fix(agent_init): correct misleading sub-64K context_length error message - #53569
Merged
Conversation
The error raised when a model's context window is below the 64K minimum advertised "or set model.context_length in config.yaml to override" — but the guard intentionally has no sub-64K escape hatch. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom). The misleading clause invited a cluster of dup PRs (#11097, #11110, #8962, #9142, #37548) all trying to wire an override that we don't want. Reword to state the real options: pick a >=64K model, or — if your local server under-reports its true window — declare the real value (which must itself be >=64K). Guard behavior is unchanged.
This was referenced Jun 27, 2026
Contributor
🔎 Lint report:
|
| Rule | Count |
|---|---|
invalid-assignment |
1 |
First entries
tests/run_agent/test_credits_notices_toggle.py:76: [invalid-assignment] invalid-assignment: Object of type `None` is not assignable to attribute `_credits_session_start_micros` of type `int`
✅ Fixed issues (2):
| Rule | Count |
|---|---|
unresolved-attribute |
2 |
First entries
tests/run_agent/test_credits_notices_toggle.py:76: [unresolved-attribute] unresolved-attribute: Unresolved attribute `_credits_session_start_micros` on type `AIAgent`
run_agent.py:3002: [unresolved-attribute] unresolved-attribute: Object of type `Self@get_credits_spent_micros` has no attribute `_credits_session_start_micros`
Unchanged: 6031 pre-existing issues carried over.
Diagnostics are surfaced as warnings — this check never fails the build.
alt-glitch
added
type/bug
pai-scaffolde
pushed a commit
to pai-scaffolde/hermes-agent
that referenced
this pull request
Jun 28, 2026
…age (NousResearch#53569) The error raised when a model's context window is below the 64K minimum advertised "or set model.context_length in config.yaml to override" — but the guard intentionally has no sub-64K escape hatch. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom). The misleading clause invited a cluster of dup PRs (NousResearch#11097, NousResearch#11110, NousResearch#8962, NousResearch#9142, NousResearch#37548) all trying to wire an override that we don't want. Reword to state the real options: pick a >=64K model, or — if your local server under-reports its true window — declare the real value (which must itself be >=64K). Guard behavior is unchanged.
waefrebeorn
pushed a commit
to waefrebeorn/slermes
that referenced
this pull request
Jul 2, 2026
…age (NousResearch#53569) The error raised when a model's context window is below the 64K minimum advertised "or set model.context_length in config.yaml to override" — but the guard intentionally has no sub-64K escape hatch. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom). The misleading clause invited a cluster of dup PRs (NousResearch#11097, NousResearch#11110, NousResearch#8962, NousResearch#9142, NousResearch#37548) all trying to wire an override that we don't want. Reword to state the real options: pick a >=64K model, or — if your local server under-reports its true window — declare the real value (which must itself be >=64K). Guard behavior is unchanged.
habarmc1223-sudo
pushed a commit
to habarmc1223-sudo/hermes-agent-fluxmem
that referenced
this pull request
Jul 8, 2026
…age (NousResearch#53569) The error raised when a model's context window is below the 64K minimum advertised "or set model.context_length in config.yaml to override" — but the guard intentionally has no sub-64K escape hatch. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom). The misleading clause invited a cluster of dup PRs (NousResearch#11097, NousResearch#11110, NousResearch#8962, NousResearch#9142, NousResearch#37548) all trying to wire an override that we don't want. Reword to state the real options: pick a >=64K model, or — if your local server under-reports its true window — declare the real value (which must itself be >=64K). Guard behavior is unchanged.
santhreal
pushed a commit
to santhreal/hermes-agent
that referenced
this pull request
Jul 13, 2026
…age (NousResearch#53569) The error raised when a model's context window is below the 64K minimum advertised "or set model.context_length in config.yaml to override" — but the guard intentionally has no sub-64K escape hatch. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom). The misleading clause invited a cluster of dup PRs (NousResearch#11097, NousResearch#11110, NousResearch#8962, NousResearch#9142, NousResearch#37548) all trying to wire an override that we don't want. Reword to state the real options: pick a >=64K model, or — if your local server under-reports its true window — declare the real value (which must itself be >=64K). Guard behavior is unchanged.
Gravezzz
pushed a commit
to Gravezzz/hermes-agent
that referenced
this pull request
Jul 21, 2026
…age (NousResearch#53569) The error raised when a model's context window is below the 64K minimum advertised "or set model.context_length in config.yaml to override" — but the guard intentionally has no sub-64K escape hatch. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom). The misleading clause invited a cluster of dup PRs (NousResearch#11097, NousResearch#11110, NousResearch#8962, NousResearch#9142, NousResearch#37548) all trying to wire an override that we don't want. Reword to state the real options: pick a >=64K model, or — if your local server under-reports its true window — declare the real value (which must itself be >=64K). Guard behavior is unchanged.
leewenjie
pushed a commit
to leewenjie/hermes-agent
that referenced
this pull request
Aug 7, 2026
…age (NousResearch#53569) The error raised when a model's context window is below the 64K minimum advertised "or set model.context_length in config.yaml to override" — but the guard intentionally has no sub-64K escape hatch. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom). The misleading clause invited a cluster of dup PRs (NousResearch#11097, NousResearch#11110, NousResearch#8962, NousResearch#9142, NousResearch#37548) all trying to wire an override that we don't want. Reword to state the real options: pick a >=64K model, or — if your local server under-reports its true window — declare the real value (which must itself be >=64K). Guard behavior is unchanged.
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
2 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.
Summary
The sub-64K context-window guard now tells the truth: there is no escape hatch for windows below the 64K minimum. Sub-64K models are rejected by design (tool schemas + system prompt need the headroom).
The old
ValueErroradvertised "or setmodel.context_lengthin config.yaml to override" — but the guard intentionally has no sub-64K override. That misleading clause kept generating duplicate PRs from operators taking the message at its word.Changes
agent/agent_init.py: reword the below-minimumValueError. Drop the false "override" promise. State the real options: pick a ≥64K model, or — if your local server under-reports its true window — declare the real value (which must itself be ≥64K). Guard behavior is unchanged.Root cause
The error string described an override path that was never intended to exist. The 64K floor is deliberate, not a bug. The defect was purely the message.
Validation
below the minimumsubstring (asserted bytest_compression_feasibility.py:121)< 64KraiseCloses the misleading-message root cause behind #11096 (Bug 1) and the dup PR cluster (#11097, #11110, #8962, #9142, #37548). Bug 2 (#11098) was declined-by-design; Bug 3 (#11103) already fixed on main via
_enable_from_env().Infographic