Follow-ups on top of the cherry-picked #27748 mechanism:
- move the cap constant to module level with full rationale comment
(class attribute aliases it so subclasses/tests can override)
- bound the iterative-update path too: the PREVIOUS SUMMARY block is
passed through _bound_summary_input so a pathological rehydrated
handoff cannot blow up the prompt (previous summary + new turns each
capped)
- extra regression tests: byte-identical small-input passthrough
(identity), direct bound+marker unit check, bound-after-per-message-
truncation shape (hundreds of under-_CONTENT_MAX turns), iterative
path bounded, marker vs classify_summary_content non-collision
- contributor email mapping for @robgfl45
MoA reference_max_tokens is preset-level — one cap for all reference
models. When mixing a verbose model with a terse one, a single cap is
either too tight for the terse model or too loose for the verbose one.
Now each reference slot can optionally carry its own max_tokens:
reference_models:
- provider: openrouter
model: deepseek/deepseek-v4-pro
max_tokens: *** # per-slot cap, overrides preset-level
- provider: openai-codex
model: gpt-5.5
# no max_tokens → falls back to preset-level reference_max_tokens
_clean_slot (moa_config.py) preserves an optional max_tokens field on
the slot dict, coerced via _coerce_int_or_none. _run_reference
(moa_loop.py) reads slot-level max_tokens first, falling back to the
preset-level cap passed by the caller. Slots without the field are
unaffected — backward compatible.
Type hints on slot-handling functions updated from dict[str, str] to
dict[str, Any] to reflect the now-heterogeneous slot shape.
_build_call_kwargs omitted max_tokens for every provider except
anthropic-compat endpoints and NVIDIA NIM. Gemini's native
generateContent maps max_tokens -> maxOutputTokens and, when it is
omitted, applies a fixed 65,535-token ceiling (not "the model's full
budget"), so dropping the value made MoA's reference_max_tokens a
silent no-op for gemini advisors — they ran effectively uncapped
(observed ~2900 output tokens against a configured cap of 600),
inflating per-turn MoA latency.
Forward max_tokens for the gemini-native path (provider name or native
base_url). Gemini supports maxOutputTokens, so the cap is safe here;
providers that reject max_tokens (Copilot, GPT-5 max_completion_tokens,
ZAI vision) are unaffected — they still omit it as before.
PR #56756 added reference_max_tokens to cap MoA advisor output and cut
turn latency. The value is correctly threaded through five layers of MoA
code (moa_config → conversation_loop → aggregate_moa_context →
_run_references_parallel → _run_reference → call_llm(task='moa_reference',
max_tokens=800, ...)).
However, _build_call_kwargs() in auxiliary_client.py silently drops
max_tokens for all OpenAI-compatible providers (PR #34845, which fixed
endpoints and NVIDIA NIM keep it. This means reference_max_tokens never
reached the API for the vast majority of providers.
The bug affects every OpenAI-compatible MoA reference/aggregator slot:
Z.AI (coding plan), OpenRouter, OpenAI, GitHub Copilot, and local
providers. Only Anthropic-compat endpoints (MiniMax, /anthropic URLs)
worked — by coincidence, not MoA-aware design.
Fix: thread the 'task' parameter through all six _build_call_kwargs()
call sites. When task starts with 'moa_', max_tokens is always included
in the request kwargs regardless of provider. Non-MoA auxiliary tasks
(compression, titles, vision, etc.) keep PR #34845 behavior unchanged.
Verified end-to-end:
- Z.AI GLM-5.2 with max_tokens=50 → returned exactly 50 tokens
- Z.AI GLM-5.2 with max_tokens=20 → returned exactly 20 tokens
- Z.AI GLM-5.2 uncapped → returned 315 tokens
- 7 new regression tests covering 4 providers, Anthropic wire, non-MoA
tasks, and prefix-matching boundary
- 288 auxiliary_client tests pass (was 281, +7 new), 84 MoA tests pass
- Zero regressions
Note: #51899's commit was authored as a placeholder identity
(hermes-agent@example.invalid); it was re-stamped to @byshubham's
numeric noreply on this branch, so no mapping file is needed. Other
salvaged commits use GitHub noreply addresses.
origin_session_id (the api_server wake self-post target) lived only in
the in-memory record: durable dispatch persistence and abandoned-
delegation recovery omitted it, leaving completions recovered after a
process restart unroutable to api_server sessions. Persist it in the
async_delegations table (CREATE TABLE + ALTER TABLE migration for legacy
DBs), restore it on recovery, and expose it via get_durable_delegation.
Also adds the contributors mapping for ianks (PR #64998 author).
Follow-up to #64998 (sweeper review F3).
When _api_key_passes_startup_guard() rejects the key (missing,
placeholder/too short, or fail-closed unverifiable strength), connect()
returned a bare False with no fatal-error info. gateway.run's reconnect
watcher treats that as transient and re-queues with backoff forever —
each retry re-instantiating the adapter and its ResponseStore sqlite
connection. Observed in production (#37011): ~501 leaked connections
(1002 fds) over ~2.5 days until EMFILE made the whole gateway
unresponsive.
Set a non-retryable fatal error (api_server_key_invalid) in connect()
when the guard rejects, covering all three rejection branches, so the
platform drops from the reconnect queue; recover with
`/platform resume api_server` after fixing the key. Same treatment as
the port-conflict guard (api_server_port_in_use, #65665 / bda8bd76a8).
Tests mirror the port-conflict precedent: each rejection path asserts
connect() is False, has_fatal_error True, fatal_error_retryable False,
and fatal_error_code api_server_key_invalid, plus a strong-key control.
Re-implementation of #38803 by @cifangyiquan against current main —
their patch targeted the old inline guard in connect() which was since
extracted to _api_key_passes_startup_guard() (and gained the
fail-closed branch in 683059feb5), so the original diff no longer
applies. Their production diagnosis and non-retryable direction
preserved.
Refs: #38803, #37011
Salvaged from PR #36180 (commits 68dfeb4b16 and 86f437509b by arimu1),
re-applied onto current main with the incidental black-reformat churn
stripped out (~1,700 lines -> the semantic change + tests).
Previously gateway/config.py enrolled the api_server platform on
`api_server_enabled or api_server_key`, so API_SERVER_ENABLED=true with
no key (or a weak/placeholder key) still loaded the platform: the
adapter is instantiated (ResponseStore/SQLite opened in __init__), the
reconnect watcher spins, and the startup guard refuses at connect() —
logging errors forever. Now the platform is enrolled only when
API_SERVER_KEY passes the same strength bar as the adapter's startup
guard (has_usable_secret, min_length=16), via a shared
_has_usable_api_server_key() helper.
The no-op `lambda cfg: True` connected-checker for API_SERVER is also
replaced with the same key check, so get_connected_platforms() only
reports the platform "up" when it could actually start.
Known limitation (intentionally out of scope): a YAML config with
`platforms.api_server.enabled: true` and no key still loads the
platform; this gate covers the env-override path only.
Dropped from the original PR: EMAIL/SMS checker additions (scope creep
beyond the PR title; absent on current main) and the wholesale black
reformat of gateway/config.py and tests.
Fixes#36111
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
shivasymbl, z23, Skywind5487, 2001Y, gonzalofrancoceballos, kylezh.
briandevans' noreply mapping already present; mzkarami's mapping file
shipped inside #66204's own commit.
Also fixes the TestFormatMessageTableIntegration fixture to match
PlatformConfig's current signature (no 'name' kwarg).
Follow-up fixes for the #62625 salvage:
- Dedup-reset gap (sweeper review): when the block clears while the
context is STILL over threshold, execution enters the compression
branch — the PR's 'else' reset never ran, so the warning stayed
suppressed forever after the first block. _clear_context_overflow_warn()
now fires on every automatic compression path: turn-context preflight,
conversation_loop pre-API gate, and the post-tool loop-compaction gate.
- should_compress_info on current main: main refactored should_compress
into _automatic_compression_blocked()/_locally(); the tuple variant now
derives its reason from the same in-memory state via
_compression_block_reason(), keeping cooldown:<s>/ineffective shapes.
- ContextEngine.should_compress_info ABC default now actually returns
(should_compress(tokens), None) — the PR's default had a docstring but
no return (returned None, would crash tuple-unpacking call sites).
- Below-threshold guard: the turn-context persisted-cooldown branch and
the conversation_loop pre-API cooldown branch no longer warn when the
estimate is under threshold (should_compress_info returns a None
reason; the preflight pre-check is not a threshold guarantee). The
pre-API guard also honors compression.max_attempts instead of a
hardcoded 3, and no longer fabricates a cooldown reason.
- Noise-filter survival (#69550 composition): warning text is now a
template constant (CONTEXT_OVERFLOW_BLOCKED_WARNING_TEMPLATE) marked
FAILURE-CLASS, pinned un-swallowed in VISIBLE_COMPRESSION_MESSAGES and
in new tests that execute the real _TELEGRAM_NOISY_STATUS_RE +
_prepare_gateway_status_message.
- Contributor mapping for stanislav@local -> sl4m3.
Treat cua-driver's Linux `is_on_screen: null` as unknown instead of
off-screen, and skip GNOME Shell desktop/backdrop helper windows
(ding "Desktop Icons", @!x,y;BDHF) when selecting the default capture
target — they are targetable X11 windows but capture as empty.
Reconciled with the _NET_ACTIVE_WINDOW fallback from #58030: helper
windows are filtered out of the candidate pool first, then the tied
z-order active-window probe runs on the remaining real app windows.
Also falls back to the requested app name for _last_app when Linux
windows carry no app_name.
Salvaged from #54173 by @dnth.
The anti-thrash guard (_ineffective_compression_count) was in-memory
only: a fresh compressor bound to a resumed, already-compacted session
started with compression_count=0 and a disarmed guard, so a
near-threshold session could legally re-compact once per process
restart, forever.
Persist the counter through the durable session-state channel,
mirroring the failure-cooldown (#54465) and fallback-streak (af7dceaf7)
pattern:
- hermes_state.py: sessions.compression_ineffective_count column
(declarative reconciliation adds it on existing DBs) +
get/set_compression_ineffective_count accessors.
- context_compressor.py: every strike/clear verdict routes through
_record_ineffective_compression_verdict() which writes through to the
session row (no-change verdicts skip the DB write);
bind_session_state() loads the persisted value; the compression
rotation boundary carries the counter onto the child row;
update_model()'s reset also clears the durable copy; the
ineffective-only fast path in _automatic_compression_blocked() is
removed because the counter is now durable and another agent's clear
must unblock a stale local snapshot.
- conversation_compression.py: _refresh_persisted_compression_guards
re-reads the counter alongside cooldown + fallback streak.
Reset semantics are unchanged: any real provider reading below the
threshold still clears the counter — and now clears it durably too.
Resolves the residual gap identified in #54923 by @lanyusea (the
second-threshold mechanism was superseded by persisting the existing
guard state).
Co-authored-by: lanyusea <lanyusea@gmail.com>
- tests/cli/test_compress_type_ahead.py: end-to-end proof of the PR #68284
docstring claim — a prompt queued into _pending_input while /compress runs
survives compaction untouched and is the next item process_loop drains,
i.e. it is processed against the compacted history. Plus a structural
guard that handle_enter never gates on _command_running /
_command_blocks_input (read-only enforcement belongs solely to the
TextArea Condition; a busy-gate in handle_enter would silently drop
type-ahead input).
- tests/test_cli_manual_compress.py: update the one remaining _busy_command
stub (added on main after the PR branched) to accept the new
blocks_input kwarg.
- contributors/emails: map lucas@policastromd.com -> enzo2.
Photon (managed iMessage) shipped without a _PLATFORM_DEFAULTS entry, so it
inherited the noisy global ('all') display defaults and narrated tool
progress / heartbeats / busy-ack detail into a permanent-message iMessage
thread. Register it as TIER_LOW alongside BlueBubbles and Signal, plus a
regression test guarding the tier.
Salvaged from #50511 (Photon tier piece only).
Keep thin-PATH resolution while asserting the absolute binary on the
already-installed version check. Map contributor emails for the salvage.
Co-authored-by: Tianqing Yun <yuntianqing@yahoo.com>
Co-authored-by: Trevor Gordon <trevorbgordon@gmail.com>
Co-authored-by: Adrian Soto Mora <adrian.soto6@gmail.com>
* fix(desktop): keep clarify lifecycle when tool progress is off
* fix(desktop): render clarify prompt from the request event
Re-authored onto the current use-message-stream/gateway-event.ts (the
original patched the pre-split use-message-stream.ts). When the tool.start
row that normally mounts the inline clarify UI is missed (stream reconnect
/ hydration race), upsert a stable pending clarify tool row from
clarify.request itself so the prompt stays answerable; a real
tool.start/complete with the same request id merges rather than duplicates.
Co-authored-by: 정수환 <centerid@naver.com>
* chore(contributors): map centerid@naver.com -> lidises
Attribution mapping for the salvaged #47544 commit.
* fix(desktop): correlate clarify rows by question so hydration can't duplicate
The hydrated row (from clarify.request's request_id) and the real tool.start
row (the model's tool_call_id) have different ids, so id-only matching appended
a second clarify card in the normal path (caught by the BLOCKING_CLARIFY e2e:
'question' resolved to 2 elements). Add 'question' to the tool match-value keys
so a clarify upsert merges into the existing pending clarify row regardless of
id (same request<->args correlation ClarifyToolPending already uses); when no
row exists yet (reconnect/hydration) it still creates one.
---------
Co-authored-by: 정수환 <centerid@naver.com>
* fix(gateway): deliver assistant prose before clarify poll
The clarify poll is sent on a separate, agent-thread-blocking path while
buffered assistant prose (interim commentary / streamed deltas) sits in
the GatewayStreamConsumer queue, drained asynchronously. The poll won the
race, so the question rendered ABOVE its own explanation, and a redundant
'clarify: ...' tool-progress bubble wedged between them.
- Add GatewayStreamConsumer.flush_pending_sync(): a synchronous flush
barrier (_FLUSH sentinel + threading.Event) that blocks the agent
thread until everything queued before it is finalized and delivered.
- Call it in the gateway clarify callback before send_clarify, so prose
always lands before the poll. Best-effort with a 3s timeout.
- Suppress the redundant clarify tool-progress bubble (the poll already
shows the question + options).
Tests: 3 new ordering/timeout cases in test_stream_consumer.py.
(cherry picked from commit 9a6e27badb)
* chore(contributors): map matvey.sakhnenko03@icloud.com -> sakhnenkoff
Attribution mapping for the salvaged #54328 commit (Cluster C).
---------
Co-authored-by: Matvii Sakhnenko <matvey.sakhnenko03@icloud.com>
With compression.in_place defaulting True the cron session id never
rotates; get_compression_tip returns the input id. Pin that the
salvaged #67188 fix titles/ends the ORIGINAL cron session in that path
(and for falsy tip returns), i.e. zero behavior change when no
compression rotation happened. Also maps colingreig's contributor
email for attribution CI.
Hardening for the #59114 salvage: generate real standalone and merged
handoffs with the current compressor and assert classify_summary_content
agrees with _is_context_summary_content and is_compaction_summary_message
on every emitted shape (behavior contract, not a format snapshot), incl.
the flag-stripped DB-reload copy. Also adds the contributor email mapping
for @israellot.
Follow-up for salvaged #24279:
- cli-config.yaml.example: document compression.threshold_tokens
(commented-out, default null = disabled)
- contributors/emails: map maly.dan@gmail.com -> DanielMaly
- tests: should_compress() fires at the absolute cap below the pct
threshold (first-fires-wins); DEFAULT_CONFIG ships None and 0/None
are behavior-neutral incl. across update_model(); the small-context
pct floor is unaffected by the cap and re-derives correctly on
model switch
Compaction summaries persist across sessions and re-enter every subsequent
summarizer prompt, but every redact_sensitive_text() call in
context_compressor.py used default mode: a no-op under
security.redact_secrets:false, and opaque OAuth-callback / URL-userinfo
credentials passed through even when enabled. The stored _previous_summary
also re-entered the iterative-update prompt unredacted.
Add _redact_compaction_text() — redact_sensitive_text(force=True,
redact_url_credentials=True) — and thread it through all compaction text
boundaries: serializer input (content + tool args), deterministic fallback
summary, summarizer LLM output, manual + auto focus topics, the latest-user
task snapshot, and _previous_summary re-entry.
Note: force=True at this boundary intentionally overrides
security.redact_secrets:false — that opt-out targets live tool output, not
persisted summaries.
Salvages the compaction half of #49556 (the redact.py strict-URL half
landed independently via 75af6dc57/62a00a739). Addresses #43666 item 2.
Co-authored-by: AndrewMoryakov <topazd2@gmail.com>
