fix(gateway): respect OPENAI_API_KEY env var to bypass OAuth - #47
Closed
mjshiggins wants to merge 1 commit into
Closed
fix(gateway): respect OPENAI_API_KEY env var to bypass OAuth#47mjshiggins wants to merge 1 commit into
mjshiggins wants to merge 1 commit into
Conversation
The gateway was forcing OAuth authentication for all Nous Research URLs, overriding user-provided API keys from environment variables. This caused failures when Nous Portal credits were exhausted or when users wanted to use direct API keys. Changes: - Check for OPENAI_API_KEY before triggering OAuth flow - Only mint agent keys when no explicit API key is provided - Allows direct API usage without portal authentication Fixes issues where users couldn't use kimi-k2.5 or other models due to OAuth credit exhaustion blocking all gateway requests.
Contributor
|
Fixed earlier! |
malaiwah
pushed a commit
to malaiwah/hermes-agent
that referenced
this pull request
Apr 5, 2026
Previous commit had double-escaped backslashes (\\) which broke the Dockerfile syntax. This fixes the RUN instructions to use proper single backslashes for line continuation. Fixes build failure in run NousResearch#47.
malaiwah
pushed a commit
to malaiwah/hermes-agent
that referenced
this pull request
Apr 11, 2026
Previous commit had double-escaped backslashes (\\) which broke the Dockerfile syntax. This fixes the RUN instructions to use proper single backslashes for line continuation. Fixes build failure in run NousResearch#47.
3 tasks
teknium1
added a commit
that referenced
this pull request
May 29, 2026
…kew) (#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call #47/#48/#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
KKT-OPT
pushed a commit
to KKT-OPT/hermes-agent
that referenced
this pull request
May 31, 2026
…kew) (NousResearch#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-NousResearch#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-NousResearch#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call NousResearch#47/NousResearch#48/NousResearch#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
alt-glitch
pushed a commit
that referenced
this pull request
Jun 14, 2026
…kew) (#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call #47/#48/#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
T02200059
pushed a commit
to T02200059/hermes-agent
that referenced
this pull request
Jun 18, 2026
…kew) (NousResearch#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-NousResearch#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-NousResearch#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call NousResearch#47/NousResearch#48/NousResearch#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
|
AFK-V2 commit 74c3924ac fixes the core routing bugs from the WhatsApp regression transcript. Fixed:
7 new regression tests, all passing. Audit report at docs/reports/REAL_USER_REGRESSION_AUDIT.md. Remaining: contact lookup without Google Workspace still returns a clean error rather than looping. /new consistency is expected behavior — no code change needed. |
waefrebeorn
pushed a commit
to waefrebeorn/slermes
that referenced
this pull request
Jul 2, 2026
…kew) (NousResearch#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-NousResearch#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-NousResearch#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call NousResearch#47/NousResearch#48/NousResearch#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
santhreal
pushed a commit
to santhreal/hermes-agent
that referenced
this pull request
Jul 13, 2026
…kew) (NousResearch#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-NousResearch#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-NousResearch#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call NousResearch#47/NousResearch#48/NousResearch#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
donbowman
pushed a commit
to donbowman/hermes-agent
that referenced
this pull request
Jul 13, 2026
…kew) (NousResearch#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-NousResearch#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-NousResearch#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call NousResearch#47/NousResearch#48/NousResearch#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
Gravezzz
pushed a commit
to Gravezzz/hermes-agent
that referenced
this pull request
Jul 21, 2026
…kew) (NousResearch#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-NousResearch#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-NousResearch#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call NousResearch#47/NousResearch#48/NousResearch#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
Soju06
added a commit
to Soju06/hermes-agent
that referenced
this pull request
Jul 28, 2026
Meraniya
pushed a commit
to Meraniya/hermes-agent
that referenced
this pull request
Aug 6, 2026
…ousResearch#47) Claude-Session: https://claude.ai/code/session_01Pnuhd75aEGWogbsguSAuez Co-authored-by: Claude <noreply@anthropic.com>
leewenjie
pushed a commit
to leewenjie/hermes-agent
that referenced
this pull request
Aug 7, 2026
…kew) (NousResearch#34475) A process running mismatched module versions — conversation_compression.py re-imported with the post-NousResearch#34351 lock code while a long-lived hermes_state.SessionDB stays bound to the pre-NousResearch#34351 class in memory — has the try_acquire_compression_lock call site but not the method. The AttributeError it raises is NOT a sqlite3.Error, so the method's own fail-open guard never runs; the exception escapes to the outer agent loop, which prints the error and retries. Compression never succeeds, the token count never drops, and the loop re-triggers compaction forever (the 'API call NousResearch#47/NousResearch#48/NousResearch#49 ... has no attribute try_acquire_compression_lock' spin a user hit after an update). Wrap the lock acquire so any unexpected exception fails OPEN: skip locking and proceed with compression. Skipping the lock risks a rare concurrent-compression session fork; an infinite no-progress loop that never compresses at all is strictly worse. The remediation hint in the log points at the real fix (restart / hermes update to resync the stale module). Also guards get_compression_lock_holder against the same skew. Adds a regression test simulating the version skew (real SessionDB wrapped so only the lock methods raise AttributeError) — asserts _compress_context proceeds and rotates instead of raising.
19 tasks
4 tasks
blut-agent
pushed a commit
to blut-agent/hermes-agent-fork
that referenced
this pull request
Aug 11, 2026
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 NousResearch#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.
Closed
33hodl
pushed a commit
to 33hodl/hermes-agent
that referenced
this pull request
Aug 12, 2026
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 NousResearch#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.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
(generated by Hermes, haven’t reviewed myself)
The gateway was forcing OAuth authentication for all Nous Research URLs, overriding user-provided API keys from environment variables. This caused failures when Nous Portal credits were exhausted or when users wanted to use direct API keys.
Changes: