The codex app-server no-usage path (_record_codex_app_server_usage) calls
queue_token_counts(), which spawns the daemon session-db-token-writer
thread. test_codex_turn_persists_each_message_exactly_once tore down with
a bare shutil.rmtree(tmp) while that writer could still be mid-commit,
racing WAL/-shm file re-creation against rmtree's unlink pass — os.rmdir
then fails with ENOTEMPTY. Seen as a CI FLAKY retry in run 31681231786
(slice 6/12). db.close() drains the queue and joins the writer, making
teardown deterministic.
Address rewinds/edits via SQLite messages.id (truncate_before_row_id)
instead of shifting user ordinals. Resolve against in-memory stamps,
then durable session history when live turns drop _row_id; refuse
unknown durable targets with 4018 (no ordinal fallback) and 4030 on
ordinal/row_id mismatch. Stamp _row_id on insert, load row ids on
resume paths, send rowId from Desktop, filter renderer-synthetic ids,
and stop silently resending failed targeted edits without truncation.
Add production-shaped SessionDB tests for resolve and fail-closed paths.
Fixes#82959
Adds a 'council' synthesis style to MoA (per preset via synthesis_style,
one-shot via the new /council command on CLI + gateway). Reference models
answer independently; the aggregator chairs the deliberation and produces
a user-facing report of consensus, per-model disagreements (with the
differing assumptions behind them), unique contributions, and a
recommendation with an explicit confidence level.
Inspired by Perplexity's Model Council rollout to Perplexity Computer
(changelog 08/04/26): pick a board of 2-8 models, run them independently,
synthesize where they agree/disagree and what each uniquely surfaces.
Port from openai/codex#37527: Terminate timed-out hook process trees.
A shell hook that forked helpers (scanners, watchers, "cmd &") and then hit
its timeout left those descendants running forever — subprocess.run() only
kills the direct child. Worse, descendants holding the inherited pipe write
ends could stall run()'s post-kill communicate() drain.
- agent/shell_hooks.py _spawn(): spawn hooks in their own process group on
POSIX (process_group=0, Python >=3.11); on timeout/error, reap the whole
tree via the shared kill_process_tree() helper, then drain bounded (1s).
Hooks that complete in time keep their descendants, so intentionally
detached helpers survive successful runs (mirrors codex semantics).
- hermes_cli/_subprocess_compat.py: rename _kill_git_process_tree ->
kill_process_tree (it was never git-specific; taskkill /T /F on Windows,
ownership-gated os.killpg on POSIX). Backward-compat alias retained.
- tests/agent/test_shell_hooks_tree_kill.py: real-subprocess regression
tests (descendant killed on timeout, preserved on success, own-group
spawn, fast-path contract, fail-open). Sabotage-verified: reverting the
process_group spawn fails exactly the two new behavior tests.
Gap proven live on main first: a forking hook timed out at 2s and its
descendant survived; same probe against this branch shows it reaped.
CI caught the file hanging AFTER '6 passed in 4.32s' until the runner's
300s SIGKILL. Two defects, same class the PR fixes:
1. The executor-refused (interpreter shutdown) fallback ran the native
call UNBOUNDED on the calling thread — a wedged pipeline would block
process exit forever. Now runs on a bounded daemon exit-thread with
the same timeout/abandon semantics as the executor lane.
2. The wedge tests left daemon workers parked on Event.wait() and live
sessions registered on the atexit shutdown hook; exit re-ran the
wedged pops (bounded, 10s each) and the per-file runner timed out.
Autouse teardown now releases every wedge and drains each runtime.
Canonical runner: 4.4s (was 300s file-timeout kill). Bare pytest was a
false green for this class — it exits before atexit replay cost shows.
The NeMo Relay native binding's scope.pop/push are synchronous and
unbounded ('returns after the scope is closed successfully'). When the
native pipeline cannot make progress, the session coordinator's turn and
session finalization block forever inside run_conversation: delegated
children finish their turns but never return, and delegation batches die
on the stall watchdog. Proven live 2026-08-10 on the staging fleet — a
falsification probe (plugin disabled, identical config) completed the
same delegation batch that wedged with the plugin active.
Bound every scope lifecycle operation that gates turn/session completion
(session push, turn push, turn pop, logical-LLM pops, session pop,
subscriber flush) by running the native call on a shared
DaemonThreadPoolExecutor and honoring a 10s result timeout. On breach a
TimeoutError propagates into each call site's existing exception
handling — warn, retain the unclosed-prefix diagnostics, continue — so
the worst case is one lost span, never a blocked agent. timeout=None
preserves byte-identical synchronous behavior for all other callers, and
interpreter-shutdown paths fall back to the synchronous call so the
atexit flush still exports.
Observability must never block the product.
Closes#26193
Adds ContextReferenceProvider ABC so plugins can register custom
@-prefixes (e.g. @issue:ENG-123) with autocomplete and expansion.
Plugin output flows through existing token-limit guards. Zero
breaking changes.
Salvage the plugin-owned static prompt idea from PR #51589 into the constrained #64167 contract: stable IDs, deterministic placement, bounded fail-open rendering, and full-prompt resume recovery without new session columns.
Co-authored-by: Topher Ross <biz@topherross.com>
Wire an optional `task=<key>` kwarg through the PluginLlm facade so a
plugin can route an LLM call through an auxiliary model slot it
registered via `ctx.register_auxiliary_task`. Registration already
existed; this adds the missing consumption half. Closes#44673.
Sub-issue 08/14 of the plugin-interface expansion tracking issue #64182.
- New optional `task:` kwarg on complete/acomplete/complete_structured/
acomplete_structured. Unset or "auto" keeps today's main-model path
byte-for-byte (task=None reaches call_llm exactly as before), so no
prompt-cache or default-behavior change.
- A set task resolves provider/model through `auxiliary.<task>` via the
existing auxiliary_client path, identical to built-in aux tasks.
- Trust gate (per the round-2 design correction): a plugin may only pass
a key it registered itself; a built-in key additionally requires
`plugins.entries.<id>.llm.allow_task_override: true`. A foreign or
unknown key is rejected with a PluginLlmTrustError and a logged warning
naming the offending plugin and key -- fail loud, NOT a silent fallback
to auto (which would mask misconfiguration and could route to the main
model the user steered elsewhere).
- The plugin_llm audit dict and audit-log line gain a `task` field.
- register_auxiliary_task now stores the plugin's canonical id
(`key or name`, the same id ctx.llm is bound to) as the slot owner, so
the trust gate matches ownership even when a manifest sets a distinct
key. For the common no-key case this equals the name (unchanged).
Tests (tests/agent/test_plugin_llm_task_routing.py, 24): _check_task
resolution incl. own/foreign/unknown/built-in-gated keys and loud
rejection; end-to-end routing sync+async+structured; production-path
forwarding into call_llm/async_call_llm (covers the task=None->task line);
and ownership resolution against the real plugin registry incl. the
name/key reconciliation.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013b1XyXitAxV7phGmKWigJX
Add regressions for the Discord-shaped applyPromptTemplate 400 that embeds
"No user query found", bare no-user-query on a large session, and the genuine
llama.cpp unable-to-generate-parser grammar path that must stay recoverable.
* fix(models_dev): map meta-ai provider to models.dev 'meta' id
Muse Spark models (muse-spark-1.1/1.2/-contributor) are served via the Meta
Model API and reverse-map from api.meta.ai to the Hermes provider id 'meta-ai'.
models.dev keys the same models under the provider id 'meta'.
lookup_models_dev_context() / _get_provider_models() resolve the models.dev id
strictly via PROVIDER_TO_MODELS_DEV.get(provider) (no raw-id fallback, unlike
get_model_info()), so an unmapped 'meta-ai' missed entirely and context fell
back to the generic 256K default instead of the true ~1M window. Add the
meta-ai->meta mapping (plus a defensive meta->meta) so context and pricing
resolve from models.dev: 1.1=1,000,000; 1.2 & -contributor=1,048,576.
* add contributor email
---------
Co-authored-by: Beto de Paola <betodepaola@meta.com>
Follow-up fixes on top of the salvaged #83678 commit:
1. Hoist the MiniMax-M3 marker exclusion ABOVE the native-Anthropic
early return. provider="anthropic" pointed at a MiniMax /anthropic
proxy is a supported override (_anthropic_base_url_override_ok), and
the is_native_anthropic branch matched on provider alone — returning
(True, True) before the M3 exclusion was reached. Two regression
tests pin the proxy route (M3 off, M2.7 still on).
2. Reuse the existing _model_name_suggests_minimax_m3() helper from
agent/model_metadata.py instead of a second inline substring copy.
3. Drop the debug kwarg on normalize_usage() — it had zero production
callers and duplicated standard logging level gating. The
cache-observability line is now a plain logger.debug scoped to
MiniMax providers on the Anthropic wire only, so the "+128 floor"
note can no longer appear for native Anthropic where it is false.
Tests updated accordingly (MiniMax logs, native Anthropic does not).
MiniMax-M3 ships server-side automatic prefix caching on the
Anthropic-compatible endpoint (content-keyed, no marker needed —
see platform.minimax.io/docs/api-reference/text-prompt-caching).
cache_control markers are NOT on its explicit-cache support list
(which covers only M2.7/M2.5/M2.1/M2).
Emitting markers on M3:
- wasted serialization overhead
- risked perturbing the server-side prefix hash
- gave users a false sense of explicit-cache savings (the
cache_read_input_tokens field carries a +128 constant floor
and cache_creation_input_tokens is always 0 for M3)
Also add an opt-in debug=True parameter to normalize_usage() that
emits a debug-level log line carrying the observable cache fields.
This is the only reliable cache signal for M3 — off by default,
debug-level, scoped to the anthropic_messages wire, so production
callers see no impact.
Pin both changes with 8 new tests:
- 4 M3 tests covering provider, host, and custom-provider paths
- 1 regression guard ensuring M2.x caching is unaffected
- 3 observability tests (off-by-default, on-with-M3, on-with-Claude)
Verified end-to-end against api.minimaxi.com/anthropic/v1/messages
with MiniMax-M3[1m]: identical system prompt hit-rate with and
without markers; cache_read field is unreliable (128 floor),
input_tokens drop (8467 -> 1) is the real hit signal.
* fix: make verify_on_stop opt-in everywhere (default False, not auto)
The verify-on-stop nudge was already judged more noise than signal: the
v31 migration flips existing installs off, the v32 migration catches the
baked-in literal-true population, and the docs tell users to 'treat off
as the effective default and opt in explicitly'. But DEFAULT_CONFIG still
shipped the "auto" sentinel, so exactly one population kept getting the
nudges: fresh installs (and any config missing the key), where "auto"
resolves ON for CLI/TUI/desktop surfaces. Live symptom: repeated
'[System: You edited code ... run verification]' interruptions the user
never asked for and had to hunt down in source to disable.
- DEFAULT_CONFIG: agent.verify_on_stop "auto" -> False (opt-in).
- verify_on_stop_enabled(): missing/unrecognized value now falls back
OFF instead of surface-aware; explicit "auto" still selects the
legacy surface-aware behavior, explicit bools unchanged, and the
HERMES_VERIFY_ON_STOP env override is untouched.
- No migration needed: v31/v32 already normalized existing installs,
and this only changes the merged default for configs without the key.
- Docs updated; default-path E2E test now asserts OFF, plus a new
missing-value regression test. Also added the standard win32 skip
marker to the symlink-based temp-dir test (pre-existing Windows
failure, same class as tests/cron/test_cron_script.py).
* test: update config goldens — verify_on_stop=False is now stripped as default
With the DEFAULT_CONFIG flip to False, the migration-write invariant
(_persist_migration / save_config strip_defaults) no longer materialises
verify_on_stop: false to disk unless the user explicitly set the key:
- V20 floor fixture (agent: {} on disk): v31's write is stripped —
agent stays {} and load_config() supplies False at read time.
- V12 floor fixture (explicit verify_on_stop: true on disk): the key is
a user-set path, so the v32 flip stays materialised as false.
- Partial-write and _persist_migration regressions now assert the key is
absent from disk and (for the merge case) that the merged view still
resolves False.
Behavior verified with a one-shot migrate_config run against both
fixture shapes.
The PR added APIConnectionError handling to the main request and
iteration try blocks but missed the finalization drain loop (line ~1492).
That site catches httpx transport errors to preserve an already-completed,
already-billed response when the drain iterator fails. Without the
APIConnectionError handler, an SDK-wrapped transport error during drain
would propagate uncaught and discard the completed response.
Also strengthens the test's no-payload-leak assertion to check the full
request body and URL are absent from the log message, not just the
literal string 'payload'.
After a partial update (stash restore overwriting providers/base.py with
an older version), the NousProfile singleton was instantiated from a
ProviderProfile class that predates the supports_prompt_cache_key field
(added in f4fb23f3d). Accessing profile.supports_prompt_cache_key raised
AttributeError, crashing every API call with:
'NousProfile' object has no attribute 'supports_prompt_cache_key'
Use getattr(profile, 'supports_prompt_cache_key', False) so a stale
profile degrades to 'no prompt cache key' instead of crashing.
many tests patched sys.platform or a module's _IS_WINDOWS flag, then
ran on linux ci. the patch selects the branch under test, but the host
does not have the behavior the branch exists for. the test proves the
patch, not the platform. some gated assertions never ran on any host.
this commit adds three markers: linux_only, macos_only, windows_only.
a conftest hook skips a marked test on the other hosts, with a clear
reason. no test fakes a host now. two documented fakes remain
(android/termux, freebsd) because no ci runner exists for them.
each fake site got one of four treatments:
- gate it: the real host supplies the platform; mocks cover real
dependencies only, never host identity
- patch the module's own probe when the subject is the probe's consumer
- assert against the real host when the fake stood in for any non-x host
- delete the patch when it set the value the host already has
bare skipif(sys.platform != ...) guards became markers too. the lane
model skips these on linux and never imports them on windows, so they
ran on no host. platform parametrize tables are now one marked test
per os.
running on real hosts found real errors: a chrome-sandbox failure in
test_gui_command that main hides, and two windows failures fixed here.
the agents.md testing section now documents the policy.
Fix: _LENGTH_CONTINUATION_DROPPED_TOOLS_PREFIX ended with '(' but
_get_continuation_prompt still had f'({tool_list})', producing
'((write_file)' instead of '(write_file)'. Removed the '(' from
the prefix constant — the parenthesis belongs in the interpolation.
Widened: promoted the empty-response nudge (line 6993,
'You just executed tool calls but returned an empty response...')
to _EMPTY_TOOL_RESPONSE_NUDGE constant and added it to the
classifier's recognition set. Same bug class — its
_empty_recovery_synthetic metadata flag doesn't survive SessionDB
projection either.
Test: added parametrize case for the empty-response nudge (7→8 cases).
E2E: verified byte-for-byte string equivalence for all nudge constants.
aed114a69 taught _is_synthetic_compression_user_turn to recognize the
max-iteration nudge as ephemeral runtime scaffolding rather than a human
turn, since its role="user" metadata flag doesn't survive SessionDB
projection and a crash/interrupt mid-turn can persist it durably — becoming
the compaction anchor / auto-focus topic in place of the real task.
conversation_loop.py's retry loop appends several more role="user" rows
with the exact same "ephemeral, metadata-tag-only" shape, none of them
recognized by the classifier:
- The three _get_continuation_prompt variants (length-continuation nudge,
tagged _length_continuation_nudge) — two fixed strings plus a third that
interpolates the dropped-tool-call list.
- _CODEX_INCOMPLETE_NUDGE (codex/responses reasoning-only retry).
- The codex ack-continuation nudge (acknowledgment-only reply re-prompt).
- The dropped-tool-call nudge (tagged _dropped_toolcall_nudge) — persisted
across up to 3 consecutive retries before the finalization pop-loop
strips it; an interrupt/crash before that pop can persist it same as the
max-iteration case.
Promote the previously-inline nudge strings to named module-level constants
in conversation_loop.py (single source of truth for both construction and
recognition), then extend the classifier to recognize all of them — exact
match for the five fixed-content nudges, a stable-prefix check for the
dropped-tool-call continuation variant (its tool list is interpolated so it
can't be exact-matched, same treatment TODO_INJECTION_HEADER already gets).
Imported lazily inside the classifier to avoid a module-load-order cycle —
conversation_loop.py already imports FROM context_compressor.py at call
time for the same reason.
Follow-ups from review of #82049:
- extract append_user_instruction() into agent/skill_commands so the
stable-prefix construction cannot drift between the skill and cron
builders (the registered prefix must stay a byte-prefix of the built
message); cron no longer imports the private _SINGLE_SKILL_INSTRUCTION
- add the startswith guard to the skill builder registration site,
matching the stronger cron guard
- rename _MAX_BYTES to _MAX_CHARS (sum(map(len, ...)) counts characters,
not bytes) and correct the comment
- collapse find_stable_prefix's two-lock dance into a single critical
section (scan is <=32 short-circuiting startswith calls, measured
2-4us; drops the snapshot copy and the TOCTOU re-check)
- document the split-shape lifetime (marked-endpoint window) in the
module docstring
- add a contract test for the helper's byte-prefix invariant
(mutation-checked)
Follow-up review of the builder-declared cache boundary (#81867) found three
ways the split could silently stop paying off, or keep paying more than it
should, on a long-lived gateway process.
Flattening no longer consults the registry. `strip_anthropic_cache_control`
matched the decorated split by looking the first block up in the prefix
registry, so a mid-turn failover that re-decorates a request built many
messages earlier (#72626) would fail to flatten once _MAX_ENTRIES newer
scaffolds had been registered in between, and would hand the next provider
the two-part shape instead of the canonical string. The split is now matched
by its shape: a marker on the *first* part of a user message is something no
other decoration produces (list content otherwise gets its marker on the last
part, and the two-part [static, volatile] split is role-gated to system), so
the ""-join stays provably byte-exact without any process state. This drops
`is_registered_stable_prefix` and one lock acquisition per stripped message.
Lookups now refresh LRU position. A scaffold fired every minute by cron could
be evicted by a burst of one-off skill invocations while still being the
hottest prefix in the process, silently reverting it to whole-message caching.
Registration now also evicts by total retained bytes (4 MiB). Entries hold
whole expanded skill bodies, so a 32-entry cap alone does not bound memory.
The newest entry is always kept, so a single oversized scaffold still gets a
boundary instead of disabling the split.
Tests: eviction-then-failover round-trip, LRU refresh on hit, byte-cap
eviction, and oversized-single-entry survival.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Webhook/cron skill invocations concatenate a large static scaffold
(activation note + expanded skill body) with a small volatile tail
(ticket payload, timestamps) into one user string, and the Anthropic
cache planner marked that whole string as a single atomic block — so a
few changed tail bytes forced a full cache rewrite on every invocation.
Instead of re-parsing scaffold marker strings out of the message at
request time (fragile when a payload or skill body quotes the marker),
the builders now register the exact stable-prefix bytes in a small
process-local LRU registry at construction time. The cache planner
splits a registered user string into [marked stable prefix, unmarked
volatile tail] request-locally; canonical session history stays a plain
string, and the failover stripper flattens the split back byte-exactly
via an O(1) registry lookup. Unregistered messages keep the existing
whole-message policy.
Covers the single-skill builder (webhook + slash command + TUI) and the
cron job prompt assembler (multi-skill, bundles, skipped-skill notice),
with registration guarded against injection-scanner sanitization.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Folds the model-switch fix in with the untitled retry. They answer
different halves and each is wrong alone: counting alone left a session
that merely opened with machinery nameless forever, because nothing
reconsidered it, and the stored title alone would never title at all on a
store too old to report one. Skip only when both agree — past the opening
turn, and already named.
Counting a turn now judges a multimodal one on its text, so "here's a
screenshot, fix the login" counts as the question it is rather than
reading as machinery and undercounting the conversation.
Co-authored-by: yy28 <yy28@vip.sina.com>
Switching models before sending the first real message titled the session
"[System: The active model for this chat has…" instead of the user's actual
question.
`_append_model_switch_marker` persists its notice with `role="user"` because
strict OpenAI-compatible providers reject a system message that is not first
(#48338). Titling had no way to tell that apart from a genuine opening turn,
which caused two distinct failures:
1. `_MACHINE_PREFIXES` did not cover the marker. Its `[System: ` prefix
matches none of `[CONTEXT COMPACTION`, `[Runtime note:`, or `[SYSTEM]`
(different case, no closing bracket), so `is_titleable_user_message()`
returned True and the marker was formatted into the title.
2. `maybe_auto_title()` counted the marker as a user message. With the marker
present, the first real question arrived at `user_msg_count == 2` and the
`> 1` guard returned early, so the session was never titled at all and its
`title` column stayed NULL. Fixing only (1) would therefore have traded a
wrong title for a permanently missing one.
Add the marker prefix to `_MACHINE_PREFIXES` (kept in sync with
`tui_gateway.server._MODEL_SWITCH_MARKER_PREFIX`) and count only titleable
user messages when detecting the opening turn.
The guard stays narrow: ordinary user text that happens to start with
"[System:" still titles normally.
Adds 6 regression tests, verified to fail without the fix.
Two lookalike gaps found auditing the titler.
_MACHINE_PREFIXES missed the compressor's legacy summary opener and the
"[System note:" injections, so a compacted or resumed session could be
named after the note that carried it. Take the summary prefix from the
compressor that emits it rather than keeping a fourth local copy.
The fast-model exclude list covered embedders but not the other non-chat
siblings a provider names after its chat model — "gpt-4o-mini-tts"
satisfies the "-mini" rung and cannot answer a prompt.
An opener is not always titleable — an image with no caption, a compaction
handoff, a bare slash command — and those sessions stayed unnamed for
life, because the guard that stops re-titling a named session also stopped
the nameless one from ever asking again. Let a later turn name a session
that still has no title.
The derived title also ran the collision dedupe inline on the turn.
It is a slice of the user's own words, so it collides constantly — people
open sessions with "hi" — and resolving "hi #47" is a widening scan on the
critical path for a name the model replaces a second later. Decline it
there and let the background stage, which can afford the scan, pick it up.
The fast-model picker reads /v1/models to find the small model a provider
currently serves, and it asked anonymously. Most of those endpoints need a
key, so the fetch 401'd and the empty result read as "this provider has no
small model" — the picker fell back to its curated list and never noticed.
Worse, a failed fetch cached its empty result forever, so one bad moment
during startup disabled live model discovery for the life of the process,
and the processes that read this run for weeks. Give the failure an expiry
and pass the provider's credentials.
The bare family rungs (-mini, -flash, haiku) also picked whichever id
sorted first, which is the oldest generation a provider still serves:
gpt-3.5-mini over gpt-5.4-mini, claude-3-haiku over claude-haiku-4.5.
Compare the digit runs as numbers so the rung meant to keep us current
does.
The turn prologue titles every session, and it is shared by every agent —
including the ones no person is reading. A cron job already names its own
session after the job in its finally block, so the titler spent a side-LLM
call per fire to write the delivery scaffolding over it for the length of
the run. A delegated child's session is hidden from every picker, so a
batch at max_concurrent_children paid N title calls for N names nobody
opens.
Both are the same class of run that already sets skip_memory to stay off
the auxiliary path, so keep the titler off it too.
_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
The native Relay pipeline binds its Futures to the event loop that
entered run_in_session_async. While a managed tool callback executes,
that loop is blocked until the callback returns — so a nested managed
relay call made from inside the callback (vision_analyze's auxiliary
LLM call on a worker-thread loop) awaits a Future that can never
complete: 'RuntimeError: Future attached to a different loop', or a
deadlock, plus 'Event loop is closed' at shutdown when the orphaned
future completes late. (#77244)
Fix: managed_callback_guard, a ContextVar depth marker set around every
Hermes callback the relay adapters hand to the native pipeline
(relay_tools.execute invoke, relay_llm execute/execute_async invoke,
ManagedLlmStream run_callback). resolve_execution_context returns the
no-relay triple while the marker is set, so nested calls run unmanaged.
The marker propagates through contextvars.copy_context() into the
worker threads tools use for their internal async work.
Top-level turn LLM calls and tool wraps stay fully managed — verified
live: vision_analyze works under active shared metrics while the main
turn still records managed llm.execute events.
Alternative fixes considered and rejected: removing
retain_managed_execution (kills the shared-metrics managed pipeline)
and gating on main-thread identity (managed tool wraps legitimately
run on the run_agent thread, so that gate disables relay everywhere).
The Anthropic SDK's streaming accumulator builds ParsedMessage snapshots
whose ParsedTextBlock content doesn't match the generic union pydantic
expects, so model_dump() on stream events (message_stop) emits
PydanticSerializationUnexpectedValue UserWarnings straight into the
user's CLI output mid-response.
Pass warnings=False at every helper that dumps arbitrary SDK models
(relay_llm/_jsonable, relay_tools/_jsonable, anthropic_adapter
_to_plain_data, run_agent _hook_jsonable, chat_completion_helpers
extra_content/reasoning_details sites, chat_completions transport),
with a TypeError fallback for duck-typed model_dump implementations.
Adds regression tests including a precondition test that proves the
fixture still trips the warning without suppression.
Per-turn .env adoption could rewrite agent.api_key while leaving
_credential_pool_entry_id on a previously rotated fallback. The next 429
then marked the healthy fallback exhausted via credential_id precedence
(#79156).
- Sync pool entry id after a successful env credential refresh
- First look does not stomp a pool-rotated key with the env primary
- mark_exhausted_and_rotate prefers api_key_hint when it disagrees with
credential_id
Fixes#79156
Generic thinking fields (reasoning / reasoning_content + the
reasoning_details text charge) are replayed for at most the NEWEST
assistant turn on every transport: Anthropic strips all-but-newest at
convert time, Bedrock Converse never replays thinking, and strict
chat-completions providers reject or one-space-pad the field. The tail
budget walks charged them on every message anyway, spending 19-24% of
the budget (per the issue's 1,025-message measurement) on bytes that
provably never reach the wire — so the tail cut landed early and each
compaction discarded more real transcript than configured.
_estimate_msg_budget_tokens now partitions the replay keys:
* _ALWAYS_REPLAYED_BUDGET_KEYS (codex_reasoning_items,
codex_message_items) — charged unconditionally. These ride the wire
on every retained turn (#55572), and codex_reasoning_items now also
carries native server-side compaction checkpoints (#81747).
* _NEWEST_TURN_ONLY_BUDGET_KEYS (reasoning, reasoning_content) + the
reasoning_details text charge — charged only for the newest assistant
turn via charge_stale_thinking, resolved by the three budget walks
(tail cut, raw-budget re-walk, proactive-prune boundary).
Default stays the conservative full charge for callers without
turn-position context. A partition invariant test pins that any future
_REPLAY_BUDGET_KEYS entry must be classified into exactly one class.
Direction credit: #73669 (@x7peeps) and #73730 (@webtecnica) both
attacked this; the keep_open reviews asked for provider/API-mode-aware
accounting that keeps Codex carriers charged — this implements that
shape.
Titling fired on the first response, so a session sat unnamed for the whole
opening turn - p50 151s, p90 1212s across real sessions, because a turn is
tool calls, not one round-trip. A turn that failed or was interrupted never
got a title at all. Four surfaces each carried their own copy of the call.
Move it into the shared turn prologue and split it in two: a deterministic
title derived from the user's opening message, written inline before the
model runs, then one small-model call that upgrades it. The response is
constrained to a JSON object so there is no preamble to strip, and control
wrappers are stripped rather than refused, so a slash command titles as
what the user asked for instead of the command itself.
Titling ran on the user's main chat model, so a five-word title was billed
to a frontier reasoning model and inherited its latency. Pinning a cheap
model id instead just moves the problem: the hardcoded default was already
dead upstream and every call paid a 404 before the retry net caught it.
Match model FAMILIES against the provider's live /v1/models catalog,
preferring rolling '-latest' aliases where a provider publishes them, and
order the families by measured latency. Nothing to bump when a provider
ships a new mini/flash/haiku. Opt-in per task, so compression, vision, and
search keep 'auto means my chat model'.
Teknium
StanleyStetson
Daniel Magro
Hermes Agent
Victor Kyriazakos
zccyman
SeoYeonKim
Magnus Hedemark
hans
xxxigm
kshitij
rob-maron
Hermes Agent
elisam0
Gille
fangliquanflq
ethernet
miura
pierrenode
joaomarcos
brooklyn!
yy28
Oliver Mee
686f6c61