length()` and
`_invalidate_cached_context_length()` now write via
`utils.atomic_yaml_write` instead of a truncating `open(path, "w")`.
Added the `atomic_yaml_write` import.
- `tests/agent/test_model_metadata.py`: added
`test_write_failure_leaves_existing_cache_intact` — simulates a crash
during the atomic swap and asserts the existing cache survives
byte-for-byte with no stray temp file.
1. `pytest tests/agent/test_model_metadata.py -q` — 98 pass, including
the new crash-safety test.
2. The new test seeds a valid cache, forces the swap step to raise, and
confirms the file is not truncated and no `.cache_*.tmp` is left.
3. `ruff check agent/model_metadata.py` passes.
- [x] I've read the Contributing Guide
- [x] My commit messages follow Conventional Commits (`fix(scope):`, etc.)
- [x] I searched for existing PRs to make sure this isn't a duplicate
- [x] My PR contains **only** changes related to this fix
- [x] I've run the affected tests (`pytest tests/agent/test_model_metadata.py -q`) and they pass
- [x] I've added tests for my changes
- [x] I've tested on my platform: macOS 15 (Darwin 25.5)
- [x] I've updated relevant documentation (README, `docs/`, docstrings) — or N/A
- [x] I've updated `cli-config.yaml.example` if I added/changed config keys — or N/A
- [x] I've updated `CONTRIBUTING.md` or `AGENTS.md` if I changed architecture or workflows — or N/A
- [x] I've considered cross-platform impact (Windows, macOS) — the helper uses os.replace, which is atomic on both
- [x] I've updated tool descriptions/schemas if I changed tool behavior — or N/A
Reapply the non-positive context-length guards onto the post-history-replacement
mainline without carrying any stale branch history. save_context_length() now
refuses to persist length <= 0 (keeping upstream's normalized _context_cache_key),
and get_model_context_length() drops non-positive cache hits at the head of the
invalidation chain (Codex/Kimi/MiniMax/Grok branches become elif) so a poisoned
entry re-resolves instead of short-circuiting to 0.
Refresh of PR #25812; original head d62ed5eb92f057d8c707ba937b44f168f2df0677.
An empty/blank model id reaching get_model_context_length() can't be
meaningfully resolved — and it's worse than a miss: the endpoint
metadata fuzzy matcher ('model in key or key in model') is vacuously
true for "", so it matches an ARBITRARY catalog entry from the live
/v1/models response and returns whatever context length that entry
happens to have, persisting it under a junk '@<base_url>' cache key.
This started failing CI on main when the Nous portal catalog changed:
tests/run_agent/test_primary_runtime_restore.py constructs agents with
model='' against the live portal URL, the arbitrary match now lands on
a 32K entry, and init_agent raises the 64K-floor ValueError
(test_allowed_for_nous_anthropic_messages, red on every PR's slice).
Guard early: a blank model id falls back to DEFAULT_FALLBACK_CONTEXT
immediately, before any cache write or network probe.
Salvaged from #65515 by @whirmill (rebased onto current main; the
guard now sits after the malformed-base_url normalization added since,
and carries an explanatory comment for the fuzzy-match footgun).
Fixes the red slice on #85444, #85452 and every other open PR.
Co-authored-by: whirmill <5079591+whirmill@users.noreply.github.com>
Replaces the per-model _model_name_suggests_grok_4_3/_grok_4_6/
_minimax_m3 stale-cache predicates with one generic
_stale_pre_catalog_cache_entry() guard driven by
_PRE_CATALOG_STALE_KEYS. A cached context length is dropped when the
model resolves (longest-key-first, same as step 8) to a listed catalog
key and the cached value is at or below what the old resolution path
could have produced (largest shorter matching catch-all, or the 256K
fallback).
Also covers qwen3.6-plus, grok-4-fast, and grok-4.20 (the models
PR #37684 requested guards for), absorbing that PR.
_model_name_suggests_minimax_m3 is kept for its two non-cache callers
(models.dev underreport guard, cache-control gating in
agent_runtime_helpers).
docs.x.ai (2026-08-12): grok-4.6 is the flagship, 500K context.
Live GET /v1/models lists grok-4.6 at context_length 500000
(no grok-4.6-latest alias).
#84661 landed the catalog. Main already lists native grok-4.6
on the xAI picker. This is only the leftover cache guard
(same pattern as grok-4.3): pre-catalog builds persisted the
grok-4 catch-all (256K).
'' is a substring of every catalog key, so _resolve_endpoint_context_length
with an empty model name "matched" whatever the endpoint listed first —
on the Nous portal that is currently a 32K embedding model, which poisoned
the resolved context length and made AIAgent init fail the 64K minimum.
This is what turned tests/run_agent/test_primary_runtime_restore.py::
TestTryRecoverPrimaryTransport::test_allowed_for_nous_anthropic_messages
red on every PR (CI slice 7/12) after the portal catalog reordered.
Single-model endpoints still resolve with an empty name (unambiguous);
non-empty names keep the substring fuzzy match.
_PROVIDER_PREFIXES was a hand-maintained frozenset, so providers that ship
as plugins (bundled like fireworks, or user plugins under
$HERMES_HOME/plugins/model-providers/) were never recognised as
provider: prefixes in model strings, and metadata/context-window lookups
received the unstripped string. Mirror the _URL_TO_PROVIDER auto-extend
that already sits below it: add each registered profile's name and
aliases after discovery. The _OLLAMA_TAG_PATTERN guard keeps model:tag
strings intact.
Fixes#66106
Qwen3.8 Max is live on both OpenRouter and the Nous portal
(qwen/qwen3.8-max, 1M context, 131K max output). Per the
newest-max-replaces-last-max convention, it takes qwen3.7-max's slot
in both curated lists.
- hermes_cli/models.py: OPENROUTER_MODELS + _PROVIDER_MODELS[nous]
swap qwen/qwen3.7-max -> qwen/qwen3.8-max
- agent/model_metadata.py: DEFAULT_CONTEXT_LENGTHS entry for
qwen3.8-max at 1,000,000 (verified against OpenRouter live
metadata and Nous /v1/models 2026-08-03)
- tests/test_empty_model_fallback.py: swap incidental catalog fixture
to the surviving slug
- website/static/api/model-catalog.json: regenerated
Pricing snapshot skipped: both routes bill via official_models_api
(live pricing), verified with resolve_billing_route. Reasoning
timeout floor already covered by the qwen3 prefix (180s).
Salvage of #71282 (Fixes#71281): a routable-but-dead endpoint (corp
LAN address while off-VPN) blackholes TCP SYNs, so every probe in the
model-metadata waterfall waits out its full connect timeout — 20+
seconds of stall per startup across detect_local_server_type,
fetch_endpoint_model_metadata, and the per-model probes.
A module-level blackhole cache keyed on host:port is populated when
any probe observes a ConnectTimeout (httpx or requests; read timeouts
deliberately excluded — an accepted connection is not a blackhole) and
consulted at the top of each guarded function. 30s TTL: long enough to
collapse one startup burst, short enough that VPN recovery is picked
up without a restart. Guard ordering: blackhole check -> disk L2 ->
HTTP waterfall, and a blackholed leg aborts the remaining legs instead
of letting each stall in turn.
Squash of the PR's two real commits (the branch's merge commits made
it un-rebase-merge-able; content verified identical via merge-tree).
CI slice 3/7 failures: run_conversation tests pass MagicMock base_urls
through the metadata probe path; re.sub raised TypeError where the old
code let non-strings flow through. Preserve that contract.
fetch_endpoint_model_metadata's generic (non-LM-Studio) /models fetch and
its llama.cpp /v1/props context-length follow-up built request URLs
straight from the unrewritten candidate, unlike every other local-probe
site. Both retained the multi-second dual-stack IPv6 connect penalty
that _localhost_to_ipv4() exists to skip (measured on macOS: localhost
32.9ms vs 127.0.0.1 0.1ms on a dead port; ~2s on Windows). normalized
stays the cache key so caching behavior is unchanged; only the outbound
request target is rewritten.
Re-derived from PR #61528 onto current main (original no longer applied
cleanly).
- Short-circuit the candidate waterfall on HTTP 401/403: an auth wall
proves the endpoint family exists, so probing the alternate URL just
doubles the wasted wait (the reported endpoint takes ~10s to return
401 without a key).
- Stream the probe so 4xx never downloads a slow error body; responses
are closed on every exit path.
- Regression tests: single-call assertion on 401/403 (fails on main),
negative-cache reuse, 404 waterfall preserved, no .json() on 4xx.
Fixes#69905
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Review pass 2 (reuse reviewer HIGH): the step-3b probe-down fallback for
custom/local endpoints returns the same silent 256K default but only
logged at INFO - invisible by default, and it is the MORE common path
for small local models (the exact users the warning exists for).
Extract _warn_context_length_fallback() (deduped per model+base_url)
and call it from both fallback sites, per the fix-the-whole-bug-class
rule. Regression test drives the custom-endpoint path and fails without
the widening (mutation-checked).
Review follow-up:
- Warn once per (model, base_url) at the step-9 fallback via a module-level
dedup set (established _WARNED_* idiom). The fallback result is
deliberately never cached, so the un-deduped warning fired on every
resolution - e.g. once per gateway message via the session-hygiene path.
- Replace the three inline-mock pool-cleanup tests (which reproduced the
try/except block against a MagicMock and passed even with the production
code reverted) with a parametrized test that drives the real
BatchRunner.run() with a patched Pool; drop the CPython stdlib
signature change-detector test.
- Add a once-per-model warning regression test; clean up dead imports.
All tests verified to fail against pre-PR batch_runner.py/model_metadata.py
and pass with the fix (mutation check).
Salvage of #6629 by aaronlab (kshitijk4poor reworked against current main).
Three concerns from the original PR, reworked to address review feedback:
1. Context-length fallback diagnostic (agent/model_metadata.py):
get_model_context_length() silently returned 256K when all 9 detection
methods failed. Users with small-context models (8K, 32K) would get 256K
silently, causing hard-to-debug API context-length errors. Added a
warning log at the step 9 fallback with model name, base_url, and the
correct config override hint (model.context_length, not context_length).
The token-estimation ceiling-division fix from the original PR already
landed on main (5c2ecdec) with CJK handling — not duplicated here.
2. Fsync for batch trajectory writes (batch_runner.py):
Trajectory entries were written without flush/fsync, but the checkpoint
immediately marked them as completed. A crash between write and disk
sync would leave the checkpoint claiming completion with no trajectory
data on disk. Added flush() + os.fsync() before checkpoint update.
3. Pool cleanup on interruption (batch_runner.py):
Ctrl+C during pool.imap_unordered() relied on context manager cleanup
which can hang. Added explicit pool.terminate() + pool.join() for both
KeyboardInterrupt and Exception paths. The original PR used
pool.join(timeout=10) which is invalid — CPython's Pool.join() takes
no timeout parameter. Fixed to use pool.join() without arguments.
Tests:
- test_warning_emitted_on_fallback: verifies warning fires at step 9
- test_no_warning_when_cached: verifies no false warning when cache hits
- test_trajectory_entry_is_synced_to_disk: verifies os.fsync is called
- test_pool_terminate_called_on_exception: verifies cleanup on RuntimeError
- test_pool_terminate_called_on_keyboard_interrupt: verifies cleanup on Ctrl+C
- test_pool_join_called_without_timeout: verifies no timeout arg to join()
- test_real_pool_join_accepts_no_timeout: integration check on CPython API
Co-authored-by: Aaron Lab <aaronlab@users.noreply.github.com>
The reasoning_details field (OpenRouter/Anthropic thinking blocks +
opaque cryptographic signature blobs) inflates the rough token estimate
by ~4x. Providers do not bill these envelope bytes as prompt tokens.
In a measured Kimi K3 session, reasoning_details held 2,124K chars
vs 281K chars of actual thinking text. The estimator reported ~533K
tokens when real prompt_tokens was ~140K — triggering compression at
~27% of the configured threshold.
Fix: skip reasoning_details in both _estimate_message_chars and
_estimate_message_tokens_without_images, alongside the existing
_anthropic_content_blocks exclusion.
Fixes#73298
Review follow-up on #75102. The shadow substituted the sidecar whenever
the ``api_content`` key was merely PRESENT, but the wire only substitutes
a non-empty string sidecar on a user/assistant row (see
``turn_context.substitute_api_content``). For any other shape the sidecar
is popped and discarded while the clean ``content`` is sent -- so the
shadow dropped real content from the estimate and UNDERcounted, the
dangerous direction: compaction fires too late and the turn dies on a
hard context-length error instead of merely compressing early.
Gate the substitution on the same predicate, and cover the divergent
shapes (None, empty string, int, list, non-user/assistant role) with a
test that fails against the unconditional version.
Also rename the image test: it never carried a sidecar, so it was not
testing what its name claimed. It is a non-regression pin on the flat
per-image accounting that moved into ``_wire_message_shadow()``, and is
now named for that.
`api_content` is a SUBSTITUTE for `content`, not an addition to it.
`turn_context.substitute_api_content()` pops the sidecar and overwrites
`content` at every API-bound message-build site (the `api_messages` build
in `conversation_loop`, the max-iterations summary in
`chat_completion_helpers`, the chat-completions transport), so exactly one
of the two is ever sent to the provider.
The preflight estimator counted both, because both `_estimate_message_chars`
and `_estimate_message_tokens_without_images` walked every key of the
persisted dict with a single-entry denylist (`_anthropic_content_blocks`).
Any message whose sidecar differs from its clean stored content was counted
twice — exactly 2.00x on a 40KB sidecar.
The sidecar exists to keep the provider prompt-cache prefix byte-stable, so
it is written on precisely the long, cache-pinned messages where the
doubling hurts most. Because `estimate_messages_tokens_rough()` also feeds
the compaction threshold via `context_compressor` and `conversation_loop`,
the inflated estimate makes compression fire on phantom bytes.
Fix: substitute rather than sum, mirroring the wire. The two estimator
helpers had drifted into near-identical copies of the same shadow-building
loop, so this factors the shared logic into `_wire_message_shadow()` and
fixes the class once instead of patching one site and leaving the other.
Image accounting is unchanged: base64 payloads are still replaced with a
placeholder and charged at the flat `_count_image_tokens` rate, and the
`_multimodal` text_summary path is preserved.
Tests: three cases in `TestEstimateMessagesTokensRough` — sidecar equal to
content is counted once, a sidecar that DIFFERS is still counted (a lower
bound, so it fails if the field were dropped rather than substituted, which
would undercount the real request), and a sidecar cannot smuggle raw base64
past the flat image rate.
Verified on Linux (Python 3.11): 53 passed in
tests/agent/test_model_metadata.py, 57 passed with
tests/agent/test_context_breakdown.py, 656 passed / 3 skipped across the
compression/context/token/estimate/prune surface of tests/agent.
Mutation-tested: reverting the substitution fails the new equality test.
`scripts/check-windows-footguns.py` is not applicable — no file I/O,
process management, terminal handling, subprocesses, or signals.
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.
Four deferrals following the established truthy-skip / PEP 562
lazy-load patterns (PRs #22681/#22859 lineage). Rebased over #74194,
which independently landed the browser_tool half of this work — that
file is dropped here; the remaining four modules are untouched by it:
- tools/vision_tools.py: defer agent.auxiliary_client
(credential_pool -> hermes_cli.auth -> httpx -> rich, ~50 ms) to
first vision handler call. async_call_llm /
extract_content_or_reasoning stay patchable module attributes;
injected test mocks win over the loader.
- agent/model_metadata.py: defer 'requests' (+urllib3, ~27 ms of the
'import cli' waterfall) to the fetch functions. PEP 562 __getattr__
keeps patch('agent.model_metadata.requests.get') working.
- tools/browser_supervisor.py: websockets (~22 ms) imports on first
CDP connect; ClientConnection type under TYPE_CHECKING.
- cron/jobs.py: croniter (~15 ms) resolves on first cron-expression
use; HAS_CRONITER stays monkeypatchable (None = unprobed sentinel).
A/B vs current main incl. #74194 (median of 7, cold subprocess):
import cli 147 -> 132 ms (-10%)
import model_tools 244 -> 224 ms (-8%)
import run_agent 264 -> 244 ms (-8%)
Lazy-verify: importing the four modules no longer pulls requests /
croniter / websockets into sys.modules. 369 targeted tests green
post-rebase.
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.
Anthropic released Claude Opus 5 (+ -fast variant) — both are live on
OpenRouter and the Nous Portal /models endpoint (verified against both
live APIs). Opus 4.8 entries are kept.
- hermes_cli/models.py: opus-5 + opus-5-fast in OPENROUTER_MODELS;
opus-5 in _PROVIDER_MODELS[nous] (Portal serves both, curated list
carries the base model like the rest of the Nous Anthropic block).
Ordering: below fable-5 flagship, above opus-4.8.
- agent/model_metadata.py: claude-opus-5 -> 1M context (matches live
OpenRouter metadata).
- agent/reasoning_timeouts.py: claude-opus-5 -> 240s stale-timeout
floor (same as the opus-4.x thinking family).
- website/static/api/model-catalog.json: regenerated via
scripts/build_model_catalog.py.
Both providers bill via official_models_api (live pricing), so no
_OFFICIAL_DOCS_PRICING snapshot entry is needed for these routes.
The salvaged estimator ran a per-character Python loop on every
estimate_tokens_rough() call — a ~28,000,000x slowdown vs (len+3)//4 on a
1MB ASCII tool output (measured ~3.0s per call). Gate it:
- str.isascii() O(1) fast path keeps pure-ASCII text bit-identical to the
classic (len+3)//4 rule at ~1.3x baseline cost (0.23us vs 0.17us per
1MB call).
- Non-ASCII text counts dense CJK chars via a compiled character-class
regex in C (len(text) - len(re.sub(''))): ~352ms/1MB hangul vs ~2.1s
for the per-char loop.
- Non-ASCII-but-non-CJK text (accents, Cyrillic, emoji) keeps the classic
rule.
Also: parity tests against the per-char reference implementation, and
updated two stale expectations that encoded the old behavior (CJK now
counted ~1 token/char; short string content now ceil-divided instead of
floored to 0). The continuity test now detects merged-into-tail summaries
via _is_context_summary_content.
The Codex backend returns the per-account model catalog only when the
ChatGPT-Account-Id header is present. Without it, GET /backend-api/codex/models
responds 200 OK with {"models":[]} and the picker silently degrades to the
hardcoded fallback list — which is stale or wrong for the active plan
(no GPT-5.6 family, wrong context windows).
This was the upstream bug behind slow first responses and HTTP 520/120s SSE
hangs: Hermes was sending invalid slugs because the probe never saw them in
the catalog, and Codex's request builder also depends on the same JWT claim
that's now being threaded through both probe paths.
Fixes the probe-side paths in hermes_cli/codex_models.py and
agent/model_metadata.py by extracting chatgpt_account_id from the OAuth JWT
(mirroring the request-side logic already in auxiliary_client.py) and sending
it as a header.
Verified live:
- _fetch_models_from_api now returns the 10-model catalog (gpt-5.6-sol,
gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.4, gpt-5.4-mini,
gpt-5.3-codex-spark, 3x -pro variants) instead of [].
- _fetch_codex_oauth_context_lengths resolves all 8 account models to 272K
context (matches direct API probes of the same account).
- end-to-end: hermes chat -m gpt-5.6-sol -q 'Reply with one word: pong'
returns 'pong' cleanly via the openai-codex route.
Same class of bug as PR #64760.
Follow-up widening for salvaged PRs #67115, #67685, #67620:
- _PROVIDER_MODELS: add kimi-k3 atop kimi-coding / moonshot / opencode-go
curated lists (kimi-coding-cn covered by cherry-picked #67620)
- setup.py _DEFAULT_PROVIDER_MODELS: kimi-k3 for kimi-coding(-cn) + opencode-go
- model_metadata: align DEFAULT_CONTEXT_LENGTHS kimi-k3 entry to 1,048,576
(matches endpoint-scoped override, models.dev, and OpenRouter live metadata)
- anthropic_adapter: classify the bare Coding Plan slug 'k3' (and k3.x/k3-*)
as Kimi family so adaptive thinking applies on proxied endpoints
- moonshot_schema: is_moonshot_model matches bare 'k3' so tool-schema
sanitization runs on the chat-completions path
- contributor mappings for githubespresso407, datachainsystems, Punyko8
Tests: 582 passed across 11 targeted files; hermetic E2E verifies picker
order (kimi-k3 first), no dupes, and 1M context resolution.
Kimi K3 ships with a 1M-token context window (verified against
platform.kimi.ai/docs/overview) but was falling through to the generic
'kimi': 262144 catch-all. Added 'kimi-k3': 1_000_000 before the catch-all
so longest-key-first substring matching resolves K3 to 1M while older
Kimi models still hit the 256K default.
Added matching test_kimi_k3_context_1m test covering native,
vendor-prefixed (kimi/, moonshotai/), and older model fallback.
Kimi Coding serves K3 under the bare slug 'k3', but users can also
configure or select the public-facing aliases 'kimi-k3' and
'kimi-k3-cot'. The endpoint-scoped 1M context window was only keyed
on the bare 'k3' slug, so selecting 'kimi-k3' fell through to the
generic 'kimi' catch-all (262k).
Extend the guard in _endpoint_scoped_context_length to also recognize
'kimi-k3' and 'kimi-k3-cot', while keeping the endpoint check that
limits the 1M value to https://api.kimi.com/coding (legacy Moonshot
endpoints still fall back to 262k). Update the existing test to cover
all three aliases.
Fixes: context window limited to 262k when using kimi-k3 via kimi-coding.
- The #44861 stale-cache guard invalidated any cached value that differed
from the static table, which would have discarded legitimate
probe-derived windows larger than the table. Treat the table as a
FLOOR: only drop under-reporting cache entries.
- Update probe test fixtures that predated the 4.6+ 1M table flip
(opus-4-6 fallback expectations 200K -> 1M).
Bedrock models resolved their context window from a hardcoded table
(BEDROCK_CONTEXT_LENGTHS) keyed by longest-substring match. AWS ships
new model versions faster than the table tracks, so a new model like
claude-opus-4-8 (1M-token window) silently matched the older
"anthropic.claude-opus-4" entry and got capped at 200K — wasting 80%
of the available context.
Bedrock exposes the real window nowhere in metadata: get-foundation-model
omits it, Converse usage metrics omit it, CountTokens is unsupported on
several models. The only authoritative source is the ValidationException
raised when a prompt exceeds the window:
"prompt is too long: 1300032 tokens > 1000000 maximum"
Length validation runs before inference, so an oversized request is
rejected immediately and cheaply (no tokens generated, no input
processed). This adds probe_bedrock_context_length(): pad a request just
past a tier, parse the reported maximum, return it. get_bedrock_context_length()
now probes first and falls back to the static table only when the probe
can't run (missing creds, network error, unparseable error). The static
table stays as a safety net.
get_model_context_length() caches the probe result per model+region, so
the network cost is paid once, not every turn. probe=False / empty region
disables probing for offline/display paths — backward compatible with the
single-arg callers.
Verified E2E against live Bedrock (eu-central-1): claude-opus-4-8 resolves
to 1000000. Unit tests cover error parsing, unparseable errors, missing
client, probe-beats-table, and table fallback.
BEDROCK_CONTEXT_LENGTHS was missing entries for current 1M-context Claude
models, and the resolution path in get_model_context_length() short-circuits
to that table (step 1b) before DEFAULT_CONTEXT_LENGTHS is ever consulted, so
the catalog's correct values could never apply on Bedrock:
- claude-fable-5 (no entry at all) fell through to
BEDROCK_DEFAULT_CONTEXT_LENGTH and reported 128K for a 1M model.
- opus-4-7 / opus-4-8 substring-matched the generic 'anthropic.claude-opus-4'
key and reported 200K.
- opus-4-6 / sonnet-4-6 had explicit 200K entries predating their 1M windows.
The practical symptom: the agent compresses context prematurely (at ~128K or
~200K of a 1M window) on every Bedrock-hosted current Claude model.
Fixing the table alone is not enough for existing installs: a previously
persisted 128K/200K value in the context-length cache wins at step 1 and
masks the corrected table forever. Step 1 now reconciles Bedrock-context
cache hits against the static table (the table is authoritative for Bedrock
— there is no live probe to reconcile against), invalidating stale entries
so existing users converge to the right window without manual cache surgery.
Tests cover the new table entries (incl. inference-profile and versioned ID
forms), the 128K-default regression for Fable, the stale-cache invalidation
path, and that pre-4.6 models keep their 200K entries.
Follow-up to the salvaged #66083/#42792 commits:
- alibaba (Qwen Cloud coding-intl) gets qwen3.7-plus too — same platform
allowlist as alibaba-coding-plan (issue #44662 comment by @coder-movers)
- qwen3-max substring context entry (262144) so the newly-listed
qwen3-max-2026-01-23 snapshot doesn't fall to the generic 131072 qwen
fallback
Add qwen3.7-plus to DEFAULT_CONTEXT_LENGTHS with 1M context window.
Without this entry, the model falls back to the generic 'qwen' entry
(128K), causing premature context compression at 50% (64K tokens)
instead of the correct 500K threshold.
Official docs: https://help.aliyun.com/zh/model-studio/developer-reference/
Pin the Upstage default to the concrete solar-pro3 instead of the
solar-pro rolling alias:
- plugin fallback_models is now ("solar-pro3",); entry [0] is the setup default
- drop the "solar-pro" context-window fallback entry (solar-pro3 covers it)
- update the reasoning default-on docstring and profile tests accordingly
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
kshitij
luoxiao6645
sasquatch9818
fangliquan
Omar Baradei
whirmill
Teknium
Julientalbot
rob-maron
Oliver Mee
Jordan
rlaope
pierrenode
AlexFucuson9
Josh Tsai
JonthanaHanh
Israel Lot
Gille
atakan g
wjq990112
miniadmin
TARS
sbe27
datachainsystems
githubespresso407
kubolko
Avi Fenesh
Ariel Bravy
asscan
amanning3390
Changhyun Min