fix: skip model/API-key validation for oracle agent#173
Merged
xdotli merged 2 commits intobenchflow-ai:mainfrom Apr 21, 2026
Merged
fix: skip model/API-key validation for oracle agent#173xdotli merged 2 commits intobenchflow-ai:mainfrom
xdotli merged 2 commits intobenchflow-ai:mainfrom
Conversation
The oracle agent runs solution/solve.sh and never calls an LLM, but resolve_agent_env() was validating API keys for whatever model the CLI defaulted to (claude-haiku-4-5-20251001). This made `bench eval create -a oracle` fail without ANTHROPIC_API_KEY set, even though oracle doesn't need it.
Contributor
Author
|
CI failed on main, not triggered by this PR. |
EYH0602
commented
Apr 21, 2026
Contributor
Author
EYH0602
left a comment
EYH0602
left a comment
There was a problem hiding this comment.
PR #173 fix is installed and works for its intended purpose (OAuth token as alternative auth), but it doesn't help the oracle case — oracle needs no model/key at all, yet benchflow always forces DEFAULT_MODEL = "claude-haiku-4-5-20251001" (in job.py:141). When you run bench eval create -t <task> -a oracle without -m, the CLI does model=model or DEFAULT_MODEL (cli/eval.py:235), which always falls back to haiku, triggering the API key validation even though oracle just runs solve.sh and never calls any LLM.
This is a separate bug worth tracking — the oracle agent should either skip model/API-key validation entirely or not have a model assigned by default.
Move the fix from resolve_agent_env to the CLI layer: oracle runs solve.sh and never calls an LLM, so it should not receive DEFAULT_MODEL at all. Both _run_single and _run_batch now pass model=None for oracle. Widen JobConfig.model to str | None to support this.
Contributor
Author
|
Moved the fix to the CLI layer as suggested. Oracle now gets Changes in
|
Member
|
/review |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
EYH0602
commented
Apr 21, 2026
Contributor
Author
EYH0602
left a comment
EYH0602
left a comment
There was a problem hiding this comment.
The fix in cli/eval.py is correct, but bench eval create actually dispatches through cli/main.py:707 (eval_create registered on eval_app), not cli/eval.py. That code path still has the unfixed model or DEFAULT_MODEL on lines 763, 769, and 780. The same oracle skip needs to be applied there too.
Member
should we open another pr? |
Contributor
Author
I think so @xdotli , should I do it? |
Member
|
Sure!
…On Tue, Apr 21, 2026 at 6:05 PM, Yifeng He < ***@***.*** > wrote:
*EYH0602* left a comment (benchflow-ai/ benchflow#173) (
#173?email_source=notifications&email_token=AMLDGK4J3RZVNC3EX2LL7334W7WENA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTIMRZGIYTKNRSHA42M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJNLQOJPWG33NNVSW45C7N5YGK3S7MNWGSY3L#issuecomment-4292156289
)
>
>>
>>
>> The fix in cli/ eval. py ( http://cli/eval.py ) is correct, but bench eval
>> create actually dispatches through cli/ main. py:707 (
>> http://cli/main.py:707 ) ( eval_create registered on eval_app ), not cli/ eval.
>> py ( http://cli/eval.py ). That code path still has the unfixed model or
>> DEFAULT_MODEL on lines 763, 769, and 780. The same oracle skip needs to be
>> applied there too.
>>
>>
>
>
>
> should we open another pr?
>
>
>
>>
>>
>> The fix in cli/ eval. py ( http://cli/eval.py ) is correct, but bench eval
>> create actually dispatches through cli/ main. py:707 (
>> http://cli/main.py:707 ) ( eval_create registered on eval_app ), not cli/ eval.
>> py ( http://cli/eval.py ). That code path still has the unfixed model or
>> DEFAULT_MODEL on lines 763, 769, and 780. The same oracle skip needs to be
>> applied there too.
>>
>>
>
>
>
> should we open another pr?
>
>
>
>>
>>
>> The fix in cli/ eval. py ( http://cli/eval.py ) is correct, but bench eval
>> create actually dispatches through cli/ main. py:707 (
>> http://cli/main.py:707 ) ( eval_create registered on eval_app ), not cli/ eval.
>> py ( http://cli/eval.py ). That code path still has the unfixed model or
>> DEFAULT_MODEL on lines 763, 769, and 780. The same oracle skip needs to be
>> applied there too.
>>
>>
>
>
>
> should we open another pr?
>
>
I think so @ xdotli ( https://github.com/xdotli ) , should I do it?
—
Reply to this email directly, view it on GitHub (
#173?email_source=notifications&email_token=AMLDGK4J3RZVNC3EX2LL7334W7WENA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTIMRZGIYTKNRSHA42M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJNLQOJPWG33NNVSW45C7N5YGK3S7MNWGSY3L#issuecomment-4292156289
) , or unsubscribe (
https://github.com/notifications/unsubscribe-auth/AMLDGK3LRZTKJ4TVKZO5ZPL4W7WENAVCNFSM6AAAAACYBPXXZKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHM2DEOJSGE2TMMRYHE
).
You are receiving this because you were mentioned. Message ID: <benchflow-ai/benchflow/pull/173/c4292156289
@ github. com>
|
5 tasks
xdotli
pushed a commit
that referenced
this pull request
Apr 22, 2026
PR #173 moved the oracle/DEFAULT_MODEL guard from resolve_agent_env to cli/eval.py, but cli/eval.py is orphaned (never imported into the live CLI), so `bench eval create` still passes DEFAULT_MODEL to oracle and trips ANTHROPIC_API_KEY validation. Three changes: - Restore the `agent != "oracle"` guard in resolve_agent_env so the chokepoint defends against any caller that forwards a model. - Delete the orphan cli/eval.py and its tests — the live eval_create lives in cli/main.py and was the actual code path users hit. - Add effective_model(agent, model) helper, change JobConfig.model default to None, replace seven `model or DEFAULT_MODEL` sites in cli/main.py and job.py YAML loaders so oracle gets honest model=None end-to-end (in result/summary JSON, prints, and downstream Trial). Regression test in test_resolve_env_helpers.py pins the chokepoint by calling resolve_agent_env("oracle", DEFAULT_MODEL, {}) with no API key and no host auth — verified to fail on main with the user-facing ANTHROPIC_API_KEY error and pass after the fix.
xdotli
pushed a commit
that referenced
this pull request
Apr 22, 2026
Bundle 14 tests in tests/test_oracle_chokepoint.py that pin each layer of the prior fix at the right altitude: - TestOrphanRemoval — cli/eval.py is gone (ModuleNotFoundError) and no src/ file references benchflow.cli.eval, guarding against a future re-introduction that could swallow the next bug fix the same way. - TestEvalCreateRouting — `bench eval create` callback lives in cli/main.py:eval_create. Pins the architectural fact PR #173 missed. - TestEffectiveModel — unit tests for the helper: oracle drops model, non-oracle falls back to DEFAULT_MODEL, empty string treated as unset. - TestOracleYamlLoaders — Job.from_yaml(oracle config) → model is None for both native and Harbor formats; non-oracle backwards-compat preserved. - TestEvalCreateOracleCLI — end-to-end: live eval_create(agent="oracle") with no API key in env does not raise. Mocks Trial.create and resets the asyncio loop after to avoid polluting pre-existing tests that use the deprecated asyncio.get_event_loop() pattern. Verified to fail on main in the right shape: 9 of 14 fail (each pinning a deleted/added behavior), 5 pass (asserting structural facts already true). The CLI test fails on main with the user-reported error "ANTHROPIC_API_KEY required for model 'claude-haiku-4-5-20251001'…".
4 tasks
xdotli
added a commit
that referenced
this pull request
Apr 25, 2026
* fix: skip model/API-key validation for oracle agent The oracle agent runs solution/solve.sh and never calls an LLM, but resolve_agent_env() was validating API keys for whatever model the CLI defaulted to (claude-haiku-4-5-20251001). This made `bench eval create -a oracle` fail without ANTHROPIC_API_KEY set, even though oracle doesn't need it. * fix: don't assign default model to oracle agent Move the fix from resolve_agent_env to the CLI layer: oracle runs solve.sh and never calls an LLM, so it should not receive DEFAULT_MODEL at all. Both _run_single and _run_batch now pass model=None for oracle. Widen JobConfig.model to str | None to support this. * fix: oracle agent — chokepoint guard, drop orphan eval CLI, helper PR #173 moved the oracle/DEFAULT_MODEL guard from resolve_agent_env to cli/eval.py, but cli/eval.py is orphaned (never imported into the live CLI), so `bench eval create` still passes DEFAULT_MODEL to oracle and trips ANTHROPIC_API_KEY validation. Three changes: - Restore the `agent != "oracle"` guard in resolve_agent_env so the chokepoint defends against any caller that forwards a model. - Delete the orphan cli/eval.py and its tests — the live eval_create lives in cli/main.py and was the actual code path users hit. - Add effective_model(agent, model) helper, change JobConfig.model default to None, replace seven `model or DEFAULT_MODEL` sites in cli/main.py and job.py YAML loaders so oracle gets honest model=None end-to-end (in result/summary JSON, prints, and downstream Trial). Regression test in test_resolve_env_helpers.py pins the chokepoint by calling resolve_agent_env("oracle", DEFAULT_MODEL, {}) with no API key and no host auth — verified to fail on main with the user-facing ANTHROPIC_API_KEY error and pass after the fix. * test: regression suite pinning oracle chokepoint + orphan removal Bundle 14 tests in tests/test_oracle_chokepoint.py that pin each layer of the prior fix at the right altitude: - TestOrphanRemoval — cli/eval.py is gone (ModuleNotFoundError) and no src/ file references benchflow.cli.eval, guarding against a future re-introduction that could swallow the next bug fix the same way. - TestEvalCreateRouting — `bench eval create` callback lives in cli/main.py:eval_create. Pins the architectural fact PR #173 missed. - TestEffectiveModel — unit tests for the helper: oracle drops model, non-oracle falls back to DEFAULT_MODEL, empty string treated as unset. - TestOracleYamlLoaders — Job.from_yaml(oracle config) → model is None for both native and Harbor formats; non-oracle backwards-compat preserved. - TestEvalCreateOracleCLI — end-to-end: live eval_create(agent="oracle") with no API key in env does not raise. Mocks Trial.create and resets the asyncio loop after to avoid polluting pre-existing tests that use the deprecated asyncio.get_event_loop() pattern. Verified to fail on main in the right shape: 9 of 14 fail (each pinning a deleted/added behavior), 5 pass (asserting structural facts already true). The CLI test fails on main with the user-reported error "ANTHROPIC_API_KEY required for model 'claude-haiku-4-5-20251001'…". * fix: restore cli/eval.py and test_eval_cli.py, apply oracle guard The previous commit deleted cli/eval.py and its tests as orphans, but they are intentionally kept. Restore both from main, update eval.py to use the effective_model() helper for the oracle chokepoint fix, and replace the "module is gone" regression test with a guard that cli/main.py does not import cli/eval (the actual invariant). * docs: clarify cli/eval.py and test_eval_cli.py are not wired into live CLI --------- Co-authored-by: Yifeng He <yfhe.prsn@gmail.com>
xdotli
added a commit
that referenced
this pull request
Apr 25, 2026
* fix: skip model/API-key validation for oracle agent The oracle agent runs solution/solve.sh and never calls an LLM, but resolve_agent_env() was validating API keys for whatever model the CLI defaulted to (claude-haiku-4-5-20251001). This made `bench eval create -a oracle` fail without ANTHROPIC_API_KEY set, even though oracle doesn't need it. * fix: don't assign default model to oracle agent Move the fix from resolve_agent_env to the CLI layer: oracle runs solve.sh and never calls an LLM, so it should not receive DEFAULT_MODEL at all. Both _run_single and _run_batch now pass model=None for oracle. Widen JobConfig.model to str | None to support this. * fix: oracle agent — chokepoint guard, drop orphan eval CLI, helper PR #173 moved the oracle/DEFAULT_MODEL guard from resolve_agent_env to cli/eval.py, but cli/eval.py is orphaned (never imported into the live CLI), so `bench eval create` still passes DEFAULT_MODEL to oracle and trips ANTHROPIC_API_KEY validation. Three changes: - Restore the `agent != "oracle"` guard in resolve_agent_env so the chokepoint defends against any caller that forwards a model. - Delete the orphan cli/eval.py and its tests — the live eval_create lives in cli/main.py and was the actual code path users hit. - Add effective_model(agent, model) helper, change JobConfig.model default to None, replace seven `model or DEFAULT_MODEL` sites in cli/main.py and job.py YAML loaders so oracle gets honest model=None end-to-end (in result/summary JSON, prints, and downstream Trial). Regression test in test_resolve_env_helpers.py pins the chokepoint by calling resolve_agent_env("oracle", DEFAULT_MODEL, {}) with no API key and no host auth — verified to fail on main with the user-facing ANTHROPIC_API_KEY error and pass after the fix. * test: regression suite pinning oracle chokepoint + orphan removal Bundle 14 tests in tests/test_oracle_chokepoint.py that pin each layer of the prior fix at the right altitude: - TestOrphanRemoval — cli/eval.py is gone (ModuleNotFoundError) and no src/ file references benchflow.cli.eval, guarding against a future re-introduction that could swallow the next bug fix the same way. - TestEvalCreateRouting — `bench eval create` callback lives in cli/main.py:eval_create. Pins the architectural fact PR #173 missed. - TestEffectiveModel — unit tests for the helper: oracle drops model, non-oracle falls back to DEFAULT_MODEL, empty string treated as unset. - TestOracleYamlLoaders — Job.from_yaml(oracle config) → model is None for both native and Harbor formats; non-oracle backwards-compat preserved. - TestEvalCreateOracleCLI — end-to-end: live eval_create(agent="oracle") with no API key in env does not raise. Mocks Trial.create and resets the asyncio loop after to avoid polluting pre-existing tests that use the deprecated asyncio.get_event_loop() pattern. Verified to fail on main in the right shape: 9 of 14 fail (each pinning a deleted/added behavior), 5 pass (asserting structural facts already true). The CLI test fails on main with the user-reported error "ANTHROPIC_API_KEY required for model 'claude-haiku-4-5-20251001'…". * fix: restore cli/eval.py and test_eval_cli.py, apply oracle guard The previous commit deleted cli/eval.py and its tests as orphans, but they are intentionally kept. Restore both from main, update eval.py to use the effective_model() helper for the oracle chokepoint fix, and replace the "module is gone" regression test with a guard that cli/main.py does not import cli/eval (the actual invariant). * docs: clarify cli/eval.py and test_eval_cli.py are not wired into live CLI * docs(plan): add plan to fix sandbox io problem * test: lock sandbox setup contract Plan step 1/6: Lock the new sandbox contract in tests * fix: stop copying root tool installs into sandbox home Plan step 2/6: Narrow setup_sandbox_user() to user state only * refactor: derive sandbox home dirs from registry config Plan step 3/6: Align registry semantics with the new contract * refactor: symlink skills into sandbox, enforce shared install prefixes Replace per-trial skill-tree copies with ln -sfn into a shared /skills (or task skills_dir) root, drop skill_paths from get_sandbox_home_dirs(), and add registry + sandbox-setup invariants that keep agent binaries on /usr/local/* rather than /root-only home paths. Updates task-authoring and api-reference docs to describe the new lightweight sandbox contract. * chore: remove completed sandbox plan doc --------- Co-authored-by: Xiangyi Li <xiangyi@benchmarkthing.com> Co-authored-by: Xiangyi Li <xiangyi@benchflow.ai>
4 tasks
EYH0602
added a commit
to EYH0602/benchflow
that referenced
this pull request
Apr 25, 2026
* fix: skip model/API-key validation for oracle agent The oracle agent runs solution/solve.sh and never calls an LLM, but resolve_agent_env() was validating API keys for whatever model the CLI defaulted to (claude-haiku-4-5-20251001). This made `bench eval create -a oracle` fail without ANTHROPIC_API_KEY set, even though oracle doesn't need it. * fix: don't assign default model to oracle agent Move the fix from resolve_agent_env to the CLI layer: oracle runs solve.sh and never calls an LLM, so it should not receive DEFAULT_MODEL at all. Both _run_single and _run_batch now pass model=None for oracle. Widen JobConfig.model to str | None to support this. * fix: oracle agent — chokepoint guard, drop orphan eval CLI, helper PR benchflow-ai#173 moved the oracle/DEFAULT_MODEL guard from resolve_agent_env to cli/eval.py, but cli/eval.py is orphaned (never imported into the live CLI), so `bench eval create` still passes DEFAULT_MODEL to oracle and trips ANTHROPIC_API_KEY validation. Three changes: - Restore the `agent != "oracle"` guard in resolve_agent_env so the chokepoint defends against any caller that forwards a model. - Delete the orphan cli/eval.py and its tests — the live eval_create lives in cli/main.py and was the actual code path users hit. - Add effective_model(agent, model) helper, change JobConfig.model default to None, replace seven `model or DEFAULT_MODEL` sites in cli/main.py and job.py YAML loaders so oracle gets honest model=None end-to-end (in result/summary JSON, prints, and downstream Trial). Regression test in test_resolve_env_helpers.py pins the chokepoint by calling resolve_agent_env("oracle", DEFAULT_MODEL, {}) with no API key and no host auth — verified to fail on main with the user-facing ANTHROPIC_API_KEY error and pass after the fix. * test: regression suite pinning oracle chokepoint + orphan removal Bundle 14 tests in tests/test_oracle_chokepoint.py that pin each layer of the prior fix at the right altitude: - TestOrphanRemoval — cli/eval.py is gone (ModuleNotFoundError) and no src/ file references benchflow.cli.eval, guarding against a future re-introduction that could swallow the next bug fix the same way. - TestEvalCreateRouting — `bench eval create` callback lives in cli/main.py:eval_create. Pins the architectural fact PR benchflow-ai#173 missed. - TestEffectiveModel — unit tests for the helper: oracle drops model, non-oracle falls back to DEFAULT_MODEL, empty string treated as unset. - TestOracleYamlLoaders — Job.from_yaml(oracle config) → model is None for both native and Harbor formats; non-oracle backwards-compat preserved. - TestEvalCreateOracleCLI — end-to-end: live eval_create(agent="oracle") with no API key in env does not raise. Mocks Trial.create and resets the asyncio loop after to avoid polluting pre-existing tests that use the deprecated asyncio.get_event_loop() pattern. Verified to fail on main in the right shape: 9 of 14 fail (each pinning a deleted/added behavior), 5 pass (asserting structural facts already true). The CLI test fails on main with the user-reported error "ANTHROPIC_API_KEY required for model 'claude-haiku-4-5-20251001'…". * fix: restore cli/eval.py and test_eval_cli.py, apply oracle guard The previous commit deleted cli/eval.py and its tests as orphans, but they are intentionally kept. Restore both from main, update eval.py to use the effective_model() helper for the oracle chokepoint fix, and replace the "module is gone" regression test with a guard that cli/main.py does not import cli/eval (the actual invariant). * docs: clarify cli/eval.py and test_eval_cli.py are not wired into live CLI * docs: use `uv tool install` instead of `pip install` benchflow is a CLI tool with entry points — uv tool install gives users an isolated environment (like pipx) without managing venvs manually. --------- Co-authored-by: Yifeng He <yfhe.prsn@gmail.com>
EYH0602
added a commit
to EYH0602/benchflow
that referenced
this pull request
Apr 25, 2026
* fix: skip model/API-key validation for oracle agent The oracle agent runs solution/solve.sh and never calls an LLM, but resolve_agent_env() was validating API keys for whatever model the CLI defaulted to (claude-haiku-4-5-20251001). This made `bench eval create -a oracle` fail without ANTHROPIC_API_KEY set, even though oracle doesn't need it. * fix: don't assign default model to oracle agent Move the fix from resolve_agent_env to the CLI layer: oracle runs solve.sh and never calls an LLM, so it should not receive DEFAULT_MODEL at all. Both _run_single and _run_batch now pass model=None for oracle. Widen JobConfig.model to str | None to support this. * fix: oracle agent — chokepoint guard, drop orphan eval CLI, helper PR benchflow-ai#173 moved the oracle/DEFAULT_MODEL guard from resolve_agent_env to cli/eval.py, but cli/eval.py is orphaned (never imported into the live CLI), so `bench eval create` still passes DEFAULT_MODEL to oracle and trips ANTHROPIC_API_KEY validation. Three changes: - Restore the `agent != "oracle"` guard in resolve_agent_env so the chokepoint defends against any caller that forwards a model. - Delete the orphan cli/eval.py and its tests — the live eval_create lives in cli/main.py and was the actual code path users hit. - Add effective_model(agent, model) helper, change JobConfig.model default to None, replace seven `model or DEFAULT_MODEL` sites in cli/main.py and job.py YAML loaders so oracle gets honest model=None end-to-end (in result/summary JSON, prints, and downstream Trial). Regression test in test_resolve_env_helpers.py pins the chokepoint by calling resolve_agent_env("oracle", DEFAULT_MODEL, {}) with no API key and no host auth — verified to fail on main with the user-facing ANTHROPIC_API_KEY error and pass after the fix. * test: regression suite pinning oracle chokepoint + orphan removal Bundle 14 tests in tests/test_oracle_chokepoint.py that pin each layer of the prior fix at the right altitude: - TestOrphanRemoval — cli/eval.py is gone (ModuleNotFoundError) and no src/ file references benchflow.cli.eval, guarding against a future re-introduction that could swallow the next bug fix the same way. - TestEvalCreateRouting — `bench eval create` callback lives in cli/main.py:eval_create. Pins the architectural fact PR benchflow-ai#173 missed. - TestEffectiveModel — unit tests for the helper: oracle drops model, non-oracle falls back to DEFAULT_MODEL, empty string treated as unset. - TestOracleYamlLoaders — Job.from_yaml(oracle config) → model is None for both native and Harbor formats; non-oracle backwards-compat preserved. - TestEvalCreateOracleCLI — end-to-end: live eval_create(agent="oracle") with no API key in env does not raise. Mocks Trial.create and resets the asyncio loop after to avoid polluting pre-existing tests that use the deprecated asyncio.get_event_loop() pattern. Verified to fail on main in the right shape: 9 of 14 fail (each pinning a deleted/added behavior), 5 pass (asserting structural facts already true). The CLI test fails on main with the user-reported error "ANTHROPIC_API_KEY required for model 'claude-haiku-4-5-20251001'…". * fix: restore cli/eval.py and test_eval_cli.py, apply oracle guard The previous commit deleted cli/eval.py and its tests as orphans, but they are intentionally kept. Restore both from main, update eval.py to use the effective_model() helper for the oracle chokepoint fix, and replace the "module is gone" regression test with a guard that cli/main.py does not import cli/eval (the actual invariant). * docs: clarify cli/eval.py and test_eval_cli.py are not wired into live CLI * test: cover sandbox setup timeout wiring * docs: document sandbox setup timeout * feat: wire sandbox setup timeout through configs `setup_sandbox_user()` already accepted a `timeout_sec` kwarg (default 120s) but no live call site surfaced it — the knob was unreachable for normal runs. Under heavy sandbox bootstrap (parallel containers copying large tool caches into /home/<sandbox_user>) the 120s cap was hit with no user override. Add `sandbox_setup_timeout: int = 120` to TrialConfig, JobConfig, and RuntimeConfig, and forward it through: - trial YAML (`trial_config_from_dict`) - job YAML (both native and Harbor-compatible loaders) - `SDK.run(..., sandbox_setup_timeout=...)` - `bench eval create --sandbox-setup-timeout` - `Trial.install_agent()` into both `setup_sandbox_user()` call sites (oracle + normal agent) The value is also recorded in the run's `config.json` snapshot to aid post-hoc diagnosis. Default stays at 120s — this change is about making the value configurable, not changing runtime behavior. --------- Co-authored-by: Xiangyi Li <xiangyi@benchmarkthing.com> Co-authored-by: Xiangyi Li <xiangyi@benchflow.ai>
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.
Closes #172
Summary
solution/solve.shand never calls an LLM, butresolve_agent_env()was validating API keys for the CLI's default model (claude-haiku-4-5-20251001)bench eval create -a oraclenow works withoutANTHROPIC_API_KEYsetagent == "oracle"Test plan
test_resolve_env_helpers.pyandtest_subscription_auth.pypassbench eval create -t <task> -a oraclewithoutANTHROPIC_API_KEY— should succeedbench eval create -t <task> -a claude-agent-acp— API key validation still works as before