opencode-llmstack 0.9.3__py3-none-any.whl → 0.9.6__py3-none-any.whl

llmstack/__init__.py

@@ -16,5 +16,5 @@ organised by concern:
 
 from __future__ import annotations
 
-__version__ = "0.9.2"
+__version__ = "0.9.6"
 __all__ = ["__version__"]

llmstack/app.py

@@ -36,7 +36,7 @@ Behaviour:
   ``POST /v1/completions``
     - if request body ``model == "auto"`` (or unset), classify the request
       and rewrite ``model`` -> one of: ``code-fast``, ``code-smart``,
-      ``code-ultra`` (when wired), ``plan``, ``plan-uncensored``.
+      ``code-ultra`` (when wired).
     - otherwise pass through unchanged.
     - tiers with ``backend = bedrock`` in ``models.ini`` are dispatched
       to AWS Bedrock via :mod:`llmstack.backends.bedrock` instead of
@@ -63,41 +63,28 @@ step DOWN as context grows**. This inverts the classic
     from priors.
 
 So as the conversation accumulates context, we step *down*: ultra
--> smart -> fast. Triggers and the plan track sit alongside this
-ladder.
+-> smart -> fast.
 
 Routing decision tree (first match wins):
 
-  1. Explicit "uncensored" trigger in the last user message
-     (``[nofilter]``, ``[uncensored]``, ``[heretic]``, or a line
-     starting with ``uncensored:`` / ``nofilter:``) -> plan-uncensored
-  2. Explicit "ultra" trigger (``[ultra]``, ``[opus]``,
+  1. Explicit "ultra" trigger (``[ultra]``, ``[opus]``,
      ``ultra:``, ``opus:``) AND ultra tier configured -> code-ultra
-  3. PLAN signal words AND no code-block / agent verbs / tools
-     AND estimated tokens <= ``[plan]`` tier's ctx_size
-     (pure design discussion that fits the planner's
-     window)                                          -> plan
-                                                         (if the planner's
-                                                          ctx_size is breached
-                                                          we fall through to
-                                                          the coding ladder
-                                                          rather than send a
-                                                          request that won't
-                                                          fit -- the coding
-                                                          tiers cover larger
-                                                          windows by design)
-  4. Estimated input tokens <= HIGH_FIDELITY_CEILING
+  2. Estimated input tokens <= HIGH_FIDELITY_CEILING
      ("reasonable context still being built")         -> code-ultra
                                                          (else code-smart)
-  5. Estimated input tokens <= MID_FIDELITY_CEILING   -> code-smart
-   6. Otherwise (long context, top-tier becomes
-      expensive/slow, fast tier's 128k window is the
-      best fit and it's free)                          -> code-fast
+  3. Estimated input tokens <= MID_FIDELITY_CEILING   -> code-smart
+  4. Otherwise (long context, top-tier becomes
+     expensive/slow, fast tier's 128k window is the
+     best fit and it's free)                          -> code-fast
                                                          (floored at
                                                           code-smart when
                                                           n_turns >=
                                                           MULTI_TURN_THRESHOLD)
 
+Plan and uncensored tiers are accessible via their dedicated agent
+modes (``agent.plan``, ``agent.plan-nofilter``) and slash commands;
+they are not auto-routed through ``model = auto``.
+
 The auto router's effective max context window is
 ``[code-fast].ctx_size`` -- fast is the bottom of the step-down
 ladder, so any context that would overflow the tiers above lands on
@@ -167,45 +154,14 @@ UNCENSORED_MODEL = os.getenv("ROUTER_UNCENSORED_MODEL", "plan-uncensored")
 #                still has comfortable headroom.
 HIGH_FIDELITY_CEILING = int(os.getenv("ROUTER_HIGH_FIDELITY_CEILING", "12000"))
 MID_FIDELITY_CEILING = int(os.getenv("ROUTER_MID_FIDELITY_CEILING", "32000"))
-# Floor the long-context rung at code-smart whenever a tool-call
-# protocol is in play -- 3B models tool-call unreliably regardless of
-# how big their context window is.
 MULTI_TURN_THRESHOLD = int(os.getenv("ROUTER_MULTI_TURN", "10"))
 AUTO_ALIASES = {"auto", "", None}
 
-UNCENSORED_TRIGGERS = re.compile(
-    r"(\[(uncensored|nofilter|no-?filter|heretic)\]"
-    r"|^[ \t]*(uncensored|nofilter|no-?filter)\s*:)",
-    re.IGNORECASE | re.MULTILINE,
-)
-
 ULTRA_TRIGGERS = re.compile(
     r"(\[(ultra|opus)\]|^[ \t]*(ultra|opus)\s*:)",
     re.IGNORECASE | re.MULTILINE,
 )
 
-PLAN_SIGNALS = re.compile(
-    r"\b(plan|design|architect(ure)?|approach|trade-?off|"
-    r"should\s+we|how\s+would\s+(you|we)|what\s+would\s+you|"
-    r"explain\s+why|reason\s+about|think\s+(through|step|hard|carefully)|"
-    r"compare\s+(options|approaches)|review\s+(the|this|my)\s+"
-    r"(architecture|design|approach|plan)|brainstorm|outline|"
-    r"summari[sz]e|root\s*cause|migrate|port\s+to)\b",
-    re.IGNORECASE,
-)
-
-AGENT_SIGNALS = re.compile(
-    r"\b(implement|fix\s+(this|the|a|my)?\s*(bug|issue|error|test)|"
-    r"write\s+(a|the|some)?\s*(function|class|test|script|module|method)|"
-    r"add\s+(a|the)?\s*(function|class|method|test|file|endpoint)|"
-    r"create\s+(a|the)?\s*(function|class|file|component|endpoint)|"
-    r"refactor|edit|patch|generate\s+code|debug|trace|"
-    r"run\s+tests?|build\s+(it|this)|compile)\b",
-    re.IGNORECASE,
-)
-
-CODE_BLOCK = re.compile(r"```|`[^`\n]{30,}`")
-
 logging.basicConfig(
     level=os.getenv("LOG_LEVEL", "INFO"),
     format="%(asctime)s %(levelname)s router %(message)s",
@@ -221,12 +177,11 @@ async def _lifespan(app: FastAPI):
     bedrock_tiers = sorted(t.name for t in TIERS.values() if t.is_bedrock)
     log.info(
         "router up upstream=%s ladder=[ultra<=%d -> agent<=%d -> fast] "
-        "fast=%s agent=%s ultra=%s plan=%s uncensored=%s bedrock=%s",
+        "fast=%s agent=%s ultra=%s bedrock=%s",
         UPSTREAM, HIGH_FIDELITY_CEILING, MID_FIDELITY_CEILING,
         FAST_MODEL, AGENT_MODEL,
         f"{ULTRA_MODEL} (active)" if _ultra_available()
             else f"{ULTRA_MODEL} (unwired -- high-fidelity rung falls back to {AGENT_MODEL})",
-        PLAN_MODEL, UNCENSORED_MODEL,
         ",".join(bedrock_tiers) or "(none)",
     )
     yield
@@ -302,12 +257,6 @@ def _estimate_tokens(messages: list[dict[str, Any]] | None, prompt: str | None)
     return chars // 4
 
 
-def _matches(pattern: re.Pattern[str], messages: list[dict[str, Any]] | None, prompt: str | None) -> bool:
-    if prompt and pattern.search(prompt):
-        return True
-    return any(pattern.search(t) for t in _iter_message_text(messages))
-
-
 def _ultra_available() -> bool:
     """True iff the ultra tier is loaded from ``models.ini``.
 
@@ -331,6 +280,11 @@ def classify(body: dict[str, Any]) -> tuple[str, str]:
 
     Step-DOWN ladder: top fidelity for short context, fall to mid for
     medium, drop to fast for long. See module docstring for rationale.
+
+    Only the fast / agent / ultra rungs are implemented here. Plan and
+    uncensored tiers are accessible via their dedicated agent modes
+    (``agent.plan``, ``agent.plan-nofilter``) and slash commands; they
+    are not auto-routed from the build agent.
     """
     messages = body.get("messages") if isinstance(body.get("messages"), list) else None
     prompt = body.get("prompt") if isinstance(body.get("prompt"), str) else None
@@ -341,50 +295,17 @@ def classify(body: dict[str, Any]) -> tuple[str, str]:
         for m in (messages or [])
         if m.get("role") == "system" and isinstance(m.get("content"), str)
     ]
-    if any(UNCENSORED_TRIGGERS.search(s) for s in (last_user, *sys_prompts) if s):
-        return UNCENSORED_MODEL, "uncensored-trigger"
 
     if any(ULTRA_TRIGGERS.search(s) for s in (last_user, *sys_prompts) if s):
         if _ultra_available():
             return ULTRA_MODEL, "ultra-trigger"
-        # Explicit user opt-in but the tier isn't wired up. Don't 404 --
-        # serve the request from the heaviest tier we *do* have and let
-        # the user notice in logs that their trigger was a no-op.
         log.warning("ultra-trigger ignored: %s not in models.ini; falling back to %s",
                     ULTRA_MODEL, AGENT_MODEL)
         return AGENT_MODEL, f"ultra-trigger->agent ({ULTRA_MODEL} unavailable)"
 
     n_turns = sum(1 for m in (messages or []) if m.get("role") == "user")
-    has_code_signal = (
-        _matches(CODE_BLOCK, messages, prompt)
-        or _matches(AGENT_SIGNALS, messages, prompt)
-    )
-
     est = _estimate_tokens(messages, prompt)
 
-    # Plan track is orthogonal to the code fidelity ladder: ``plan`` is a
-    # chat-tuned model meant for design / "should we" discussions. Only
-    # take it when nothing about the request says "I'm about to write
-    # code" (no triple-backticks, no agent verbs). Tools are stripped
-    # from the request body before dispatch (see ``_handle_completion``),
-    # so their presence here does not block plan routing.
-    # Only route to plan if the input fits in the planner's ctx_size --
-    # past that we fall through to the coding ladder which has tiers
-    # (smart, fast) explicitly sized for larger contexts.
-    if (
-        not has_code_signal
-        and _matches(PLAN_SIGNALS, messages, prompt)
-    ):
-        plan_tier = TIER_BY_ALIAS.get(PLAN_MODEL)
-        plan_ctx = plan_tier.ctx_size if plan_tier else 0
-        if not plan_ctx or est <= plan_ctx:
-            return PLAN_MODEL, "plan-signal"
-        log.info(
-            "plan-signal but tokens~%d > %s.ctx_size %d; "
-            "falling through to coding ladder",
-            est, PLAN_MODEL, plan_ctx,
-        )
-
     # Rung 1: short context -- start at the top.
     if est <= HIGH_FIDELITY_CEILING:
         if _ultra_available():
@@ -399,9 +320,7 @@ def classify(body: dict[str, Any]) -> tuple[str, str]:
         return AGENT_MODEL, f"mid-fidelity tokens~{est}<={MID_FIDELITY_CEILING}"
 
     # Rung 3: long context -- step down to fast. Floor at smart only
-    # when the multi-turn threshold is hit; tools alone no longer
-    # prevent the step-down (plan tiers strip tools before dispatch,
-    # and code-fast is a hosted model that tool-calls reliably).
+    # when the multi-turn threshold is hit.
     if n_turns >= MULTI_TURN_THRESHOLD:
         return AGENT_MODEL, f"long-context tokens~{est}>{MID_FIDELITY_CEILING} (user-turns={n_turns}>={MULTI_TURN_THRESHOLD} floor)"
     return FAST_MODEL, f"long-context tokens~{est}>{MID_FIDELITY_CEILING}"
@@ -530,14 +449,14 @@ async def list_models() -> JSONResponse:
             f"'{AGENT_MODEL}' up to ~{MID_FIDELITY_CEILING}, "
             f"'{FAST_MODEL}' beyond that."
         )
-        name = "Auto (step-down router: ultra/agent/fast + plan/uncensored)"
+        name = "Auto (step-down router: ultra/agent/fast)"
     else:
         top_blurb = (
             f"Step-down ladder (top->bottom as context grows): "
             f"'{AGENT_MODEL}' up to ~{MID_FIDELITY_CEILING} tokens, "
             f"'{FAST_MODEL}' beyond that."
         )
-        name = "Auto (step-down router: agent/fast + plan/uncensored)"
+        name = "Auto (step-down router: agent/fast)"
     data["data"].insert(0, {
         "id": "auto",
         "object": "model",
@@ -546,8 +465,6 @@ async def list_models() -> JSONResponse:
         "name": name,
         "description": (
             f"{top_blurb} "
-            f"'{PLAN_MODEL}' for design/planning (orthogonal to ladder); "
-            f"'{UNCENSORED_MODEL}' for explicit [nofilter] triggers; "
             f"'[ultra]'/'[opus]' triggers force '{ULTRA_MODEL}' regardless of size."
         ),
         "tier": "auto",
@@ -607,6 +524,41 @@ def _inject_sampler(body: dict[str, Any], tier: Tier) -> bool:
     return mutated
 
 
+def _inject_name_json(raw: bytes, tier_name: str) -> bytes:
+    try:
+        data = json.loads(raw)
+    except (json.JSONDecodeError, ValueError):
+        return raw
+    try:
+        msg = data["choices"][0]["message"]
+        if msg.get("content"):
+            msg["name"] = tier_name
+    except (KeyError, IndexError, TypeError):
+        pass
+    return json.dumps(data).encode()
+
+
+def _inject_name_sse(chunk: bytes, tier_name: str, injected: list[bool]) -> bytes:
+    if injected[0]:
+        return chunk
+    line = chunk.decode(errors="replace")
+    if not line.startswith("data: "):
+        return chunk
+    payload_str = line[len("data: "):].strip()
+    if payload_str in ("[DONE]", ""):
+        return chunk
+    try:
+        payload = json.loads(payload_str)
+        delta = payload["choices"][0]["delta"]
+        if "role" in delta:
+            delta["name"] = tier_name
+            injected[0] = True
+            return f"data: {json.dumps(payload, separators=(',', ':'))}\n\n".encode()
+    except (KeyError, IndexError, TypeError, json.JSONDecodeError):
+        pass
+    return chunk
+
+
 async def _handle_completion(req: Request, path: str) -> Response:
     raw = await req.body()
     headers = _filter_request_headers(req)
@@ -630,11 +582,6 @@ async def _handle_completion(req: Request, path: str) -> Response:
         mutated = True
 
     chosen_name = body.get("model")
-    if chosen_name in {PLAN_MODEL, UNCENSORED_MODEL} and body.get("tools"):
-        log.info("plan tier %s: stripping tools from request", chosen_name)
-        body.pop("tools")
-        body.pop("tool_choice", None)
-        mutated = True
     tier = _resolve_tier(chosen_name)
     if tier is not None and _inject_sampler(body, tier):
         mutated = True
@@ -645,6 +592,28 @@ async def _handle_completion(req: Request, path: str) -> Response:
     if tier is not None and tier.is_bedrock:
         from llmstack.backends import bedrock as bedrock_backend
         resp = await bedrock_backend.dispatch(req, tier, body)
+    elif tier is not None and body.get("stream"):
+        proxy = await _stream_proxy(req.method, path, raw, headers)
+        injected: list[bool] = [False]
+        tier_name = tier.name
+        original_gen = proxy.body_iterator
+
+        async def _named_gen():
+            async for chunk in original_gen:
+                yield _inject_name_sse(chunk, tier_name, injected)
+
+        proxy.body_iterator = _named_gen()
+        resp = proxy
+    elif tier is not None:
+        proxy = await _stream_proxy(req.method, path, raw, headers)
+        raw_resp = b"".join([chunk async for chunk in proxy.body_iterator])
+        patched = _inject_name_json(raw_resp, tier.name)
+        resp = Response(
+            content=patched,
+            status_code=proxy.status_code,
+            headers=dict(proxy.headers),
+            media_type=proxy.media_type,
+        )
     else:
         resp = await _stream_proxy(req.method, path, raw, headers)
 

llmstack/backends/bedrock.py

@@ -588,6 +588,8 @@ async def _complete_response(client: Any, tier: Tier, converse_kwargs: dict[str,
         return JSONResponse(status_code=502, content={"error": _error_payload(exc)})
 
     message, finish = _openai_message_from_converse(resp)
+    if message.get("content"):
+        message["name"] = tier.name
     usage_in = (resp.get("usage") or {})
     payload = {
         "id":      _completion_id(),
@@ -665,7 +667,7 @@ async def _stream_response(client: Any, tier: Tier, converse_kwargs: dict[str, A
 
         # First chunk: announce the assistant role so OpenAI clients can
         # initialise their accumulator.
-        yield _sse(_frame({"role": "assistant"}))
+        yield _sse(_frame({"role": "assistant", "name": model_label}))
 
         # Per-content-block state: index -> "text" | "tool_use"
         block_kinds: dict[int, str] = {}

llmstack/generators/opencode.py

@@ -194,7 +194,7 @@ def build_config(
 
     models: dict[str, dict] = {
         "auto": {
-            "name":      "Auto (router selects: fast / agent / plan / uncensored)",
+            "name":      "Auto (router selects: fast / agent / ultra)",
             "limit":     {"context": auto_ctx, "output": 16384},
             "tool_call": True,
             "cost":      ZERO_COST,

llmstack/models.ini

@@ -178,7 +178,7 @@ description  = Qwopus GLM 18B - planning, design discussions, architecture
 ; aws_region   = eu-central-1
 ; aws_profile  = bedrock-prod
 ; ctx_size     = 200000
-; sampler      = temp=0.7, top_p=0.9     ; creative; Opus 4.6 accepts both
+; sampler      = temp=0.7     ; creative; Opus 4.6
 ; description  = Claude Opus 4.6 on Bedrock - planning, design discussions, architecture
 
 [plan-uncensored]
@@ -258,21 +258,18 @@ description  = Mistral-Small 3.2 24B Heretic - no-filter planning
 ;
 ; First-match-wins decision tree applied by llmstack/app.py when model="auto":
 ;
-;   1. "[nofilter]" / "uncensored:" trigger                       -> plan-uncensored
-;   2. "[ultra]" / "[opus]" / "ultra:" trigger AND code-ultra
+;   1. "[ultra]" / "[opus]" / "ultra:" trigger AND code-ultra
 ;      tier configured                                            -> code-ultra
-;   3. PLAN signal words AND no code-block / agent verbs / tools
-;      AND tokens <= [plan].ctx_size (pure design discussion that
-;      still fits the planner's window)                           -> plan
-;      ...if the plan tier's ctx_size is breached, the request
-;      falls through to the coding ladder below rather than being
-;      sent to a planner whose window can't hold the input.
-;   4. tokens <= high_fidelity_ceiling AND code-ultra configured  -> code-ultra
+;   2. tokens <= high_fidelity_ceiling AND code-ultra configured  -> code-ultra
 ;      tokens <= high_fidelity_ceiling AND no code-ultra          -> code-smart
-;   5. tokens <= mid_fidelity_ceiling                             -> code-smart
-;   6. otherwise (long context):
-;        - if tools[] OR turns >= multi_turn (3B tool-calls badly) -> code-smart
-;        - else                                                    -> code-fast
+;   3. tokens <= mid_fidelity_ceiling                             -> code-smart
+;   4. otherwise (long context):
+;        - if turns >= multi_turn (floor at smart)                -> code-smart
+;        - else                                                   -> code-fast
+;
+; Plan and uncensored tiers are accessible via their dedicated agent
+; modes (agent.plan, agent.plan-nofilter) and slash commands; they are
+; NOT auto-routed through model=auto.
 ;
 ; AUTO ROUTER MAX CONTEXT = [code-fast].ctx_size. The fast tier sits at
 ; the bottom of the step-down ladder, so any context too big for the
@@ -303,9 +300,6 @@ description  = Mistral-Small 3.2 24B Heretic - no-filter planning
 high_fidelity_ceiling = 12000    ; tokens; below this, top-tier model is still cheap+fast (and ultra ctx_size = 2 * this)
 mid_fidelity_ceiling  = 32000    ; tokens; smart's sweet spot up to here, then step down to fast (smart ctx_size = 2 * this)
 multi_turn            = 10       ; turn count that floors the long-context rung at code-smart
-agent_signal_words    = implement, fix bug, write a function, refactor, edit, patch, debug, run tests, build it
-plan_signal_words     = design, architect, approach, trade-off, should we, how would you, explain why, think through, compare options, brainstorm, root cause
-uncensored_triggers   = [nofilter], [uncensored], [heretic], "uncensored:", "nofilter:" (line start)
 ultra_triggers        = [ultra], [opus], "ultra:", "opus:" (line start)
 
 ;------------------------------------------------------------------------------

{opencode_llmstack-0.9.3.data → opencode_llmstack-0.9.6.data}/data/CHANGELOG.md

@@ -4,6 +4,21 @@ All notable changes to `opencode-llmstack` are documented here.
 
 ---
 
+## [0.9.4] — 2026-05-11
+
+### Fixed
+- `classify()` now scopes `has_code_signal` to the **last user message only**
+  (was scanning the full conversation history). Previously, any prior coding
+  exchange in the session (code blocks, agent verbs) would permanently block
+  plan routing for the rest of the conversation — e.g. "explain why these
+  changes are important?" after a refactor request would never reach `plan`.
+- Added regression test:
+  `test_plan_signal_after_prior_coding_exchange_routes_to_plan`.
+- `__version__` corrected from `"0.9.2"` to `"0.9.4"` (was skewed vs
+  `pyproject.toml` since 0.9.3).
+
+---
+
 ## [0.9.2] — 2026-05-11
 
 ### Fixed

{opencode_llmstack-0.9.3.dist-info → opencode_llmstack-0.9.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opencode-llmstack
-Version: 0.9.3
+Version: 0.9.6
 Summary: Multi-tier local LLM stack: llama-swap + FastAPI auto-router + opencode wiring.
 Author: llmstack
 License: MIT License

{opencode_llmstack-0.9.3.dist-info → opencode_llmstack-0.9.6.dist-info}/RECORD

@@ -1,16 +1,16 @@
 llmstack/AGENTS.md,sha256=4DVUkqJ1-EP-cDNRCpznzghOOX6dAMbVWdcwyfFCALw,528
-llmstack/__init__.py,sha256=Qs9d58V8cJWmJvu4QLvO7_panKa8UkGRXAurHYgKDyU,855
+llmstack/__init__.py,sha256=Ie-86h7q7pEsE9zTlWfjBEYDIoR4mC8ZutdC5Nx-x8k,855
 llmstack/__main__.py,sha256=wXHd5-BmCCHUfNEmy2rbilBSyVhi4KD1dSIO_4NlxuE,199
 llmstack/_platform.py,sha256=eDY3T9krkaBigG5xXxqzIbH3MhdZqX3BWe7bozOsAso,13099
-llmstack/app.py,sha256=3Qt_bveLS13rPEucyX0P6QDf9o9O68amnJIvwMqoTQQ,28469
+llmstack/app.py,sha256=CiqIGpEbcjuSGDFNH951LiWZlE7Ju2_w5FHL5ieiAog,25952
 llmstack/check_models.py,sha256=WvTS2Td4acp-Q0-yWXUgXAgAgFOmpxiaeSDuAoivirw,4559
 llmstack/cli.py,sha256=Om70PzHrmU81y2Mw1sB6eeUs1fRHP0PnsCEVNC0UNvI,11341
-llmstack/models.ini,sha256=U38Z6wfGCpmgQTCNbnp1zu80rUrhNGWFTvI2nhVx1Mo,20556
+llmstack/models.ini,sha256=7ObeGrScRm0pGjyjAencr5lg8gEsMpjNvvF4o4Fxhps,19860
 llmstack/paths.py,sha256=A8q4-tpwIt5UMGG5ZDESKSuViMGLbPIAL1VoONopJqU,11512
 llmstack/shell_env.py,sha256=MJSW0PP15q-fsppIZ98WZ7XoqYMZmDy4k8N0gzEA6wU,39362
 llmstack/tiers.py,sha256=yl5xEhECe-GHiVXBRvlNoFtH_9y4uNSASpfHlZ4Ja74,14820
 llmstack/backends/__init__.py,sha256=-85sQz0R94OdbM2bUHGyyA5WaMnI9bHywPOaELeQHX0,777
-llmstack/backends/bedrock.py,sha256=Nb9sV45aH0RQHie_AkQwcpX5pkio5EAqnsphZM5P_nQ,30638
+llmstack/backends/bedrock.py,sha256=1o-s5C4CWorhqnse6dTY7E6y-98CoTckwP6qfq_H9Lw,30726
 llmstack/commands/__init__.py,sha256=eVO-YUxh1fSfdq72KggC-NrTYMtN6zIykgjyRgOCAt4,406
 llmstack/commands/_helpers.py,sha256=UKADaNXrnuoDi_JG0W2Tph7rWFB0cXvQh8YknZBw56I,2660
 llmstack/commands/activate.py,sha256=zCdEmyVv5qZUdhfez6hZ5Y46N_yjPwfKbPTwCJXnA3o,3663
@@ -29,13 +29,13 @@ llmstack/download/binary.py,sha256=xpv15wF4viv8uFC5UqfSIf36CIoPpmaNUaVtjF-vTWA,8
 llmstack/download/ggufs.py,sha256=2hCr-svUiPIV2I3ruwTbXo6lPn9m-VBOqa3DFbvdIcA,5435
 llmstack/generators/__init__.py,sha256=LfbcReuyYBCdVuT9J5RKo7-f8n585YBU3Hus6DsxqTs,1189
 llmstack/generators/llama_swap.py,sha256=KdYH9N6TJECotZvyxvAjaa3kRyzn4YOi2T6D2UdyVKw,14785
-llmstack/generators/opencode.py,sha256=s_FrLXUBnLzRGQovl1PcAEs7V_P52wT1vnvvxMcKfs4,11203
-opencode_llmstack-0.9.3.data/data/CHANGELOG.md,sha256=2Ok5sn4aA_N5UMaUJ4jRbuTeWC1pt7gdFgYnxj2JdKU,5217
-opencode_llmstack-0.9.3.data/data/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
-opencode_llmstack-0.9.3.data/data/UPGRADING.md,sha256=0XSNZ9trCviFLH5EL3Jz02fO2_8AfqB8_9aX0-o1bik,24927
-opencode_llmstack-0.9.3.dist-info/licenses/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
-opencode_llmstack-0.9.3.dist-info/METADATA,sha256=QL_Za8nscUU57s41131pavDonGlSmSbHnNUZXWAMYqo,36323
-opencode_llmstack-0.9.3.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-opencode_llmstack-0.9.3.dist-info/entry_points.txt,sha256=soomjpqvl4KzFScgpQbu96vgcLriOtkB9MbiSC0rvZ8,47
-opencode_llmstack-0.9.3.dist-info/top_level.txt,sha256=tMv9sDWp8RW_DNNY8cuM4Uy4sND-KwTLcsScl5gdcEQ,9
-opencode_llmstack-0.9.3.dist-info/RECORD,,
+llmstack/generators/opencode.py,sha256=8-eVGD3ZTgta3DHQ5gu6I9CkYZt7x-EdMw2qNzgyoQ4,11191
+opencode_llmstack-0.9.6.data/data/CHANGELOG.md,sha256=58feU0rA9bBYvecDoFaLcwwgezLPkD3MSt0vRUVjdF8,5837
+opencode_llmstack-0.9.6.data/data/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
+opencode_llmstack-0.9.6.data/data/UPGRADING.md,sha256=0XSNZ9trCviFLH5EL3Jz02fO2_8AfqB8_9aX0-o1bik,24927
+opencode_llmstack-0.9.6.dist-info/licenses/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
+opencode_llmstack-0.9.6.dist-info/METADATA,sha256=VHLq0f7YxR0BAPnGYC7uLS4jqNGB0Ki5GPZq0ER1nW8,36323
+opencode_llmstack-0.9.6.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+opencode_llmstack-0.9.6.dist-info/entry_points.txt,sha256=soomjpqvl4KzFScgpQbu96vgcLriOtkB9MbiSC0rvZ8,47
+opencode_llmstack-0.9.6.dist-info/top_level.txt,sha256=tMv9sDWp8RW_DNNY8cuM4Uy4sND-KwTLcsScl5gdcEQ,9
+opencode_llmstack-0.9.6.dist-info/RECORD,,