Assert that a superseded stream (older writer token, other thread) is fenced
from the delta sink, the active writer is never fenced, a non-claiming thread
is never treated as a writer, and the real consume loop stops the instant it is
superseded — so two streams can never interleave into one turn (#65991).
Degrading models (observed with gpt-5.6 past ~350K input) emit tool-call
batches like 6 valid named calls + 1 blank-name call. Previously the
whole turn was voided — every valid call got 'Skipped: another tool call
in this turn used an invalid name' — and three such batches tripped the
3-strike stop, killing sessions that were still making progress.
Now a mixed batch error-results ONLY the invalid call(s) (terse
anti-priming error for blank names per #47967, catalog dump for typos)
and dispatches the valid subset for execution. The assistant message
keeps every emitted call so provider-side tool_call/result pairing stays
intact. The 3-strike counter only advances when a turn contains NO valid
call, so a fully-degenerate model still stops while a mostly-coherent
one keeps working. Broken JSON args on a never-executing invalid call no
longer trigger the whole-turn JSON retry loop.
Field evidence: July 2026 debug bundle showed gpt-5.6-sol emitting
6-call batches with one blank-name rider at 559K/384K-token context in
two separate sessions; 13 valid tool calls were discarded before the
session stopped as partial.
Two changes to tests/agent/test_file_safety_session_state.py:
1. Drop the stale monkeypatch on tools.file_tools._get_live_tracking_cwd
— the helper was deleted in the cwd-tracking refactor (c80b244b5),
and monkeypatch.setattr on a missing attribute raises AttributeError,
breaking CI slice 4/8 on main for every PR. The patch was redundant:
the test writes an absolute path, so cwd resolution never engages.
2. Make the fixture stale-proof: instead of monkeypatching the private
_hermes_home_path/_hermes_root_path helpers (same failure class if
they're ever renamed), set HERMES_HOME to <root>/profiles/work and
let the real resolution chain (get_hermes_home /
get_default_hermes_root's profiles-parent rule) derive both paths.
The fixture now references zero private symbols and exercises the
production resolution path.
Port from anomalyco/opencode#35671: Z.AI / Zhipu GLM returns
'tokens in request more than max tokens allowed' (error code 1210) on
context overflow. This matched no pattern in _CONTEXT_OVERFLOW_PATTERNS,
so the error classified as unknown/retryable — the agent would retry the
oversized request instead of triggering context compression.
Proven live on main before the fix: classify_api_error() returned
FailoverReason.unknown for the exact Z.AI error shape; now returns
context_overflow.
Port from Kilo-Org/kilocode#11955: Gemini validates every object schema's
required list strictly against the same node's properties and fails the
ENTIRE GenerateContentRequest with HTTP 400 'required[0]: property is not
defined' when a name has no matching property. MCP servers (e.g. the GitHub
remote MCP) routinely emit array item schemas carrying required without
properties, which made every request on the native Gemini path fail before
any model output.
sanitize_gemini_schema() now filters required to names present in the node's
properties and drops the keyword when nothing valid remains. Applies
recursively (properties / items / anyOf). Tool handlers still validate
required fields at execution time, so nothing the model could actually use
is lost.
Scoped to the Gemini-facing sanitizer only — the universal
tools/schema_sanitizer.py already prunes typed object nodes, and its
remaining gap (untyped nodes) is contested by open PR #20151.
The previous commit fixes the canonical agent/skill_utils.parse_frontmatter.
Six more modules reimplement the '---' fence check locally and had the
same bug:
- tools/skill_manager_tool.py _validate_frontmatter — rejected BOM'd
skill_manage create/edit content outright
- tools/skills_hub.py GitHubSource._parse_frontmatter_quick and
OptionalSkillSource._parse_frontmatter — hub browse/install metadata
- hermes_cli/skills_hub.py — local skill install validation
- gateway/run.py — skill slug discovery for disabled-skill hints
- agent/prompt_builder.py _strip_yaml_frontmatter — BOM'd context files
(AGENTS.md) leaked raw frontmatter into the system prompt
- tools/blueprints.py _split_frontmatter — str.lstrip() does not strip
U+FEFF (not whitespace), so the existing lstrip never covered it
Sibling-surface regression tests added.
Bug class also fixed upstream in cline/cline#12218 (found by the weekly
Cline PR scout).
A UTF-8 BOM saved into a SKILL.md (e.g. Notepad or PowerShell `>`) is kept by
read_text(encoding="utf-8"), so the string handed to parse_frontmatter starts
with the BOM and the startswith("---") fence check fails. The whole frontmatter
is then silently dropped: the skill loads with no name/description, `platforms`
gating falls open (a macOS-only skill becomes visible everywhere), and
required_environment_variables / metadata.hermes.config setup never fires.
Strip a single leading BOM at the top of parse_frontmatter, the shared
chokepoint for every local skill-loading path (_parse_skill_file,
discover_all_skill_config_vars, DESCRIPTION.md parsing, _inject_skill_config,
and the tools/skills_tool._parse_frontmatter re-export), so the whole class is
covered, not just the reported site. Only the leading marker is removed; a BOM
mid-content is left as data. Mirrors the existing file-tools BOM handling
(#35278) and CONTRIBUTING.md "File encoding".
Adds tests: BOM'd frontmatter parses identically to plain, the body is
BOM-free, platforms gating and config-var extraction survive a BOM, and an
end-to-end BOM-write / plain-read round trip (mirroring _parse_skill_file).
Only advertise finite watchdog deadlines that are still in the future, exercise the full MoA heartbeat path, and register the salvaged contributor attribution.
Follow-ups on top of @xxxigm's salvaged bridge (#33294):
- Remove the now-dead narrow item/started-only mapper from #38835
(_codex_note_to_tool_progress) — the full bridge supersedes it and
keeps the same tool-name contract; its tests are repointed at the
bridge helpers.
- Preserve main's request_routing/approval-bypass wiring on the
CodexAppServerSession constructor (landed after the PR was filed).
- Gate agentMessage interim delivery on display.show_commentary so the
app-server runtime honors the same toggle as the codex_responses
commentary channel (tool progress is unaffected).
- Add json import (bridge helpers use json.dumps) and modernize the
wiring test's stub agent for main's usage-accounting attributes.
42 tests across five suites:
* ``TestCodexItemToToolName`` / ``TestCodexItemToArgs`` /
``TestCodexItemToPreview`` / ``TestCodexItemCompletionPayload`` —
pin the per-type mapping so the synthetic tool name + args the
UI sees match what ``CodexEventProjector`` writes into messages.
* ``TestStreamDeltaDispatch`` / ``TestToolProgressDispatch`` /
``TestAgentMessageInterimDispatch`` — drive each Codex
notification shape through the bridge and assert the right
agent callback fires with the right arguments (including the
duration / is_error / result kwargs the gateway renders).
* ``TestBridgeRobustness`` — defensive paths: non-dict
notifications, missing params, raising callbacks (must not
tear down the codex turn loop), and agents without callbacks
registered (cron / gateway-less contexts).
* ``TestBridgeWiredInRuntime`` — integration guard that
``run_codex_app_server_turn`` actually constructs the session
with ``on_event=<bridge>``, preventing a future refactor from
silently regressing live progress visibility again.
Keep each xAI OAuth auth-add login as an independent manual device-code pool entry and recognize xAI personal-team spending-limit 403 responses as billing exhaustion. Preserve the structured top-level error message so the failed credential is quarantined and the next healthy account is selected without attempting a pointless token refresh.
Route direct xAI HTTP consumers through the credential pool as well. Proactive and 401-reactive refreshes update the exact issuing manual entry, preserve validated xAI base URL overrides, and serialize single-use refresh-token rotation across concurrent pool instances.
Add a runtime_validator callback to generate_title() / auto_title_session()
/ maybe_auto_title(). Callers snapshot the session's model+provider when
spawning the background titler; the validator runs right before the LLM
request and skips it silently when the live runtime no longer matches —
so a stale title request can't reload a model that strict_single_load
already evicted after a user model switch. Fail-open: a raising validator
never disables titling.
Wired at all four call sites (cli, gateway, tui_gateway, acp_adapter).
Surgical reapply of PR #19137 (base was 8k+ commits stale; the original
patch predates the pinned-language prompts, the atomic-write helper, and
the moved TUI/ACP call sites). Original work by @Thatgfsj. Closes#19027.
Combines the two salvaged fixes so they compose instead of conflict:
_persist_session_title (#50575) now writes through set_auto_title_if_empty
(#51483) when the store provides it — the collision-dedup retry and the
manual-/title race protection apply together. Predicate failure (a manual
title landed while generation was in flight) returns None: nothing written,
no callback. Legacy stores without the atomic method keep the plain
set_session_title path, including the vanished-session RuntimeError.
Tests cover both store shapes plus the race-skip path; E2E verified against
a real SQLite SessionDB (collision -> 'Weekly Report #2', manual title
preserved, cron dedup, blank guard). AUTHOR_MAP entry for rasitakyol.
- Make the config imports lazy inside _auto_title_enabled(), matching the
existing _title_language() pattern (title_generator is imported from agent
code paths where a module-level hermes_cli import risks circularity).
- Check the enabled flag after the cheap first-exchange guard in
maybe_auto_title so config isn't read on every turn of a long session.
- Repoint the two new tests at the real import site.
- Document the key in cli-config.yaml.example and merge the enabled flag
into the existing title_generation block in configuration.md.
- AUTHOR_MAP entry for the contributor.
auto_title_session runs as a bare daemon-thread target. Any exception
escaping it hits the default threading excepthook and sprays a raw
traceback into the user's terminal mid-session. The canonical trigger
is the post-'hermes update' stale-module window: the function's lazy
imports read NEW source from disk while already-imported modules
(agent.portal_tags) are still the OLD cached version, producing an
ImportError that repeats on every auto-title attempt until the
long-running process restarts (seen live after 9ce0e67f2 added
set_conversation_context).
The public entrypoint now wraps the body in a catch-all that logs one
WARNING naming the likely cause ('restart the running Hermes process'),
routes the exception through the existing failure_callback channel
(user-visible warning in CLI, debug-suppressed in gateway per #23246),
and never re-raises. This also makes the function honor its own
docstring contract ('silently skips if title generation fails').
LM Studio's request vocabulary tops out at "xhigh", but Hermes' generic
effort ladder has since grown two stronger levels. "max" and "ultra" miss
the _LM_VALID_EFFORTS membership test, keep the initialized "medium"
default, and are thereby conflated with unparseable input -- so asking for
more reasoning yields less than "xhigh":
high -> 'high' xhigh -> 'xhigh'
max -> 'medium' ultra -> 'medium'
This is drift, not a design choice. The valid set was an exact mirror of
VALID_REASONING_EFFORTS when the file was authored; the ladder then grew
"max" and later "ultra", and the sweep that taught every other provider
about the new levels missed this module -- it has never been touched since
it was written.
Clamp the two stronger levels onto LM Studio's declared ceiling instead,
mirroring the ceiling clamp every other provider already applies. Widening
_LM_VALID_EFFORTS would instead assert that LM Studio accepts "max" on the
wire, which is a provider-side claim this repo cannot verify; clamping
consumes only the ceiling the file already declares for itself.
The clamp is kept separate from _LM_EFFORT_ALIASES because that mapping is
also applied to the model's published allowed_options, which must not be
rewritten. A clamped value stays subject to the allowed_options check, so a
model that does not publish "xhigh" still gets the field omitted and falls
back to its own default -- exactly how a directly-requested "xhigh" behaves.
The regression test asserts monotonicity over the canonical ladder rather
than the two values alone, so the next level added upstream cannot silently
reintroduce the inversion.
DeepSeek's own API (api.deepseek.com) reports context-cache hits as
top-level usage.prompt_cache_hit_tokens / prompt_cache_miss_tokens
(prompt_tokens = hit + miss), not the OpenAI nested
prompt_tokens_details.cached_tokens shape. Neither normalize_usage()
nor the chat_completions transport's extract_cache_stats() read those
fields, so direct DeepSeek sessions always showed 0 cache-hit tokens:
invisible in accounting, mis-billed at the full input rate, and 0%
cache display.
Both layers now fall back to prompt_cache_hit_tokens when the nested
shape is absent; the nested value wins when both are present (proxies).
Fixes#61871.
Review follow-ups on the cherry-picked #36043 commit:
1. Guard the custom:<name> passthrough with a _get_named_custom_provider
lookup. The PR unconditionally kept the full custom:<name> string, which
broke config-less runtime custom providers (#34777 regression — entries
that exist only in the live runtime, not config.yaml): the named arm
found no entry and resolution fell through to Step 2. Now custom:<name>
only takes the named arm when a config entry actually exists; otherwise
it collapses to the anonymous-custom arm with the runtime endpoint,
preserving pre-PR behavior.
2. Drop the dead 'explicit_api_key = runtime_api_key' assignment (and its
misleading comment) in the named-entry branch. resolve_provider_client's
named-custom arm derives the key exclusively from the entry's
api_key/key_env and never reads explicit_api_key, so the assignment was
a no-op. Wiring precedence in was not justified: for a named custom
provider the runtime key IS the entry's key (set_runtime_main sources it
from the same config), so deletion is the honest option.
3. Tighten the Palantir Bearer-auth check from a loose substring match
('palantirfoundry' in normalized) to a hostname match via
base_url_host_matches(..., 'palantirfoundry.com'), so path segments or
lookalike domains containing the string no longer trigger Bearer auth.
Tests: named-custom anthropic_messages end-to-end routing (full name kept,
AnthropicAuxiliaryClient at the original /anthropic URL, no /v1 rewrite)
plus Palantir Bearer-auth positive and substring-false-positive cases.
Switch provider and model together after setup-time auth failure. Serialize global auth-store merges under target-specific locks and preserve auth-to-shared lock ordering for profile OAuth refreshes.
Widens the deepseek-v4-flash addition to the whole stale-snapshot class:
- deepseek-v4-pro: $1.74/$3.48 → $0.435/$0.87, cache-read $0.003625
(DeepSeek's 2026-07 price cut; every pro session was over-reporting 4x)
- deepseek-chat / deepseek-reasoner: deprecated 2026-07-24, now alias
v4-flash non-thinking/thinking modes — repriced to match flash
(reasoner was $0.55/$2.19 with no cache rate)
- cache_read added to every row; pricing_version unified at
deepseek-pricing-2026-07
- invariant tests: aliases price identically to flash; every deepseek
row carries cache_read < input
DeepSeek's /models endpoint returns no pricing, so direct-provider routes fall back to the _OFFICIAL_DOCS_PRICING snapshot. The table included deepseek-v4-pro but not the newer deepseek-v4-flash, so flash sessions reported $0.00 with cost_source "none". Add the flash entry (values from DeepSeek's official pricing page, mirroring the v4-pro entry; DeepSeek bills no separate cache-write cost) plus two regression tests.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two turns interleaving on one session corrupt the durable transcript:
flushes race (user rows persist out of arrival order), the identity-marker
dedup over shared history dicts can swallow a row, and the second turn
runs on a history base that never saw the first turn's exchange. The
dispatch route that lets the second turn through the busy guard is not
yet identified.
Add note_turn_start (build_turn_context) / note_turn_persisted
(_persist_session funnel): one WARNING naming both turn_ids when a turn
starts before the previous turn's turn-end persist. Ownership transfer
keeps a crashed turn from warning more than once; the unconditional clear
makes the tripwire under-report rather than double-report under a real
overlap. Log-only, no behavior change.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Follow-up on the salvaged #64611 commit: the original guard blocked the
install tree unconditionally, which would have broken the legitimate
'developing Hermes from a source clone' CLI flow (launching hermes inside
the repo and getting its AGENTS.md as project context).
Refined policy:
- resolve_context_cwd(): validates configured paths (missing dir -> None +
warning) but honors an EXPLICIT install-tree cwd verbatim — deliberate
user choice.
- build_context_files_prompt(): blocks only the cwd=None -> os.getcwd()
FALLBACK into the install tree, with a new allow_install_tree_fallback
param. system_prompt.py passes it for platform cli/tui (launch dir is
the user's real shell cwd there); desktop/gateway surfaces keep the
guard (their fallback dir is self-spawned, never user-picked).
- Warning log names the resolved dir and the terminal.cwd remedy.
E2E-verified all five scenarios: desktop fallback blocked, in-tree CLI dev
keeps AGENTS.md, explicit install-tree cwd honored, invalid TERMINAL_CWD
falls to None then blocked, normal workspace loads.
- Refresh _OFFICIAL_DOCS_PRICING fireworks entries against current
docs.fireworks.ai/serverless/pricing: qwen3p6-plus is gone (replaced
by qwen3p7-plus); add glm-5p2/5p1, kimi-k2p7-code, deepseek-v4-flash,
minimax-m3/m2p7, gpt-oss-120b/20b, and the routers/*-fast tiers with
their distinct higher rates.
- Picker pricing via get_pricing_for_provider('fireworks'): pure dict
transform over the shared models.dev in-memory/disk cache (1h TTL) +
_pricing_cache memoization — no new network call on the picker path.
- Wire pricing display into the generic api-key-provider setup flow so
Fireworks model pickers show $/M columns like OpenRouter/Nous do.
- Invariant tests: plugin fallback_models all priced, fast tiers price
higher than standard, every row carries cache_read < input.
Fireworks-hosted sessions previously showed estimated_cost_usd = 0
because (a) _OFFICIAL_DOCS_PRICING had no Fireworks entries and (b)
resolve_billing_route() had no branch for provider="fireworks",
falling through to billing_mode="unknown".
Adds entries for the three Fireworks models hermes operators are
most likely to route through (Kimi K2.6, DeepSeek V4 Pro, Qwen3.6-Plus)
and a routing branch that triggers on either explicit
provider="fireworks" or api.fireworks.ai base_url match. Mirrors the
recently-merged MiniMax addition pattern; pricing snapshot sourced
from https://docs.fireworks.ai/serverless/pricing and the per-model
pages on fireworks.ai.
Tests cover: (a) full Fireworks model id resolves to the snapshot
entry, (b) base_url alone is sufficient to route, (c) end-to-end
estimate returns "estimated" status with the expected dollar amount.
A follow-up upstream issue is open proposing a dynamic pricing
source (e.g. litellm's pricing JSON) as a permanent fix to the
PR-per-model treadmill that this snapshot keeps adding to.
* feat(analytics): record auxiliary model usage per task in session accounting
Auxiliary LLM calls (vision, compression, title_generation, web_extract,
session_search, ...) discarded their token usage, leaving dashboard
analytics blind to aux model spend (issue #23270).
- hermes_state.py: session_model_usage gains a task PK dimension
(''=main loop) via v22 table-rebuild migration (SQLite can't alter a
PK); record_auxiliary_usage() writes per-(model,provider,task) deltas
WITHOUT touching sessions counters (gateway overwrites those with
absolute main-loop totals — folding aux in would double-count or be
clobbered). Aux rows never inherit the session's main-loop route.
- agent/aux_accounting.py: ContextVar ambient accounting context
(mirrors the portal_tags conversation context); record_aux_usage()
normalizes usage via usage_pricing.normalize_usage, estimates cost,
and is strictly best-effort. moa_reference/moa_aggregator excluded —
conversation_loop already folds MoA usage+cost into the main delta.
- agent/auxiliary_client.py: _validate_llm_response is the recording
chokepoint — every successful non-streaming aux response passes
through it exactly once, sync and async, including fallback paths
(model read from the response itself stays accurate across
fallbacks).
- run_agent.py: run_conversation publishes/resets the accounting
context; agent/title_generator.py republishes on its bare thread.
- hermes_cli/web_server.py: /api/analytics/usage folds aux rows into
by_model (aux-only models finally appear) and adds a by_task
summary; /api/analytics/models surfaces aux rows on the Models page.
Design per review of PR #62850 by @eeksock (thread-local + separate
auxiliary_usage table): rebuilt on ContextVar (async-safe — thread-local
cross-attributes concurrent coroutines on one event loop) and the
existing session_model_usage table instead of a parallel accounting
path, extended beyond vision to every aux task, and wired the analytics
endpoints so the dashboard actually shows it. Credit to @eeksock for
the approach and @tboatman for the detailed root-cause analysis.
* test(moa): match _validate_llm_response mock to new accounting-hint signature
* test(aux): accept accounting-hint kwargs in remaining _validate_llm_response mocks
Extends the conversation=<id> Portal tag (salvaged from PR #65183 by
@J-SUPHA) from main-loop-only to every LLM call in a conversation:
- agent/portal_tags.py: ContextVar-based conversation context.
nous_portal_tags() falls back to the ambient id when no explicit
session_id is passed, so every aux tag site (auxiliary_client,
chat_completion_helpers summary path, web_tools) inherits the tag
with zero per-call-site plumbing. Ambient id wins over explicit
per-segment ids since it carries the lineage root.
- hermes_state.py: SessionDB.get_conversation_root() — public wrapper
over the lineage walk; returns the ROOT session id, so one
user-facing conversation keeps a single conversation= value across
context-compression rotation, and delegate subagent trees tag as
their parent conversation.
- run_agent.py: run_conversation() publishes the root id for the turn
and resets it in finally. _conversation_root_id() resolves via
_parent_session_id for subagents.
- agent/moa_loop.py: MoA reference fan-out workers now run under
propagate_context_to_thread so advisor slots attribute to the acting
conversation (also fixes approval-callback propagation on that path).
- agent/title_generator.py: bare title thread republishes the context
from its session id (spawned after turn reset).
Tests: ContextVar semantics, cross-context isolation, thread-hop
propagation, lineage-root resolution incl. cycle guard.
The per-session record store is now the ONLY cwd mechanism. Deleted:
- env.cwd_owner stamping + prev_owner threading (terminal_tool): the
shared env no longer carries ownership metadata at all
- _resolve_command_cwd's env/prev_owner params: resolution is
workdir > session record > config/override default
- file_tools._live_cwd_if_owned + _get_live_tracking_cwd: path
resolution never consults the shared env's live cwd
- file_tools._last_known_cwd + _remember_last_known_cwd +
_last_known_cwd_for: the #26211 preserved-anchor registry is
subsumed by the session record, which never lived on the env and
therefore cannot be lost to env cleanup. The _get_file_ops
stale-cache rescue now writes the record instead.
- env recreation (both _get_file_ops and terminal_tool) seeds the
fresh env from override > session record > config
Why no transition fallback: the legacy state was process-local and
in-memory exactly like the record store — after a restart both start
empty, and within a running process every legacy write site has been
dual-writing the record since step 1. There is no populated-legacy/
empty-record state to fall back for.
Tests updated to drive the record store instead of the deleted
mechanism; the cross-session isolation suite now asserts the same
behavior contracts (no leak, cd isolation, #26211 persistence)
against the new architecture, plus a new "session C inherits nothing"
case that the old ownership guard could not express.
Fixes#62452. Two amplifiers turned one slow auxiliary route into a
per-turn multi-minute stall:
1. Fallback candidates inherited the exact effective_timeout the primary
was called with. When the primary's deadline was short (tuned or
already burned), an independently healthy fallback died on the same
clock — the reporter's 163k-token compression needed ~90s on the
fallback and got the primary's 30s, every turn. fallback_chain
entries may now declare their own 'timeout' (seconds); both fallback
candidate call sites (sync + async) resolve it via
_fallback_entry_timeout, label-scoped so only configured-chain
candidates are affected. No entry timeout → task-level timeout,
preserving existing behavior.
2. A session whose transcript structurally cannot be summarized within
the deadline re-attempted every 60s, re-burning the full timeout on
every subsequent turn. Consecutive timeout-class failures now
escalate the cooldown 60s → 300s → 900s (capped); any successful
summary or session reset clears the streak. Timeout classification
takes precedence over the streaming-closed 30s rung ('timed out'
also matches _is_connection_error) and now recognizes the SDK's
'Request timed out.' phrasing.
Fail-safe behavior is unchanged: all messages are preserved when every
candidate fails; the cooldown only spaces out retries.
The cross-turn stale-call circuit breaker (_check_stale_giveup in
agent/chat_completion_helpers.py) raises a RuntimeError when the
provider has been unresponsive for N consecutive stale attempts.
This error was classified as FailoverReason.unknown (retryable=True,
should_fallback=False), causing the retry loop to burn all max_retries
against the same dead provider — each retry hitting the circuit breaker
instantly with zero network overhead — before fallback was attempted.
Add a classification rule (section 7b in classify_api_error) that
recognizes the stale-breaker RuntimeError by its signature phrases and
classifies it as FailoverReason.timeout with retryable=False,
should_fallback=True. This makes the retry loop skip retries and go
straight to fallback provider activation on the first hit.
Test: test_stale_breaker_runtime_error_triggers_fallback_not_retry
Rewrites the cherry-picked test to import os locally and monkeypatch the
resolver seams instead of patching bedrock_adapter internals; adds the
inverse assertion (no bearer -> AnthropicBedrock SDK path preserved).
Three fixes for the Bedrock Claude path:
1. Streaming fallback: When AnthropicBedrock SDK raises 'Unexpected event
order' (SDK misparses Bedrock error events as message_start), auto-switch
to native Converse API for the rest of the session instead of failing
after 3 retries.
2. Image base64 decode (#33317): data URL payloads were passed as base64
strings to source.bytes, but boto3 re-encodes at the wire layer. Now
decoded to raw bytes before passing to Converse API.
3. Bearer token routing (#28156): Users with AWS_BEARER_TOKEN_BEDROCK are
now routed through Converse API regardless of model, since the
AnthropicBedrock SDK only supports SigV4 signing.
3 new tests. 121 bedrock_adapter tests passing.
