agentshim 0.6.7__tar.gz → 0.7.0__tar.gz

{agentshim-0.6.7 → agentshim-0.7.0}/CHANGELOG.md

@@ -1,5 +1,80 @@
 # Changelog
 
+## 0.7.0 (2026-09-27)
+
+First-class cache accounting and a static pricing table. Additive except one
+change of meaning: `cached_input_tokens` now counts cache reads only (see
+Changed).
+
+### Added
+
+- `TokenUsage.cache_read_input_tokens` (input served from the prompt cache),
+  `cache_write_1h_input_tokens` (the one-hour-TTL part of cache writes, from
+  Claude's `cache_creation` breakdown) and the derived
+  `uncached_input_tokens` (`input - cache_read - cache_write`). `to_dict()`
+  gains the three keys; no key was removed.
+- Codex turns now report `cache_write_input_tokens` and
+  `reasoning_output_tokens` from `turn.completed` (both used to be dropped).
+- `TokenUsage` checks its invariants on construction:
+  `cache_read + cache_write <= input`, `cache_write_1h <= cache_write`,
+  `reasoning <= output`, no negative counts. Parsers build it through the new
+  `normalized_usage`, which clamps a CLI's inconsistent counts instead.
+- `TokenUsage.from_dict` reads a `to_dict()` mapping back, including one
+  written before 0.7.0.
+- `TokenWeights` and `TokenUsage.weighted_total(weights)`: a total weighted by
+  token class (uncached input, cache reads, 5m and 1h cache writes, output,
+  reasoning), each token weighted once.
+- A static, versioned pricing table (`agentshim.core.pricing`):
+  `ModelPricing`, `PricingTable`, `default_pricing()`,
+  `price_for(provider, model, table=None)` (`None` for an unknown model, never
+  zero), `cost_usd(usage, pricing)` and `ModelPricing.relative_weights()`.
+  It covers OpenAI GPT-6 (astra, sol, luna), GPT-5.6, GPT-5.5 and earlier
+  GPT-5 models, and Claude Fable 5.1, Fable 5, Opus 5.5, Opus 5, Opus 4.8,
+  Sonnet 5, Sonnet 4.6 and Haiku 4.5, each with its official source URL and
+  check date (all 2026-09-27). Callers override or extend it with
+  `PricingTable.with_entries` or `PricingTable.from_dict`. Holding prices in
+  agentshim is a user-directed decision; see `docs/pricing.md`.
+- Recorded Codex, Claude (5m and 1h cache writes), opencode and Gemini
+  streams under `tests/fixtures/`, with tests pinning each provider's mapping.
+  The Claude Haiku 4.5 recording's `total_cost_usd` is reproduced exactly by
+  the table.
+
+### Changed
+
+- `cached_input_tokens` is a deprecated alias of `cache_read_input_tokens`.
+  On Claude, opencode and Copilot it used to be reads plus writes; it is now
+  reads only, since a cache write is billed above base input and a read far
+  below it. Codex and Gemini report no writes in their cached count, so their
+  value is unchanged. Constructing with `cached_input_tokens=` still works.
+
+### Documented
+
+- Claude's `result.usage` covers the main conversation only; a Task
+  subagent's tokens appear only in `modelUsage` and `total_cost_usd`.
+
+## 0.6.8 (2026-09-27)
+
+A tightening of the Codex (`STRICT`) schema check: schemas it now rejects
+were already rejected by the API, after a full model turn.
+
+### Fixed
+
+- A Codex output schema is checked against OpenAI's strict structured-output
+  rules before the CLI starts. `turn()` raises `SchemaDialectError`, naming
+  each offending node by JSON pointer, when an object leaves a property out
+  of `required` (declare it required and nullable instead), lists a
+  `required` name missing from `properties`, omits `properties` (`{}` is
+  fine) or `additionalProperties: false` (including on a nullable
+  `["object", "null"]` object), uses `anyOf` at
+  the root, or has a `$ref` that resolves to nothing. Codex used to fail such
+  a turn with `invalid_json_schema` only after the model ran. The Claude
+  (`OPEN`) dialect is unchanged.
+- A `$ref` of `"#"` (root recursion) is accepted as local in both dialects.
+- Problem pointers escape `/` and `~` in property names (RFC 6901), and
+  `enum`, `const` and `required` values are no longer inspected as schemas.
+- `normalize` closes a nullable object node too, and gives an object with
+  no `properties` an empty one, so its output passes the `STRICT` check.
+
 ## 0.6.7 (2026-09-27)
 
 Additive, with one tightening: a sandboxed Codex turn no longer applies the

{agentshim-0.6.7 → agentshim-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: agentshim
-Version: 0.6.7
+Version: 0.7.0
 Summary: Provider-agnostic coding-agent CLI shims
 Requires-Python: >=3.10
 Provides-Extra: test
@@ -23,8 +23,9 @@ No required runtime dependencies. Python 3.10+.
 
 - `CliAgent` / `AgentSession`: one turn at a time, resumable, cancellable
 - typed events delivered on the calling thread
-- normalized token accounting where `cached_input_tokens <= input_tokens` on
-  every provider
+- normalized token accounting (total input, cache reads, cache writes,
+  uncached input, output and reasoning) on every provider, plus a static,
+  versioned pricing table (see [Usage and Pricing](docs/pricing.md))
 - declared capabilities on `ProviderProfile`, so no caller probes a provider
 - injectable `CommandExecutor`s for running the CLI in a container or over a
   remote shell

{agentshim-0.6.7 → agentshim-0.7.0}/README.md

@@ -14,8 +14,9 @@ No required runtime dependencies. Python 3.10+.
 
 - `CliAgent` / `AgentSession`: one turn at a time, resumable, cancellable
 - typed events delivered on the calling thread
-- normalized token accounting where `cached_input_tokens <= input_tokens` on
-  every provider
+- normalized token accounting (total input, cache reads, cache writes,
+  uncached input, output and reasoning) on every provider, plus a static,
+  versioned pricing table (see [Usage and Pricing](docs/pricing.md))
 - declared capabilities on `ProviderProfile`, so no caller probes a provider
 - injectable `CommandExecutor`s for running the CLI in a container or over a
   remote shell

{agentshim-0.6.7 → agentshim-0.7.0}/agentshim/__init__.py

@@ -29,11 +29,13 @@ from .core import (
     McpMechanism,
     McpServer,
     McpTransport,
+    ModelPricing,
     NoopInstallation,
     NullEventHandler,
     OutputSchema,
     OutputSchemaStyle,
     ParsedTurn,
+    PricingTable,
     Provider,
     ProviderCapabilityError,
     ProviderError,
@@ -51,6 +53,7 @@ from .core import (
     StdioMcpServer,
     StreamParser,
     TokenUsage,
+    TokenWeights,
     ToolCall,
     ToolResult,
     ToolTracker,
@@ -59,12 +62,16 @@ from .core import (
     UsageReport,
     compact_json,
     compose_event_handlers,
+    cost_usd,
+    default_pricing,
     dialect_problems,
     install_config_file,
     interactive_env,
     materialize,
     normalize,
+    normalized_usage,
     parse_json_object,
+    price_for,
 )
 from .execution import (
     CallbackCommandStreamSink,
@@ -84,7 +91,7 @@ from .providers.copilot import CopilotProvider
 from .providers.gemini import GeminiProvider
 from .providers.opencode import OpencodeProvider
 
-__version__ = "0.6.7"
+__version__ = "0.7.0"
 
 __all__ = [
     "AgentEvent",
@@ -123,6 +130,7 @@ __all__ = [
     "McpMechanism",
     "McpServer",
     "McpTransport",
+    "ModelPricing",
     "NoopInstallation",
     "NullEventHandler",
     "NullSink",
@@ -130,6 +138,7 @@ __all__ = [
     "OutputSchema",
     "OutputSchemaStyle",
     "ParsedTurn",
+    "PricingTable",
     "Provider",
     "ProviderCapabilityError",
     "ProviderError",
@@ -148,6 +157,7 @@ __all__ = [
     "StdioMcpServer",
     "StreamParser",
     "TokenUsage",
+    "TokenWeights",
     "ToolCall",
     "ToolResult",
     "ToolTracker",
@@ -158,12 +168,16 @@ __all__ = [
     "__version__",
     "compact_json",
     "compose_event_handlers",
+    "cost_usd",
+    "default_pricing",
     "dialect_problems",
     "get_provider",
     "install_config_file",
     "interactive_env",
     "materialize",
     "normalize",
+    "normalized_usage",
     "parse_json_object",
+    "price_for",
     "provider_names",
 ]

{agentshim-0.6.7 → agentshim-0.7.0}/agentshim/core/__init__.py

@@ -50,12 +50,13 @@ from .mcp import (
     StdioMcpServer,
     install_config_file,
 )
+from .pricing import ModelPricing, PricingTable, cost_usd, default_pricing, price_for
 from .profile import McpMechanism, OutputSchemaStyle, ProviderProfile, SchemaDialect
 from .provider import ArgvContext, McpInstallation, ParsedTurn, Provider, StreamParser
 from .schema import compact_json, dialect_problems, materialize, normalize
 from .stream import ToolTracker, parse_json_object
 from .turn import OutputSchema, TurnRequest, TurnResult
-from .usage import ProviderUsage, TokenUsage
+from .usage import ProviderUsage, TokenUsage, TokenWeights, normalized_usage
 
 __all__ = [
     "AgentEvent",
@@ -79,11 +80,13 @@ __all__ = [
     "McpMechanism",
     "McpServer",
     "McpTransport",
+    "ModelPricing",
     "NoopInstallation",
     "NullEventHandler",
     "OutputSchema",
     "OutputSchemaStyle",
     "ParsedTurn",
+    "PricingTable",
     "Provider",
     "ProviderCapabilityError",
     "ProviderError",
@@ -101,6 +104,7 @@ __all__ = [
     "StdioMcpServer",
     "StreamParser",
     "TokenUsage",
+    "TokenWeights",
     "ToolCall",
     "ToolResult",
     "ToolTracker",
@@ -109,10 +113,14 @@ __all__ = [
     "UsageReport",
     "compact_json",
     "compose_event_handlers",
+    "cost_usd",
+    "default_pricing",
     "dialect_problems",
     "install_config_file",
     "interactive_env",
     "materialize",
     "normalize",
+    "normalized_usage",
     "parse_json_object",
+    "price_for",
 ]