client: regenerate from hanzo-inc/cloud@2774987ccc (8.5.164)

The client lane checks the committed client against the document
api.hanzo.ai serves now, not against the ref .spec-lock pins. Cloud
v1.833.257 (2774987c) went live after 8.5.163 was cut and rewrote the
POST /v1/decisions description (cad76e1a0: Jev by OpenRouter's vendor
ids), so the served document moved from 296b1f84 to 783f66a3 and every
push since has failed the check on ai_api.py's docstring. The drift
reproduces identically at e34ab7e1; nothing in this tree caused it.

This is the lane's own move, done by hand: .spec-lock names the served
revision and digest, the generator reruns over those bytes, uv.lock
takes what `uv run` wrote, and the version takes the next patch.

.spec-lock

@@ -1,4 +1,4 @@
-ref=efc1644bfe36c30695746c7bf6bc7b92acb95b60
-sha256=296b1f84f7dba5e3fbd4e04e03171bb6b95c7700e570bbf76bf3d9be81f3e8ae
+ref=2774987ccc2b22f2fb2714b10e66ace5abc8825a
+sha256=783f66a300ab38b292048c1bfccdb5655ba8d0e91cea43c55c2cd83fc12af3e9
 repo=hanzo-inc/cloud
 path=openapi.yaml

pkg/hanzoai/cloud/api/ai_api.py

@@ -69440,7 +69440,7 @@ class AiApi:
     ) -> AiDecisionsResponse:
         """Implements POST /v1/decisions (the Decisions API).
 
-        Implements POST /v1/decisions (the Decisions API).  Body: {\"model\": \"kai\", \"state\": \"...\"|{...}|[...], \"questions\": {\"<name>\": {\"type\": \"choice\"|\"noul\"|\"score\", \"instructions\": ..., \"criteria\": ...}}}. model is kai, Kai's versioned id kai-<12 hex of the weights' sha256> — priced as kai and sent as asked — or a Jev id. model is required; state and questions are required unless the request names a handle, which carries neither. instructions is optional and any JSON. A choice names at least 2 labels and a score at least 1 level, bounded by the token budget rather than a count; questions holds 1 to 100.  observe holds the state under an id, and a later request naming that id as its handle decides over it again. An id is 1 to 128 characters of A-Z, a-z, 0-9, '.', '_' and '-'. A handle belongs to the org that observed it: no other org's request can name it.  Response: {\"id\",\"model\",\"provider\",\"answers\":{\"<name>\":{\"type\",...}}, \"usage\":{\"input_tokens\",\"output_tokens\"},\"routing\",\"state_hash\",\"latency_ms\"}. usage.input_tokens is the billed count — the request's text counted once, the state once and each question's instructions and options once; a decision over a handle bills the state once, when it was observed.  The body may be sent gzip, deflate, br or zstd encoded; decoded, it is bounded as sent.  Refusals are {\"error\":{\"code\",\"message\"}}: 400 malformed JSON or unknown model, 401 no valid credential, 402 insufficient balance, 403 a key kind that may not call this (pk-), 415 any other Content-Encoding, 422 an invalid question or handle id, a state beyond the checkpoint's reach (code state_too_long) or a body past 16 MiB (code request_too_long), 429 rate limited or queue full, 502 the service failed, 503 the model is known and not served, 529 overloaded. 402, 429 and 529 carry Retry-After and Retry-After-Ms, and every answer carries X-Request-Id. Billed on the answer's input tokens at the model's price.
+        Implements POST /v1/decisions (the Decisions API).  Body: {\"model\": \"kai\", \"state\": \"...\"|{...}|[...], \"questions\": {\"<name>\": {\"type\": \"choice\"|\"noul\"|\"score\", \"instructions\": ..., \"criteria\": ...}}}. model is kai, Kai's versioned id kai-<12 hex of the weights' sha256> — priced as kai and sent as asked — or Jev by OpenRouter's vendor ids, typesafe/jev-1.13 and ~typesafe/jev-latest, which reach Jev itself and bill at Jev's list price. No Jev id is ever answered by Kai: a bare one, such as jev-latest, is an unknown model. model is required; state and questions are required unless the request names a handle, which carries neither. instructions is optional and any JSON. A choice names at least 2 labels and a score at least 1 level, bounded by the token budget rather than a count; questions holds 1 to 100.  observe holds the state under an id, and a later request naming that id as its handle decides over it again. An id is 1 to 128 characters of A-Z, a-z, 0-9, '.', '_' and '-'. A handle belongs to the org that observed it: no other org's request can name it.  Response: {\"id\",\"model\",\"provider\",\"answers\":{\"<name>\":{\"type\",...}}, \"usage\":{\"input_tokens\",\"output_tokens\"},\"routing\",\"state_hash\",\"latency_ms\"}. usage.input_tokens is the billed count — the request's text counted once, the state once and each question's instructions and options once; a decision over a handle bills the state once, when it was observed.  The body may be sent gzip, deflate, br or zstd encoded; decoded, it is bounded as sent.  Refusals are {\"error\":{\"code\",\"message\"}}: 400 malformed JSON or unknown model, 401 no valid credential, 402 insufficient balance, 403 a key kind that may not call this (pk-), 415 any other Content-Encoding, 422 an invalid question or handle id, a state beyond the checkpoint's reach (code state_too_long) or a body past 16 MiB (code request_too_long), 429 rate limited or queue full, 502 the service failed, 503 the model is known and not served, 529 overloaded. 402, 429 and 529 carry Retry-After and Retry-After-Ms, and every answer carries X-Request-Id. Billed on the answer's input tokens at the model's price.
 
         :param ai_decisions_request: (required)
         :type ai_decisions_request: AiDecisionsRequest
@@ -69516,7 +69516,7 @@ class AiApi:
     ) -> ApiResponse[AiDecisionsResponse]:
         """Implements POST /v1/decisions (the Decisions API).
 
-        Implements POST /v1/decisions (the Decisions API).  Body: {\"model\": \"kai\", \"state\": \"...\"|{...}|[...], \"questions\": {\"<name>\": {\"type\": \"choice\"|\"noul\"|\"score\", \"instructions\": ..., \"criteria\": ...}}}. model is kai, Kai's versioned id kai-<12 hex of the weights' sha256> — priced as kai and sent as asked — or a Jev id. model is required; state and questions are required unless the request names a handle, which carries neither. instructions is optional and any JSON. A choice names at least 2 labels and a score at least 1 level, bounded by the token budget rather than a count; questions holds 1 to 100.  observe holds the state under an id, and a later request naming that id as its handle decides over it again. An id is 1 to 128 characters of A-Z, a-z, 0-9, '.', '_' and '-'. A handle belongs to the org that observed it: no other org's request can name it.  Response: {\"id\",\"model\",\"provider\",\"answers\":{\"<name>\":{\"type\",...}}, \"usage\":{\"input_tokens\",\"output_tokens\"},\"routing\",\"state_hash\",\"latency_ms\"}. usage.input_tokens is the billed count — the request's text counted once, the state once and each question's instructions and options once; a decision over a handle bills the state once, when it was observed.  The body may be sent gzip, deflate, br or zstd encoded; decoded, it is bounded as sent.  Refusals are {\"error\":{\"code\",\"message\"}}: 400 malformed JSON or unknown model, 401 no valid credential, 402 insufficient balance, 403 a key kind that may not call this (pk-), 415 any other Content-Encoding, 422 an invalid question or handle id, a state beyond the checkpoint's reach (code state_too_long) or a body past 16 MiB (code request_too_long), 429 rate limited or queue full, 502 the service failed, 503 the model is known and not served, 529 overloaded. 402, 429 and 529 carry Retry-After and Retry-After-Ms, and every answer carries X-Request-Id. Billed on the answer's input tokens at the model's price.
+        Implements POST /v1/decisions (the Decisions API).  Body: {\"model\": \"kai\", \"state\": \"...\"|{...}|[...], \"questions\": {\"<name>\": {\"type\": \"choice\"|\"noul\"|\"score\", \"instructions\": ..., \"criteria\": ...}}}. model is kai, Kai's versioned id kai-<12 hex of the weights' sha256> — priced as kai and sent as asked — or Jev by OpenRouter's vendor ids, typesafe/jev-1.13 and ~typesafe/jev-latest, which reach Jev itself and bill at Jev's list price. No Jev id is ever answered by Kai: a bare one, such as jev-latest, is an unknown model. model is required; state and questions are required unless the request names a handle, which carries neither. instructions is optional and any JSON. A choice names at least 2 labels and a score at least 1 level, bounded by the token budget rather than a count; questions holds 1 to 100.  observe holds the state under an id, and a later request naming that id as its handle decides over it again. An id is 1 to 128 characters of A-Z, a-z, 0-9, '.', '_' and '-'. A handle belongs to the org that observed it: no other org's request can name it.  Response: {\"id\",\"model\",\"provider\",\"answers\":{\"<name>\":{\"type\",...}}, \"usage\":{\"input_tokens\",\"output_tokens\"},\"routing\",\"state_hash\",\"latency_ms\"}. usage.input_tokens is the billed count — the request's text counted once, the state once and each question's instructions and options once; a decision over a handle bills the state once, when it was observed.  The body may be sent gzip, deflate, br or zstd encoded; decoded, it is bounded as sent.  Refusals are {\"error\":{\"code\",\"message\"}}: 400 malformed JSON or unknown model, 401 no valid credential, 402 insufficient balance, 403 a key kind that may not call this (pk-), 415 any other Content-Encoding, 422 an invalid question or handle id, a state beyond the checkpoint's reach (code state_too_long) or a body past 16 MiB (code request_too_long), 429 rate limited or queue full, 502 the service failed, 503 the model is known and not served, 529 overloaded. 402, 429 and 529 carry Retry-After and Retry-After-Ms, and every answer carries X-Request-Id. Billed on the answer's input tokens at the model's price.
 
         :param ai_decisions_request: (required)
         :type ai_decisions_request: AiDecisionsRequest
@@ -69592,7 +69592,7 @@ class AiApi:
     ) -> RESTResponseType:
         """Implements POST /v1/decisions (the Decisions API).
 
-        Implements POST /v1/decisions (the Decisions API).  Body: {\"model\": \"kai\", \"state\": \"...\"|{...}|[...], \"questions\": {\"<name>\": {\"type\": \"choice\"|\"noul\"|\"score\", \"instructions\": ..., \"criteria\": ...}}}. model is kai, Kai's versioned id kai-<12 hex of the weights' sha256> — priced as kai and sent as asked — or a Jev id. model is required; state and questions are required unless the request names a handle, which carries neither. instructions is optional and any JSON. A choice names at least 2 labels and a score at least 1 level, bounded by the token budget rather than a count; questions holds 1 to 100.  observe holds the state under an id, and a later request naming that id as its handle decides over it again. An id is 1 to 128 characters of A-Z, a-z, 0-9, '.', '_' and '-'. A handle belongs to the org that observed it: no other org's request can name it.  Response: {\"id\",\"model\",\"provider\",\"answers\":{\"<name>\":{\"type\",...}}, \"usage\":{\"input_tokens\",\"output_tokens\"},\"routing\",\"state_hash\",\"latency_ms\"}. usage.input_tokens is the billed count — the request's text counted once, the state once and each question's instructions and options once; a decision over a handle bills the state once, when it was observed.  The body may be sent gzip, deflate, br or zstd encoded; decoded, it is bounded as sent.  Refusals are {\"error\":{\"code\",\"message\"}}: 400 malformed JSON or unknown model, 401 no valid credential, 402 insufficient balance, 403 a key kind that may not call this (pk-), 415 any other Content-Encoding, 422 an invalid question or handle id, a state beyond the checkpoint's reach (code state_too_long) or a body past 16 MiB (code request_too_long), 429 rate limited or queue full, 502 the service failed, 503 the model is known and not served, 529 overloaded. 402, 429 and 529 carry Retry-After and Retry-After-Ms, and every answer carries X-Request-Id. Billed on the answer's input tokens at the model's price.
+        Implements POST /v1/decisions (the Decisions API).  Body: {\"model\": \"kai\", \"state\": \"...\"|{...}|[...], \"questions\": {\"<name>\": {\"type\": \"choice\"|\"noul\"|\"score\", \"instructions\": ..., \"criteria\": ...}}}. model is kai, Kai's versioned id kai-<12 hex of the weights' sha256> — priced as kai and sent as asked — or Jev by OpenRouter's vendor ids, typesafe/jev-1.13 and ~typesafe/jev-latest, which reach Jev itself and bill at Jev's list price. No Jev id is ever answered by Kai: a bare one, such as jev-latest, is an unknown model. model is required; state and questions are required unless the request names a handle, which carries neither. instructions is optional and any JSON. A choice names at least 2 labels and a score at least 1 level, bounded by the token budget rather than a count; questions holds 1 to 100.  observe holds the state under an id, and a later request naming that id as its handle decides over it again. An id is 1 to 128 characters of A-Z, a-z, 0-9, '.', '_' and '-'. A handle belongs to the org that observed it: no other org's request can name it.  Response: {\"id\",\"model\",\"provider\",\"answers\":{\"<name>\":{\"type\",...}}, \"usage\":{\"input_tokens\",\"output_tokens\"},\"routing\",\"state_hash\",\"latency_ms\"}. usage.input_tokens is the billed count — the request's text counted once, the state once and each question's instructions and options once; a decision over a handle bills the state once, when it was observed.  The body may be sent gzip, deflate, br or zstd encoded; decoded, it is bounded as sent.  Refusals are {\"error\":{\"code\",\"message\"}}: 400 malformed JSON or unknown model, 401 no valid credential, 402 insufficient balance, 403 a key kind that may not call this (pk-), 415 any other Content-Encoding, 422 an invalid question or handle id, a state beyond the checkpoint's reach (code state_too_long) or a body past 16 MiB (code request_too_long), 429 rate limited or queue full, 502 the service failed, 503 the model is known and not served, 529 overloaded. 402, 429 and 529 carry Retry-After and Retry-After-Ms, and every answer carries X-Request-Id. Billed on the answer's input tokens at the model's price.
 
         :param ai_decisions_request: (required)
         :type ai_decisions_request: AiDecisionsRequest

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "hanzoai"
-version = "8.5.163"
+version = "8.5.164"
 description = "The official Python library for the Hanzo API"
 dynamic = ["readme"]
 license = "Apache-2.0"

uv.lock

@@ -1545,7 +1545,7 @@ provides-extras = ["dev"]
 
 [[package]]
 name = "hanzo-tools"
-version = "0.3.6"
+version = "0.3.7"
 source = { editable = "pkg/hanzo-tools" }
 dependencies = [
     { name = "aiofiles" },
@@ -1709,7 +1709,7 @@ requires-dist = [
     { name = "hanzo-tools-vcs", marker = "extra == 'vcs'", specifier = ">=0.1.0" },
     { name = "hanzo-tools-vector", marker = "extra == 'all'", specifier = ">=0.1.0" },
     { name = "hanzo-tools-vector", marker = "extra == 'vector'", specifier = ">=0.1.0" },
-    { name = "mcp", specifier = ">=1.25.0" },
+    { name = "mcp", specifier = ">=1.25.0,<2" },
     { name = "pydantic", specifier = ">=2.12.5" },
     { name = "typing-extensions", specifier = ">=4.13.0" },
 ]
@@ -2252,7 +2252,7 @@ wheels = [
 
 [[package]]
 name = "hanzoai"
-version = "8.5.162"
+version = "8.5.163"
 source = { editable = "." }
 dependencies = [
     { name = "pydantic" },