hebbrix 2.5.0__tar.gz → 2.6.0__tar.gz

{hebbrix-2.5.0 → hebbrix-2.6.0}/CHANGELOG.md

@@ -1,5 +1,56 @@
 # Changelog
 
+## 2.6.0 — 2026-10-04 (stable SDK)
+
+- Bound runtime HTTPX to `>=0.25.0,<1`, excluding incompatible 1.x prereleases.
+- Add sync/async atomic setup options for explicit policy configuration and built-in success-minus-cost metrics.
+- Keep advisor input/probability validation, scope and protected evidence transports unchanged.
+- Backend v3 learning methods remain explicit experimental opt-ins. Stable packaging does not establish performance, calibrated confidence or execution permission.
+
+## 2.6.0rc5 — 2026-10-03 (prerelease)
+
+- Snapshot advisor context/candidates and reject scope overrides or mutable identities.
+- Validate the complete finite logging distribution against original candidates before writing.
+- Invoke the callback once; preserve caller probabilities without normalization or retries.
+- Caller probabilities are not authenticated randomization; no execution authority or measured learning-performance gain is claimed.
+
+## 2.6.0rc4 — 2026-10-02 (prerelease)
+
+- Correct both HTTP User-Agent version strings and add a source-version parity
+  check. The previously published rc3 remains unchanged; helper behavior is
+  otherwise identical.
+
+## 2.6.0rc3 — 2026-10-02 (prerelease)
+
+- Add scoped one-call policy setup and descriptive learning-report helpers.
+- Add bounded advisor callbacks that log the caller's actual chosen action and
+  supplied behavior distribution; advice never executes or authorizes an action.
+- These helpers require the October 2 outcome-followup backend release or a
+  compatible successor. Check `/v1/release` before using the new endpoints.
+- Learning performance and reliable model compliance with feedback are not
+  established. This release makes no superiority or benchmark claim.
+
+## 2.6.0rc2 — 2026-10-01 (prerelease)
+
+- Add sync/async context enrollment, revision-checked policy configuration,
+  scoped evidence cards and exact action-advice helpers.
+- Preserve collection/end-user scope and JSON context. ACT remains advisory;
+  callers must independently authorize external actions.
+- Policy configuration/advice requires backend `e5f6g7h8i868` or a compatible
+  successor. Existing protected workflow transports are unchanged.
+
+## 2.6.0rc1 — 2026-09-09 (prerelease)
+
+- Add sync/async native experience programs, reflection jobs, reviewed lesson
+  revisions and one-use execution-permission transports.
+- Bind complete model requests and tool invocations, retain uncertain delivery,
+  and prevent automatic retries of potentially completed side effects.
+- Add the optional bounded OpenAI reflection adapter and `hebbrix-reflect` CLI.
+- Require separately scoped worker/reviewer/executor credentials and the matching
+  `b5c6d7e8f959` backend. That backend is not yet deployed to public production;
+  stable 2.5.0 remains the production recommendation. No autonomous actions are
+  enabled by installing this package.
+
 ## 2.5.0 — 2026-09-07
 
 - Add matching synchronous and asynchronous Evidence Loop methods: owner-managed verifiers, durable episodes, actual-execution claims, protected outcome delivery and evidence assessments.

{hebbrix-2.5.0 → hebbrix-2.6.0}/MANIFEST.in

@@ -3,3 +3,6 @@ include CHANGELOG.md
 include LICENSE
 include pyproject.toml
 recursive-include hebbrix *.py
+recursive-include examples *.py
+recursive-include docs *.md
+recursive-include contracts *.json

{hebbrix-2.5.0/hebbrix.egg-info → hebbrix-2.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hebbrix
-Version: 2.5.0
+Version: 2.6.0
 Summary: Typed Python client for Hebbrix memory, retrieval, and outcome-learning APIs
 Author-email: Hebbrix Team <support@hebbrix.com>
 Maintainer-email: Hebbrix Team <support@hebbrix.com>
@@ -33,7 +33,7 @@ Project-URL: Issues, https://github.com/Hebbrix/hebbrix-python/issues
 Project-URL: Support, https://www.hebbrix.com/contact
 Project-URL: API Reference, https://api.hebbrix.com/docs
 Keywords: ai,memory,agents,llm,chatbot,assistant,ml,reinforcement-learning,knowledge-graph,vector-search,rag,temporal,procedural-memory,working-memory
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
@@ -49,7 +49,7 @@ Classifier: Framework :: AsyncIO
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: httpx>=0.25.0
+Requires-Dist: httpx<1,>=0.25.0
 Requires-Dist: requests>=2.31.0
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
@@ -65,10 +65,15 @@ Dynamic: license-file
 
 Typed Python client for Hebbrix memory, retrieval, and outcome-learning APIs.
 
+This branch is the **2.6.0 stable SDK**. The new policy configuration and
+advice helpers require backend schema `e5f6g7h8i868` or a compatible successor.
+A stable SDK does not qualify experimental learning or enable autonomous execution. ASK/REVIEW/ACT is advice;
+an action still requires independent permission.
+
 ## Install
 
 ```bash
-pip install hebbrix==2.5.0
+pip install hebbrix==2.6.0
 ```
 
 Python 3.8+ is supported. `MemoryClient` is asynchronous. `SyncMemoryClient`
@@ -76,8 +81,38 @@ supports the core collection, memory, search, correction, procedure, and
 ProofLoop workflows; advanced temporal, working-memory, consolidation,
 memory-tool, and RL resources are currently async-only.
 
+The runtime requires `httpx>=0.25.0,<1`; incompatible 1.x prereleases are excluded.
+For the matching Round 5 backend, `setup_policy` accepts explicit `configuration`
+options for versioned change response and declared optional-field sharing, plus
+`value_objective={"success_value":10,"max_cost":20,"cost_unit":"USD"}`.
+Report both actual success and cost with `record_outcome`. Chat follow-up capture
+requires `features.learning: true` and an exact `outcome_followup.decision_id`;
+captured signals are provisional, not verified execution or autonomy evidence.
+These options require the matching runtime, not only the unchanged database schema.
+
 ## Quick start
 
+October 2 follow-up: `proofloop.setup_policy` atomically creates a new
+context/schema policy with explicitly declared low-risk exploration; existing
+policies are not migrated automatically. `learning_report` reads a bounded,
+scoped descriptive report, not proven uplift. `decide_with_advice` reads an
+evidence card, invokes the supplied advisor once and logs its actual choice and
+probabilities. `decide` accepts bounded `prior_action` / `prior_strength` for one
+server-selected decision; this is not outcome evidence. These new helpers and
+structured paraphrase matching require the matching October 2 outcome-followup
+backend, not merely its database schema; inspect `/v1/release` before use.
+Nothing here grants permission to execute. Learning performance and reliable
+model compliance with feedback are not established.
+
+Both clients expose `proofloop.register_context_schema`, `context_schema`,
+`configure_policy`, `policy_configuration`, `policy_advice` and `action_advice`.
+Enroll context before recording decisions. Configuration uses `expected_revision`
+for compare-and-swap; do not retry a conflict blindly. Exploration remains an
+explicit low-risk opt-in. `action_advice` takes the exact configured description,
+policy/action IDs and context, and maps `user_id` to the confidence endpoint's
+`end_user_id`. For the complete request shapes, see the
+[learning guide](https://www.hebbrix.com/docs/learning).
+
 ```python
 import asyncio
 from hebbrix import MemoryClient
@@ -188,3 +223,14 @@ The production API publishes exact build and artifact compatibility at
 ## License
 
 MIT. See `LICENSE` in the distribution.
+## Native experience workflow (prerelease)
+
+The current source includes `client.experiences`, bounded reflection workers,
+separate lesson review/revision and explicit one-use execution admission. These
+methods require the matching new backend; the published 2.5.0 release does not
+include this extension. The candidate package supplies `hebbrix-reflect --help`.
+Importing it does not call a model, approve a lesson or execute a tool.
+
+See `docs/native-experience-operations.md` for role scopes,
+uncertain-call recovery, exact-request binding and policy rollback. Do not treat a
+lesson, score, review or issued permit as execution permission.

{hebbrix-2.5.0 → hebbrix-2.6.0}/README.md

@@ -2,10 +2,15 @@
 
 Typed Python client for Hebbrix memory, retrieval, and outcome-learning APIs.
 
+This branch is the **2.6.0 stable SDK**. The new policy configuration and
+advice helpers require backend schema `e5f6g7h8i868` or a compatible successor.
+A stable SDK does not qualify experimental learning or enable autonomous execution. ASK/REVIEW/ACT is advice;
+an action still requires independent permission.
+
 ## Install
 
 ```bash
-pip install hebbrix==2.5.0
+pip install hebbrix==2.6.0
 ```
 
 Python 3.8+ is supported. `MemoryClient` is asynchronous. `SyncMemoryClient`
@@ -13,8 +18,38 @@ supports the core collection, memory, search, correction, procedure, and
 ProofLoop workflows; advanced temporal, working-memory, consolidation,
 memory-tool, and RL resources are currently async-only.
 
+The runtime requires `httpx>=0.25.0,<1`; incompatible 1.x prereleases are excluded.
+For the matching Round 5 backend, `setup_policy` accepts explicit `configuration`
+options for versioned change response and declared optional-field sharing, plus
+`value_objective={"success_value":10,"max_cost":20,"cost_unit":"USD"}`.
+Report both actual success and cost with `record_outcome`. Chat follow-up capture
+requires `features.learning: true` and an exact `outcome_followup.decision_id`;
+captured signals are provisional, not verified execution or autonomy evidence.
+These options require the matching runtime, not only the unchanged database schema.
+
 ## Quick start
 
+October 2 follow-up: `proofloop.setup_policy` atomically creates a new
+context/schema policy with explicitly declared low-risk exploration; existing
+policies are not migrated automatically. `learning_report` reads a bounded,
+scoped descriptive report, not proven uplift. `decide_with_advice` reads an
+evidence card, invokes the supplied advisor once and logs its actual choice and
+probabilities. `decide` accepts bounded `prior_action` / `prior_strength` for one
+server-selected decision; this is not outcome evidence. These new helpers and
+structured paraphrase matching require the matching October 2 outcome-followup
+backend, not merely its database schema; inspect `/v1/release` before use.
+Nothing here grants permission to execute. Learning performance and reliable
+model compliance with feedback are not established.
+
+Both clients expose `proofloop.register_context_schema`, `context_schema`,
+`configure_policy`, `policy_configuration`, `policy_advice` and `action_advice`.
+Enroll context before recording decisions. Configuration uses `expected_revision`
+for compare-and-swap; do not retry a conflict blindly. Exploration remains an
+explicit low-risk opt-in. `action_advice` takes the exact configured description,
+policy/action IDs and context, and maps `user_id` to the confidence endpoint's
+`end_user_id`. For the complete request shapes, see the
+[learning guide](https://www.hebbrix.com/docs/learning).
+
 ```python
 import asyncio
 from hebbrix import MemoryClient
@@ -125,3 +160,14 @@ The production API publishes exact build and artifact compatibility at
 ## License
 
 MIT. See `LICENSE` in the distribution.
+## Native experience workflow (prerelease)
+
+The current source includes `client.experiences`, bounded reflection workers,
+separate lesson review/revision and explicit one-use execution admission. These
+methods require the matching new backend; the published 2.5.0 release does not
+include this extension. The candidate package supplies `hebbrix-reflect --help`.
+Importing it does not call a model, approve a lesson or execute a tool.
+
+See `docs/native-experience-operations.md` for role scopes,
+uncertain-call recovery, exact-request binding and policy rollback. Do not treat a
+lesson, score, review or issued permit as execution permission.