Prove a fence-cancelled helper (no abort flag) persists cooldown so the
next turn does not re-arm compression, the host does not wait out the
600s ceiling after cancel, a held lock skips the sibling agent, and
unwind cancellation records the same brake.
(cherry picked from commit d2e178cd96fbcc8b2baf68488a8f46c70bff31a2)
Review follow-ups on the salvaged #90845:
- hygiene_max_turn_hold_seconds registered in config_defaults next to
its sibling hygiene knobs (run.py already read it; the key was
undiscoverable).
- Turn-hold abandonment now records a flat 60s retry-after via the
existing cooldown column. Without it, sustained traffic re-spawned,
held, and cancelled a fresh compressor on EVERY turn — a per-turn
summary-model token burn that never commits. Deliberately outside the
x1/x3/x9 failure ladder: the compressor is healthy, so the failure
streak must not advance (witness updated to assert exactly that
boundary: no streak increment, flat <=120s spacing, turn-hold reason).
Session hygiene auto-compression runs inline on the incoming-message path
and awaits the summary worker with a progress-aware inactivity budget
(hygiene_timeout_seconds) that extends up to hygiene_total_ceiling_seconds
(default 600s). A summary model that keeps streaming tokens keeps resetting
the inactivity slice, so the wait can stretch toward the ceiling while zero
bytes reach the user — chat transports (Telegram ~30s idle-timeout) drop the
connection and the turn appears frozen, even though the gateway is healthy.
Add hygiene_max_turn_hold_seconds (default 10), a turn-hold budget that caps
the wall-clock the incoming message waits on hygiene compression. The wait
slice is additionally capped at the remaining budget so the budget is
re-evaluated even when the worker keeps the inactivity slice large. On
exceeding the budget the gateway abandons the inline wait and proceeds on
the uncompressed transcript via the existing timeout path, which revokes the
worker's commit admission (CompressionCommitFence) and defers cleanup — so a
stale compression finishing later can never overwrite the turns appended
after the wait was abandoned.
Well under the typical transport idle-timeout, this guarantees the message
is answered promptly while the detached compression completes in the
background. Configurable via compression.hygiene_max_turn_hold_seconds.
Adds a regression test: a worker that streams progress continuously (so the
inactivity slice never fires) must be abandoned once it exceeds the
turn-hold budget, the turn proceeds uncompressed, and the stale commit is
fenced (no session mutation, role alternation intact).
Follow-up to c0d974b19 (#79741). Three review findings against that commit,
none of which change the escalation behaviour it shipped.
1. The recovery decision lived inline in `_handle_message_with_agent`, a
~2000-line async method, so the only way to pin it was a test that read
`inspect.getsource(...)` and asserted on substrings. AGENTS.md bans reading
source in tests outright and names this exact situation: "if the logic lives
inline in a god-file (gateway/run.py) and extracting it feels disruptive:
that's the actual signal to do the extraction, not to regex around it."
Those tests were not merely stylistically wrong, they were actively harmful.
One asserted the substring `_new_tokens < _approx_tokens` was PRESENT -- so
it passed while the gate had the bug that substring represents, and had to be
edited when the gate was fixed. It failed on correct code and passed on
broken code, in one assertion.
Extracted `hygiene_compaction_recovered()` as a module-level pure predicate
and replaced the three source-reading tests with eight direct unit tests.
The extraction immediately earned itself: the new tests caught a `NameError`
(the predicate called `compression_made_progress` while the module bound it
under an alias) that a source-text assertion cannot see, because the symbol
is spelled correctly in the source and only fails at runtime.
2. The gate inferred "did the transcript actually get rewritten" from a numeric
side effect -- the degenerate "did not rotate or compact in place" path
(#21301) reuses the pre-compression counts -- when the booleans
`_hyg_rotated` / `_hyg_in_place` were already in scope and explicitly set
False on that path. The predicate now takes them directly, so a future edit
that re-estimates instead of reusing the old counts cannot silently defeat
the escalation.
3. `_record_hygiene_cooldown` passed no `error` to
`record_compression_failure_cooldown`, which writes `compression_failure_error`
unconditionally -- so a hygiene failure clobbered to NULL whatever reason the
in-conversation path had recorded, and readers then show the user "unknown
error" (agent/manual_compression_feedback.py, gateway/slash_commands.py). The
reason was already in hand at both call sites. Pre-existing from #74136 but
amplified by escalation: a blank reason on a 45-minute cooldown is far more
user-visible than on a 5-minute one.
Also: the ladder docstring described the compressor's absolute 60/300/900s
ladder while the constant is multipliers (1, 3, 9); the config docs still
described `hygiene_failure_cooldown_seconds` as a flat interval rather than the
first rung of a capped ladder; and `PersistentState.hygiene_failure_streak` now
documents that it is process-local by design -- keying on `session_key` is what
survives compaction rotation, which the persisted `compression_*_streak`
columns cannot express since they key on the rotating `session_id`. Making it
durable is a schema change, tracked on #79624 rather than smuggled in here.
Also replaces the file's hand-written `_Runner` stub with
`object.__new__(GatewayRunner)` (already the idiom elsewhere in the same file).
The stub reimplemented `_session_state` and `_peek_session_state`, so the tests
exercised copies that could drift from production; using the real class
immediately made one assertion stronger -- on a fresh runner `_sessions` does not
exist at all until something materialises it, so the reset provably did not even
create the map.
A review pass on this follow-up then caught that the CALL SITE was still
unbound: deleting the whole `if not _hyg_aborted: if
hygiene_compaction_recovered(...)` block left every ladder test green, because
the unit tests prove the predicate correct without proving it is wired in. The
merged commit had the same gap and its only cover was the banned source-reading
test. `test_session_hygiene_forces_in_place_compaction_with_bound_session_db`
now spies the reset on a genuine in-place compaction, so deleting the wiring
fails. Two earlier attempts at this test did NOT close the gap -- asserting on
streak VALUES passes either way, since the streak is 0 whether or not the gate
ran; only a positive spy assertion on a recovering run detects the deletion.
Same pass also corrected an overstatement: point (2) is hardening, not a live
bug. The degenerate path also sets `_new_count = _msg_count` and `_new_tokens =
_approx_tokens`, and `compression_made_progress(n, n, t, t)` is always False, so
the merged code already declined to reset there. A 200k-trial fuzz over the
reachable state space found zero behavioural disagreements between the merged
gate and this one. The guard's value is surviving a future edit that stops
reusing those counts.
Tests: 28 in tests/gateway/test_hygiene_failure_cooldown_ladder.py (8 new unit
tests for the predicate, 3 for reason forwarding, 3 source-reading tests
deleted). All 5 mutations caught -- including one that restores the hand-rolled
comparison and one that removes the rotated/in_place guard. Two mutations
initially SURVIVED and exposed vacuous tests of my own: the no-rewrite test used
counts the progress predicate already rejects, so it passed without binding the
guard at all; it now passes counts that read as progress on their own, proving
the guard is what rejects them. gateway hygiene + session-state + agent
compression-progress suites: 54 passed; ruff clean.
Refs #79624
Fix-up for the cherry-picked cooldown persistence: the PR's tests mocked
the DB (SimpleNamespace(_db=MagicMock())), which cannot prove the cooldown
survives a restart. Replace with the production shape — a real SessionDB
on disk behind the real AsyncSessionDB facade — and add a restart
regression: fail a hygiene compression on runner #1, tear it down, build a
fresh GatewayRunner on the SAME database, and assert the cooldown is still
honored (no compression agent instantiated). Also updates the timeout test
to assert the DB-backed record_compression_failure_cooldown write instead
of the removed in-memory dict.
Sabotage-verified: reverting gateway/run.py to the in-memory dict makes
the restart test fail.
Manual /compress already persists the rotated child transcript first and
only then repoints the live session_entry; a False rewrite_transcript
return keeps the entry on the original session_id so the conversation
stays reachable. Session hygiene auto-compress did the opposite: it
rebound session_id (and lease/topic) first, then called rewrite_transcript
without checking the return value. On a failed write the live entry
already pointed at an empty child SID and the turn continued — permanent
silent conversation loss. Persist first; rebind only after success.
The gateway's pre-agent session-hygiene compression killed the summary
call at a fixed 30s wall-clock deadline (compression.hygiene_timeout_seconds),
regardless of whether the summary model was hung or merely slow. A reasoning
model happily streaming a large summary was cut off mid-generation, the user
got '⚠️ Context compression timed out after 30.0s', and a 300s failure
cooldown left the session oversized — a doom loop for slow-but-healthy
auxiliary models.
Timeouts are now liveness-based instead of wall-clock-based:
- agent/auxiliary_client.py: new thread-local aux_progress_hook. When
installed (only by context compression today), the primary call_llm
attempt streams (stream=True) and aggregates chunks back into a complete
response, ticking the hook per chunk. The configured timeout then acts
per stream read (idle) instead of as a total budget. Providers that
reject streaming fall back to the plain non-streaming call; auth/payment/
rate-limit/transport errors propagate unchanged into the existing
recovery chains. Codex Responses (per SSE event) and Anthropic Messages
(per stream event, via the new create_anthropic_message on_stream_event
callback) tick the same hook from inside their wire adapters.
- agent/conversation_compression.py: CompressionCommitFence gains
touch_progress()/seconds_since_progress(); compress_context() installs
fence.touch_progress as the progress hook around the compress call.
- gateway/run.py: the hygiene wait loop treats hygiene_timeout_seconds as
an INACTIVITY budget — while the fence reports fresh progress the wait
extends, bounded by the new compression.hygiene_total_ceiling_seconds
(default 600s, clamped >= the idle budget) so a degenerate trickle
stream still dies. The timeout warning now says the summary model
produced no output, which is the only case that still triggers it.
- config/docs: hygiene_total_ceiling_seconds added to DEFAULT_CONFIG and
configuration.md; hygiene_timeout_seconds documented as inactivity-based.
Tests: tests/agent/test_aux_progress_streaming.py (hook plumbing, stream
aggregation incl. tool-call deltas and reasoning deltas, rejection
fallback, ceiling kill, fence progress surface); two new gateway tests
prove a slow-but-streaming worker survives past the fixed timeout
(sabotage-verified: fails with the old fixed deadline) and a
forever-trickling worker is still cut off at the ceiling.
0.15s missed by 1-8ms on busy CI shards twice today (runs 30025889952,
30026770278 — branches not touching this file). The assertion pins
'handler did not block on the timeout path' (blocking = seconds); 2.0s
keeps the contract per the loose-bounds flake policy.
Flip the two tests that pinned the old buggy behavior (rewrite_transcript
called after in-place compaction) to assert the corrected invariant from
#61145: archive_and_compact() already persisted, so the handler must NOT
call rewrite_transcript — its replace_messages(active_only=False) would
DELETE the just-archived rows.
E2E-verified against a real SessionDB: 6 soft-archived rows are wiped by
replace_messages' default path, confirming the data-loss premise.
After a prolonged outage the in-process network-error ladder escalates to
fatal and GatewayRunner._platform_reconnect_watcher rebuilds a fresh adapter
that reconnects through the bootstrap path. That path called
start_polling(drop_pending_updates=True), discarding every update Telegram
queued during the outage — all messages sent while the bot was down were
silently lost. The in-process ladder and 409-conflict handler already passed
drop_pending_updates=False; only bootstrap did not distinguish a cold first
boot from a reconnect.
Thread an is_reconnect signal from the watcher through
_connect_adapter_with_timeout into adapter.connect(). The base
BasePlatformAdapter.connect() gains a keyword-only is_reconnect=False so every
adapter inherits a tolerant signature (no per-platform breakage when the
runner forwards the kwarg). Telegram translates is_reconnect into
drop_pending_updates=not is_reconnect on both the polling and webhook bootstrap
calls. Cold boot still drops the stale queue; a watcher reconnect preserves it.
Fixes#46621.
Co-authored-by: annguyenNous <annguyen@nousresearch.com>
Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com>
Co-authored-by: Kewe63 <Kewe63@users.noreply.github.com>
Salvage of #50098 by @srojk34, cherry-picked onto current main.
The hygiene auto-compress guard and the /compress slash command both read
compression_in_place (config flag — is in-place mode enabled?) instead of
_last_compaction_in_place (result flag — did in-place compaction actually
succeed?). Both agents are built without a session_db, so archive_and_compact
always fails silently and _last_compaction_in_place stays False. Reading the
config flag makes the guard think in-place succeeded, triggering
rewrite_transcript() which replaces the original messages with only the
compressed summary — permanent data loss.
Co-authored-by: srojk34 <srojk34@users.noreply.github.com>
The gateway pre-compression hygiene valve force-compressed any session
crossing 400 messages regardless of token usage. On large-context (1M+)
models doing many short, message-dense turns, a healthy session at ~16%
token usage could hit 400 messages and get force-compressed — and the
compression summary's stale Active Task could then bleed into the next
turn.
The valve's actual purpose is to break a death spiral: when API calls
keep disconnecting on an oversized session, no token-usage data arrives,
the token threshold never fires, and the transcript grows unbounded.
It's a count-based floor for that pathological case only. 400 was tuned
for ~200K-context models and is far too low for modern large-context
sessions. Raise the default to 5000 — still well clear of any death
spiral, but no longer firing on legitimate long conversations.
The value remains fully configurable via compression.hygiene_hard_message_limit.
Gateway Session Hygiene auto-compression destroyed the original transcript
when the throwaway hygiene agent couldn't rotate the session (#21301, P1).
The _hyg_agent is built WITHOUT a session_db, so _compress_context cannot
end-and-fork the session (its rotate block is gated on agent._session_db).
The session_id stays unchanged, and the rewrite_transcript() call ran
UNCONDITIONALLY — replacing the full original transcript with just the
head+summary list. Permanent data loss on every hygiene compaction.
Guard the rewrite behind 'rotated OR in-place' exactly like the /compress
path already does (#44794/#39704): only overwrite when a new session id
was minted or in-place compaction succeeded; otherwise preserve the
original transcript and log a warning. The token/count bookkeeping that
followed the rewrite is moved inside the guard, with no-change values in
the preserve branch.
Co-authored-by: SandroHub013 <sandrohub013@gmail.com>
Co-authored-by: WuTianyi123 <wtyopenclaw@gmail.com>
Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com>
Remove unused imports (F401) and duplicate/shadowed import
redefinitions (F811) across the codebase using ruff's safe
autofixes. No behavioral changes -- imports only.
- ~1400 safe autofixes applied across 644 files (net -1072 lines)
- __init__.py re-exports preserved (excluded from F401 removal so
public re-export surfaces stay intact)
- Re-exports that are imported or monkeypatched by tests but look
unused in their defining module are kept with explicit # noqa:
F401 (gateway/run.py load_dotenv; run_agent re-exports from
agent.message_sanitization, agent.context_compressor,
agent.retry_utils, agent.prompt_builder, agent.process_bootstrap,
agent.codex_responses_adapter)
- Unsafe F841 (unused-variable) fixes deliberately skipped -- those
can change behavior when the RHS has side effects
- ruff lints remain disabled in pyproject.toml (only PLW1514 is
selected); this is a one-time cleanup, not a config change
Verification:
- python -m compileall: clean
- pytest --collect-only: all 27161 tests collect (zero import errors)
- core entry points import clean (run_agent, model_tools, cli,
toolsets, hermes_state, batch_runner, gateway)
- static scan: every name any test imports directly from an edited
module still resolves
When auxiliary compression's summary generation returns None (aux model
errored, returned non-JSON, timed out, etc.) the compressor previously
still dropped every middle message between compress_start..compress_end
and replaced them with a static 'Summary generation was unavailable'
placeholder. The session kept going but the user silently lost N turns
of context for nothing.
New behavior: on summary failure, compress() aborts entirely — returns
the input messages unchanged and sets _last_compress_aborted=True. The
existing _summary_failure_cooldown_until gate (30-60s) keeps the aux
model from being burned on every turn. Auto-compress callers detect
the no-op (len(after) == len(before)) and stop looping. The chat is
'frozen' at its current size until the next /compress or /new.
Manual /compress (CLI + gateway) now passes force=True which clears
the cooldown so users can retry immediately after an auto-abort. If
the manual retry also fails, the user gets a visible warning telling
them nothing was dropped and how to retry.
- agent/context_compressor.py: compress() gains force= kwarg; failure
branch sets _last_compress_aborted and returns messages unchanged
instead of inserting placeholder.
- run_agent.py: _compress_context() detects abort, surfaces warning,
skips session-rotation entirely, returns messages unchanged.
- cli.py + gateway/run.py: manual /compress paths pass force=True.
- gateway/run.py: hygiene + /compress handlers detect _last_compress_aborted
and emit the new 'Compression aborted' warning (gateway.compress.aborted)
instead of the old 'N historical messages were removed' message.
- locales/*.yaml: new gateway.compress.aborted key in all 16 locales.
- tests: updated to assert the abort contract (messages preserved,
compression_count not incremented, abort flag set, no placeholder
leaked). New test_force_true_bypasses_failure_cooldown covers the
manual-retry path.
The gateway session-hygiene pre-compression safety valve had a hardcoded
400-message threshold. On long-lived sessions with short turns this was
either too high (users with aggressive compression preferences) or too
low (users with very large context models who want to keep more history
in-flight).
Add compression.hygiene_hard_message_limit (default 400) so it can be
tuned without forking the gateway.
Reported by @OP (Apr 26 feedback bundle).
## Changes
- hermes_cli/config.py: new DEFAULT_CONFIG key with 400 default
- gateway/run.py: read compression.hygiene_hard_message_limit at
hygiene-time, fall back to 400 if missing/invalid
- tests/gateway/test_session_hygiene.py: two tests — override fires at
the configured limit, default does not fire below 400
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
A misconfigured auxiliary.compression.model is a user-fixable problem that silent recovery would hide. The previous retry-on-main logic transparently swallowed aux-model failures whenever the fallback succeeded, leaving the user's broken config in place and racking up future failures.
Track the aux-model failure on the compressor alongside the existing fallback-placeholder fields:
- _last_aux_model_failure_model: str | None
- _last_aux_model_failure_error: str | None
Both are set at the moment the aux model errors (captured before summary_model is cleared for retry), regardless of whether the retry succeeds. Cleared at compress() start and on on_session_reset() so a clean run doesn't leak stale warnings.
Surface at three places:
- gateway hygiene auto-compress: ℹ note to the platform adapter (thread_id preserved)
- gateway /compress command: ℹ line appended to the reply
- CLI via _emit_warning: deduped on (model, error) so repeat compactions don't spam
Distinct from the existing ⚠️ dropped-turns warning — different severity, different emoji, explicit 'context is intact' reassurance.
Address review feedback on PR #16333:
1. The hygiene-path warning send was missing metadata=_hyg_meta. On
Telegram topics / Slack threads / Discord threads the warning would
land in the main channel instead of the originating thread. Now
reuses the same _hyg_meta dict already computed for the hygiene
compaction itself.
2. New gateway-level test
test_session_hygiene_warns_user_when_summary_generation_fails
verifies end-to-end:
- When the compressor's _last_summary_fallback_used flag is True,
the gateway invokes adapter.send() exactly once.
- The warning message includes the dropped count and the underlying
error string.
- metadata={'thread_id': ...} is propagated so the warning lands
in the originating topic/thread.
Tests: 20 gateway hygiene + 54 context_compressor — all pass.
Production fixes:
- Add clear_session_context() to hermes_logging.py (fixes 48 teardown errors)
- Add clear_session() to tools/approval.py (fixes 9 setup errors)
- Add SyncError M_UNKNOWN_TOKEN check to Matrix _sync_loop (bug fix)
- Fall back to inline api_key in named custom providers when key_env
is absent (runtime_provider.py)
Test fixes:
- test_memory_user_id: use builtin+external provider pair, fix honcho
peer_name override test to match production behavior
- test_display_config: remove TestHelpers for non-existent functions
- test_auxiliary_client: fix OAuth tokens to match _is_oauth_token
patterns, replace get_vision_auxiliary_client with resolve_vision_provider_client
- test_cli_interrupt_subagent: add missing _execution_thread_id attr
- test_compress_focus: add model/provider/api_key/base_url/api_mode
to mock compressor
- test_auth_provider_gate: add autouse fixture to clean Anthropic env
vars that leak from CI secrets
- test_opencode_go_in_model_list: accept both 'built-in' and 'hermes'
source (models.dev API unavailable in CI)
- test_email: verify email Platform enum membership instead of source
inspection (build_channel_directory now uses dynamic enum loop)
- test_feishu: add bot_added/bot_deleted handler mocks to _Builder
- test_ws_auth_retry: add AsyncMock for sync_store.get_next_batch,
add _pending_megolm and _joined_rooms to Matrix adapter mocks
- test_restart_drain: monkeypatch-delete INVOCATION_ID (systemd sets
this in CI, changing the restart call signature)
- test_session_hygiene: add user_id to SessionSource
- test_session_env: use relative baseline for contextvar clear check
(pytest-xdist workers share context)
Auto-compression still runs silently in the background with server-side
logging, but no longer sends messages to the user's chat about it.
Removed:
- 'Session is large... Auto-compressing' pre-compression notification
- 'Compressed: N → M messages' post-compression notification
- 'Session is still very large after compression' warning
- 'Auto-compression failed' warning
- Rate-limit tracking (only existed for these warnings)
* feat: add /yolo slash command to toggle dangerous command approvals
Adds a /yolo command that toggles HERMES_YOLO_MODE at runtime, skipping
all dangerous command approval prompts for the current session. Works in
both CLI and gateway (Telegram, Discord, etc.).
- /yolo -> ON: all commands auto-approved, no confirmation prompts
- /yolo -> OFF: normal approval flow restored
The --yolo CLI flag already existed for launch-time opt-in. This adds
the ability to toggle mid-session without restarting.
Session-scoped — resets when the process ends. Uses the existing
HERMES_YOLO_MODE env var that check_all_command_guards() already
respects.
* fix: prevent context pressure warning spam (agent loop + gateway rate-limit)
Two complementary fixes for repeated context pressure warnings spamming
gateway users (Telegram, Discord, etc.):
1. Agent-level loop fix (run_agent.py):
After compression, only reset _context_pressure_warned if the
post-compression estimate is actually below the 85% warning level.
Previously the flag was unconditionally reset, causing the warning
to re-fire every loop iteration when compression couldn't reduce
below 85% of the threshold (e.g. very low threshold like 15%,
or system prompt alone exceeds the warning level).
2. Gateway-level rate-limit (gateway/run.py, salvaged from PR #3786):
Per-chat_id cooldown of 1 hour on compression warning messages.
Both warning paths ('still large after compression' and 'compression
failed') are gated. Defense-in-depth — even if the agent-level fix
has edge cases, users won't see more than one warning per hour.
Co-authored-by: dlkakbs <dlkakbs@users.noreply.github.com>
---------
Co-authored-by: dlkakbs <dlkakbs@users.noreply.github.com>
* fix(gateway): preserve full transcript on /compress instead of overwriting
The /compress command calls _compress_context() which correctly ends the
old session (preserving its full transcript in SQLite) and creates a new
session_id for the continuation. However, it then immediately called
rewrite_transcript() on the OLD session_id, overwriting the preserved
transcript with the compressed version — destroying searchable history.
Auto-compression (triggered by context pressure) does not have this bug
because the gateway already handles the session_id swap via the
agent.session_id != session_id check after _run_agent_sync.
Fix: after _compress_context creates the new session, write the compressed
messages into the NEW session_id and update the session store pointer.
The old session's full transcript stays intact and searchable via
session_search.
Before: /compress destroys original messages, session_search can't find
details from compressed portions.
After: /compress behaves like /new for history — full transcript preserved,
compressed context for the live session.
* fix(gateway): preserve transcript on /compress and hygiene compression
Apply session_id swap after _compress_context in both /compress handler
and hygiene pre-compression. _compress_context creates a new session
(ending the old one), but both paths were calling rewrite_transcript on
the OLD session_id — overwriting the preserved transcript and destroying
searchable history.
Now follows the same pattern as the auto-compression handler (lines
5415-5423): detect the new session_id, update the session store entry,
and write compressed messages to the new session.
Also fix FakeCompressAgent test mock to include session_id attribute
and simulate the session_id change that real _compress_context performs.
Co-authored-by: MacroAnarchy <MacroAnarchy@users.noreply.github.com>
---------
Co-authored-by: MacroAnarchy <MacroAnarchy@users.noreply.github.com>
The previous commit capped the 1.4x at 95% of context, but the multiplier
itself is unnecessary and confusing:
85% threshold × 1.4 = 119% of context → never fires
95% warn × 1.4 = 133% of context → never warns
The 85% hygiene threshold already provides ample headroom over the agent's
own 50% compressor. Even if rough estimates overestimate by 50%, hygiene
would fire at ~57% actual usage — safe and harmless.
Remove the multiplier entirely. Both actual and estimated token paths
now use the same 85% / 95% thresholds. Update tests and comments.
Three bugs in gateway session hygiene pre-compression caused 'Session too
large' errors for ~200K context models like GLM-5-turbo on z.ai:
1. Gateway hygiene called get_model_context_length(model) without passing
config_context_length, provider, or base_url — so user overrides like
model.context_length: 180000 were ignored, and provider-aware detection
(models.dev, z.ai endpoint) couldn't fire. The agent's own compressor
correctly passed all three (run_agent.py line 1038).
2. The 1.4x safety factor on rough token estimates pushed the compression
threshold above the model's actual context limit:
200K * 0.85 * 1.4 = 238K > 200K (model limit)
So hygiene never compressed, sessions grew past the limit, and the API
rejected the request.
3. Same issue for the warn threshold: 200K * 0.95 * 1.4 = 266K.
Fix:
- Read model.context_length, provider, and base_url from config.yaml
(same as run_agent.py does) and pass them to get_model_context_length()
- Resolve provider/base_url from runtime when not in config
- Cap the 1.4x-adjusted compress threshold at 95% of context_length
- Cap the 1.4x-adjusted warn threshold at context_length
Affects: z.ai GLM-5/GLM-5-turbo, any ~200K or smaller context model
where the 1.4x factor would push 85% above 100%.
Ref: Discord report from Ddox — glm-5-turbo on z.ai coding plan
The gateway had a SEPARATE compression system ('session hygiene')
with hardcoded thresholds (100k tokens / 200 messages) that were
completely disconnected from the model's context length and the
user's compression config in config.yaml. This caused premature
auto-compression on Telegram/Discord — triggering at ~60k tokens
(from the 200-message threshold) or inconsistent token counts.
Changes:
- Gateway hygiene now reads model name from config.yaml and uses
get_model_context_length() to derive the actual context limit
- Compression threshold comes from compression.threshold in
config.yaml (default 0.85), same as the agent's ContextCompressor
- Removed the message-count-based trigger (was redundant and caused
false positives in tool-heavy sessions)
- Removed the undocumented session_hygiene config section — the
standard compression.* config now controls everything
- Env var overrides (CONTEXT_COMPRESSION_THRESHOLD,
CONTEXT_COMPRESSION_ENABLED) are respected
- Warn threshold is now 95% of model context (was hardcoded 200k)
- Updated tests to verify model-aware thresholds, scaling across
models, and that message count alone no longer triggers compression
For claude-opus-4.6 (200k context) at 85% threshold: gateway
hygiene now triggers at 170k tokens instead of the old 100k.
Long-lived gateway sessions can accumulate enough history that every new
message rehydrates an oversized transcript, causing repeated truncation
failures (finish_reason=length).
Add a session hygiene check in _handle_message that runs right after
loading the transcript and before invoking the agent:
1. Estimate message count and rough token count of the transcript
2. If above configurable thresholds (default: 200 msgs or 100K tokens),
auto-compress the transcript proactively
3. Notify the user about the compression with before/after stats
4. If still above warn threshold (default: 200K tokens) after
compression, suggest /reset
5. If compression fails on a dangerously large session, warn the user
to use /compress or /reset manually
Thresholds are configurable via config.yaml:
session_hygiene:
auto_compress_tokens: 100000
auto_compress_messages: 200
warn_tokens: 200000
This complements the agent's existing preflight compression (which
runs inside run_conversation) by catching pathological sessions at
the gateway layer before the agent is even created.
Includes 12 tests for threshold detection and token estimation.
HexLab98