Skip to content

fix(agent): prevent false OAuth detection for third-party Anthropic providers#7367

Closed
n-WN wants to merge 1 commit into
NousResearch:mainfrom
n-WN:fix/third-party-anthropic-oauth-detection
Closed

fix(agent): prevent false OAuth detection for third-party Anthropic providers#7367
n-WN wants to merge 1 commit into
NousResearch:mainfrom
n-WN:fix/third-party-anthropic-oauth-detection

Conversation

@n-WN

@n-WN n-WN commented Apr 10, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Summary

Third-party Anthropic-compatible providers (Kimi, MiniMax, DashScope, etc.) using api_mode: anthropic_messages get incorrectly identified as Anthropic OAuth sessions. This causes Claude Code identity injection into the system prompt and two cascading gateway crashes.

Root cause

_is_oauth_token() only excludes sk-ant-api* prefixes. Any other key format (e.g. sk-kimi-*) returns True, setting _is_anthropic_oauth = True. This triggers:

  1. Identity injection: System prompt prepended with "You are Claude Code, Anthropic's official CLI for Claude.", all occurrences of "Hermes Agent" replaced with "Claude Code", "Nous Research" replaced with "Anthropic", tool names prefixed with mcp_
  2. request_overrides crash: Gateway assigns agent.request_overrides = None via turn_route.get("request_overrides") when no service_tier is configured, bypassing the __init__ guard of dict(request_overrides or {}). The anthropic_messages code path then calls self.request_overrides.get("speed") → AttributeError
  3. api_kwargs unbound: When _build_api_kwargs() raises before assigning api_kwargs, the retry-exhaustion error handler references the unbound variable → UnboundLocalError masks the real error

Changes (run_agent.py)

  • Gate _is_anthropic_oauth on _is_native_anthropic (provider == "anthropic") in both the init path and the failover/credential-swap path
  • Guard self.request_overrides.get("speed") with (self.request_overrides or {}).get("speed")
  • Initialize api_kwargs = None before the retry loop

How to test

  1. Configure a non-Anthropic provider with api_mode: anthropic_messages (e.g. Kimi with sk-kimi-* key, provider: custom)
  2. Ask the agent "who are you?" — should respond as Hermes Agent, not Claude Code
  3. Send messages via gateway (Telegram/Discord/Slack) — no AttributeError or UnboundLocalError in logs

Platform tested

  • Linux (Docker, Ubuntu 24.04, aarch64)
  • Telegram gateway with Kimi (kimi-for-coding, Anthropic Messages API)

Fixes #7366
Fixes #7277

@n-WN
fix: prevent false OAuth detection and crashes for third-party Anthro…
b6f7a69 
…pic providers

Three bugs fixed:

1. Third-party Anthropic-compatible providers (Kimi, MiniMax, etc.) had their
   API keys misidentified as OAuth tokens by _is_oauth_token(), which only
   excludes sk-ant-api* prefixes. This caused Claude Code identity injection
   (system prompt prepend, "Hermes Agent" → "Claude Code" text replacement,
   mcp_ tool name prefixing) when using these providers via anthropic_messages
   mode. Fix: gate _is_anthropic_oauth on _is_native_anthropic check.

2. Gateway sets agent.request_overrides = None when no service_tier is
   configured, bypassing the __init__ guard of dict(request_overrides or {}).
   This caused AttributeError on self.request_overrides.get("speed") in the
   anthropic_messages code path. Fix: use (self.request_overrides or {}).get().

3. When _build_api_kwargs() raises before assigning api_kwargs, the error
   handler at the retry-exhaustion path references the unbound variable,
   producing an UnboundLocalError that masks the real error. Fix: initialize
   api_kwargs = None before the retry loop.
teknium1 added a commit that referenced this pull request Apr 20, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
8a0f8b1 
…pport

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  #7410  @nocoo           — URL detection helper
  #7393  @keyuyuan        — OAuth 5-site guard
  #7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  #8636  @sgaofen         — caching helper + native-vs-proxy layout split
  #10954 @Only-Code-A     — caching on anthropic_messages+Claude
  #7648  @zhongyueming1121 — aux client anthropic_messages branch
  #6096  @hansnow         — /model switch clears stale api_mode
  #9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: #7366, #8294 (third-party Anthropic identity + caching).
Supersedes: #7410, #7367, #7393, #8636, #10954, #7648, #6096, #9691.
Rejects:    #9621 (OpenAI-wire caching with incomplete blocklist — risky),
            #7242 (superseded by #9691, stale branch),
            #8321 (targets smart_model_routing which was removed in #12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
@teknium1 teknium1 mentioned this pull request Apr 20, 2026
Merged
teknium1 added a commit that referenced this pull request Apr 20, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
65a31ee 
…pport (#12846)

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  #7410  @nocoo           — URL detection helper
  #7393  @keyuyuan        — OAuth 5-site guard
  #7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  #8636  @sgaofen         — caching helper + native-vs-proxy layout split
  #10954 @Only-Code-A     — caching on anthropic_messages+Claude
  #7648  @zhongyueming1121 — aux client anthropic_messages branch
  #6096  @hansnow         — /model switch clears stale api_mode
  #9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: #7366, #8294 (third-party Anthropic identity + caching).
Supersedes: #7410, #7367, #7393, #8636, #10954, #7648, #6096, #9691.
Rejects:    #9621 (OpenAI-wire caching with incomplete blocklist — risky),
            #7242 (superseded by #9691, stale branch),
            #8321 (targets smart_model_routing which was removed in #12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
@teknium1

teknium1 commented Apr 20, 2026

Copy link
Copy Markdown
Contributor

Superseded by PR #12846 (merged as commit 65a31ee on main).

Your contribution: OAuth guard for third-party Anthropic providers — your explanatory comment was kept; mechanism was broadened to all 5 _is_oauth_token call sites (cousin PR #7393's pattern).

Your authorship is preserved via a Co-authored-by: trailer on the merge commit so the AUTHOR_MAP attribution script picks you up. Thanks for raising this!

#12846

@teknium1 teknium1 closed this Apr 20, 2026
ulasbilgen pushed a commit to ulasbilgen/hermes-adhd-agent that referenced this pull request May 1, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
bd0dab3 
…pport (NousResearch#12846)

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  NousResearch#7410  @nocoo           — URL detection helper
  NousResearch#7393  @keyuyuan        — OAuth 5-site guard
  NousResearch#7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  NousResearch#8636  @sgaofen         — caching helper + native-vs-proxy layout split
  NousResearch#10954 @Only-Code-A     — caching on anthropic_messages+Claude
  NousResearch#7648  @zhongyueming1121 — aux client anthropic_messages branch
  NousResearch#6096  @hansnow         — /model switch clears stale api_mode
  NousResearch#9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: NousResearch#7366, NousResearch#8294 (third-party Anthropic identity + caching).
Supersedes: NousResearch#7410, NousResearch#7367, NousResearch#7393, NousResearch#8636, NousResearch#10954, NousResearch#7648, NousResearch#6096, NousResearch#9691.
Rejects:    NousResearch#9621 (OpenAI-wire caching with incomplete blocklist — risky),
            NousResearch#7242 (superseded by NousResearch#9691, stale branch),
            NousResearch#8321 (targets smart_model_routing which was removed in NousResearch#12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
aj-nt pushed a commit to aj-nt/hermes-agent that referenced this pull request May 1, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
213769a 
…pport (NousResearch#12846)

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  NousResearch#7410  @nocoo           — URL detection helper
  NousResearch#7393  @keyuyuan        — OAuth 5-site guard
  NousResearch#7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  NousResearch#8636  @sgaofen         — caching helper + native-vs-proxy layout split
  NousResearch#10954 @Only-Code-A     — caching on anthropic_messages+Claude
  NousResearch#7648  @zhongyueming1121 — aux client anthropic_messages branch
  NousResearch#6096  @hansnow         — /model switch clears stale api_mode
  NousResearch#9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: NousResearch#7366, NousResearch#8294 (third-party Anthropic identity + caching).
Supersedes: NousResearch#7410, NousResearch#7367, NousResearch#7393, NousResearch#8636, NousResearch#10954, NousResearch#7648, NousResearch#6096, NousResearch#9691.
Rejects:    NousResearch#9621 (OpenAI-wire caching with incomplete blocklist — risky),
            NousResearch#7242 (superseded by NousResearch#9691, stale branch),
            NousResearch#8321 (targets smart_model_routing which was removed in NousResearch#12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
Luminet2023 pushed a commit to Luminet2023/hermes-agent that referenced this pull request May 1, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
dea97af 
…pport (NousResearch#12846)

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  NousResearch#7410  @nocoo           — URL detection helper
  NousResearch#7393  @keyuyuan        — OAuth 5-site guard
  NousResearch#7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  NousResearch#8636  @sgaofen         — caching helper + native-vs-proxy layout split
  NousResearch#10954 @Only-Code-A     — caching on anthropic_messages+Claude
  NousResearch#7648  @zhongyueming1121 — aux client anthropic_messages branch
  NousResearch#6096  @hansnow         — /model switch clears stale api_mode
  NousResearch#9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: NousResearch#7366, NousResearch#8294 (third-party Anthropic identity + caching).
Supersedes: NousResearch#7410, NousResearch#7367, NousResearch#7393, NousResearch#8636, NousResearch#10954, NousResearch#7648, NousResearch#6096, NousResearch#9691.
Rejects:    NousResearch#9621 (OpenAI-wire caching with incomplete blocklist — risky),
            NousResearch#7242 (superseded by NousResearch#9691, stale branch),
            NousResearch#8321 (targets smart_model_routing which was removed in NousResearch#12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
02356abc pushed a commit to 02356abc/hermes-agent that referenced this pull request May 14, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
bf43e46 
…pport (NousResearch#12846)

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  NousResearch#7410  @nocoo           — URL detection helper
  NousResearch#7393  @keyuyuan        — OAuth 5-site guard
  NousResearch#7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  NousResearch#8636  @sgaofen         — caching helper + native-vs-proxy layout split
  NousResearch#10954 @Only-Code-A     — caching on anthropic_messages+Claude
  NousResearch#7648  @zhongyueming1121 — aux client anthropic_messages branch
  NousResearch#6096  @hansnow         — /model switch clears stale api_mode
  NousResearch#9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: NousResearch#7366, NousResearch#8294 (third-party Anthropic identity + caching).
Supersedes: NousResearch#7410, NousResearch#7367, NousResearch#7393, NousResearch#8636, NousResearch#10954, NousResearch#7648, NousResearch#6096, NousResearch#9691.
Rejects:    NousResearch#9621 (OpenAI-wire caching with incomplete blocklist — risky),
            NousResearch#7242 (superseded by NousResearch#9691, stale branch),
            NousResearch#8321 (targets smart_model_routing which was removed in NousResearch#12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
gweeteve pushed a commit to gweeteve/hermes-agent that referenced this pull request Jun 2, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
c89fb91 
…pport (NousResearch#12846)

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  NousResearch#7410  @nocoo           — URL detection helper
  NousResearch#7393  @keyuyuan        — OAuth 5-site guard
  NousResearch#7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  NousResearch#8636  @sgaofen         — caching helper + native-vs-proxy layout split
  NousResearch#10954 @Only-Code-A     — caching on anthropic_messages+Claude
  NousResearch#7648  @zhongyueming1121 — aux client anthropic_messages branch
  NousResearch#6096  @hansnow         — /model switch clears stale api_mode
  NousResearch#9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: NousResearch#7366, NousResearch#8294 (third-party Anthropic identity + caching).
Supersedes: NousResearch#7410, NousResearch#7367, NousResearch#7393, NousResearch#8636, NousResearch#10954, NousResearch#7648, NousResearch#6096, NousResearch#9691.
Rejects:    NousResearch#9621 (OpenAI-wire caching with incomplete blocklist — risky),
            NousResearch#7242 (superseded by NousResearch#9691, stale branch),
            NousResearch#8321 (targets smart_model_routing which was removed in NousResearch#12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
Egavasyug pushed a commit to Egavasyug/hermes-agent that referenced this pull request Jun 10, 2026
@teknium1 @nocoo
@keyuyuan @n-WN @sgaofen @vince-core @zhongyueming1121 @hansnow @TroyMitchell911
fix(anthropic): complete third-party Anthropic-compatible provider su…
4c90ef1 
…pport (NousResearch#12846)

Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers.  Synthesizes
eight stale community PRs into one consolidated change.

Five fixes:

- URL detection: consolidate three inline `endswith("/anthropic")`
  checks in runtime_provider.py into the shared _detect_api_mode_for_url
  helper.  Third-party /anthropic endpoints now auto-resolve to
  api_mode=anthropic_messages via one code path instead of three.

- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
  (__init__, switch_model, _try_refresh_anthropic_client_credentials,
  _swap_credential, _try_activate_fallback) now gate on
  `provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
  Claude-Code identity injection on third-party endpoints.  Previously
  only 2 of 5 sites were guarded.

- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
  `(should_cache, use_native_layout)` per endpoint.  Replaces three
  inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
  call-site flag.  Native Anthropic and third-party Anthropic gateways
  both get the native cache_control layout; OpenRouter gets envelope
  layout.  Layout is persisted in `_primary_runtime` so fallback
  restoration preserves the per-endpoint choice.

- Auxiliary client: `_try_custom_endpoint` honors
  `api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
  instead of silently downgrading to an OpenAI-wire client.  Degrades
  gracefully to OpenAI-wire when the anthropic SDK isn't installed.

- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
  clears stale `api_key`/`api_mode` when switching to a built-in
  provider, so a previous MiniMax custom endpoint's credentials can't
  leak into a later OpenRouter session.

- Truncation continuation: length-continuation and tool-call-truncation
  retry now cover `anthropic_messages` in addition to `chat_completions`
  and `bedrock_converse`.  Reuses the existing `_build_assistant_message`
  path via `normalize_anthropic_response()` so the interim message
  shape is byte-identical to the non-truncated path.

Tests: 6 new files, 42 test cases.  Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).

Synthesized from (credits preserved via Co-authored-by trailers):
  NousResearch#7410  @nocoo           — URL detection helper
  NousResearch#7393  @keyuyuan        — OAuth 5-site guard
  NousResearch#7367  @n-WN            — OAuth guard (narrower cousin, kept comment)
  NousResearch#8636  @sgaofen         — caching helper + native-vs-proxy layout split
  NousResearch#10954 @Only-Code-A     — caching on anthropic_messages+Claude
  NousResearch#7648  @zhongyueming1121 — aux client anthropic_messages branch
  NousResearch#6096  @hansnow         — /model switch clears stale api_mode
  NousResearch#9691  @TroyMitchell911 — anthropic_messages truncation continuation

Closes: NousResearch#7366, NousResearch#8294 (third-party Anthropic identity + caching).
Supersedes: NousResearch#7410, NousResearch#7367, NousResearch#7393, NousResearch#8636, NousResearch#10954, NousResearch#7648, NousResearch#6096, NousResearch#9691.
Rejects:    NousResearch#9621 (OpenAI-wire caching with incomplete blocklist — risky),
            NousResearch#7242 (superseded by NousResearch#9691, stale branch),
            NousResearch#8321 (targets smart_model_routing which was removed in NousResearch#12732).

Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

2 participants

@n-WN @teknium1