contextcompass 2.19.0__tar.gz → 2.19.3__tar.gz

{contextcompass-2.19.0 → contextcompass-2.19.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: contextcompass
-Version: 2.19.0
+Version: 2.19.3
 Summary: Durable, file-backed execution state for coding agents.
 Project-URL: Homepage, https://github.com/Synaptic724/context_compass
 Project-URL: Repository, https://github.com/Synaptic724/context_compass
@@ -201,8 +201,9 @@ instructions or tool permissions.
 
 ### Know Who Is Doing The Work
 
-Agents represent themselves by their assigned name and actual role, including
-in their replies, ticket posts and Notes. If several agents share one GitHub
+Agents identify themselves by their assigned name and actual role in ticket
+bodies, Notes and ticket comments. Ordinary chat messages do not need a
+name/role prefix. If several agents share one GitHub
 account, you can still tell who wrote the finding or did the work. The person
 accountable for a ticket, its executor, its authors, its publisher and its
 reviewer are recorded separately. Posting a result is not the same as authoring

{contextcompass-2.19.0 → contextcompass-2.19.3}/README.md

@@ -180,8 +180,9 @@ instructions or tool permissions.
 
 ### Know Who Is Doing The Work
 
-Agents represent themselves by their assigned name and actual role, including
-in their replies, ticket posts and Notes. If several agents share one GitHub
+Agents identify themselves by their assigned name and actual role in ticket
+bodies, Notes and ticket comments. Ordinary chat messages do not need a
+name/role prefix. If several agents share one GitHub
 account, you can still tell who wrote the finding or did the work. The person
 accountable for a ticket, its executor, its authors, its publisher and its
 reviewer are recorded separately. Posting a result is not the same as authoring

{contextcompass-2.19.0 → contextcompass-2.19.3}/src/context_compass/AGENTS.MD

@@ -42,14 +42,17 @@ holds state about the work that lives outside this repository.
   status widgets, planning trackers, session memory - to plan, track, route, or
   record your work.
 - You MUST use the configured Context Compass work backend for Epic/Story/Task
-  tickets and their `## Notes`. `work_tracking.backend` in
+  tickets and their durable Notes, supported comments and authorized linked evidence.
+  `work_tracking.backend` in
   `config/context_compass_config.yaml` defaults to `local` when absent. In
   `local` mode, read and update tickets under `tickets/epics/`,
   `tickets/stories/`, and `tickets/tasks/`. In `github_codex_plugin` mode,
   resolve the configured `connection_nickname` through the current GitHub
   account catalog before calls, then fetch and update Issues through that
   connection; each Issue body
-  holds its template, Status, and `## Notes`. A Project URL is optional. In both modes,
+  holds its template, Status, `## Notes` and current resume view; supported Issue comments
+  may hold attributed findings directly without copying every finding into the body.
+  A Project URL is optional. In both modes,
   `attention_board.md`, `artifact_board.md` + `artifacts/`,
   `context_management/`, and `mailbox_board.md` remain local. Plugin mode also
   uses local `issue_board.md` for agent claims. Read the backend-specific general

{contextcompass-2.19.0 → contextcompass-2.19.3}/src/context_compass/MANIFEST.md

@@ -6,7 +6,7 @@ from the files themselves, which is the only reason it can be trusted.
 | field | value |
 | --- | --- |
 | manifest_version | 1.0.0 |
-| package_version | 2.19.0 |
+| package_version | 2.19.3 |
 | files | 465 |
 
 ## Lane policy
@@ -40,7 +40,7 @@ Everything outside them is STRICT: an upgrade sweeps what is not listed here.
 | path | class | sha256 |
 | --- | --- | --- |
 | `.gitattributes` | PACKAGE | `9ff348d31ff5f0941a76321a0ef45d47acb5bd218c3febffd3885f453ea325ef` |
-| `AGENTS.MD` | PACKAGE | `37ee27cacf1151457bb48e8877e8e755fd4661c90b19dc013982ccfd23c55697` |
+| `AGENTS.MD` | PACKAGE | `4666e7ca0151711cd49a08d6ac11d455916855846510d012b812da24c3b11adb` |
 | `agent_onboarding/default/continuity_fact_checker/AGENTS.MD` | PACKAGE | `3928c7c3959d7c75e0b3752cce505119060bed73b4ad565923d4801cfa703557` |
 | `agent_onboarding/default/continuity_fact_checker/behavioral_guidelines/continuity_fact_checker_workflow.md` | PACKAGE | `ace3e5e300fda18719730e05bdb0ca15d8afdc32289e1a13a7c8bd3d91470753` |
 | `agent_onboarding/default/continuity_fact_checker/examples/continuity_fact_checker_task_flow.md` | PACKAGE | `97303ea953c81565410b611848b42b4ec84f73d6351ae2754111c7bd2dd4e4aa` |
@@ -112,9 +112,9 @@ Everything outside them is STRICT: an upgrade sweeps what is not listed here.
 | `agent_onboarding/default/draft_writer/skills/draft_writer_execution.md` | PACKAGE | `c2c32f82b91b0fb793b29421990bc6d0a4452f444531cd9741c931001e40e0e7` |
 | `agent_onboarding/default/draft_writer/WORKFLOWS.MD` | PACKAGE | `eb488174d9c52d130fac93715da91e8850d29aac9bbd84b1be3ff16a89df6621` |
 | `agent_onboarding/default/draft_writer/workflows/README.md` | PACKAGE | `c26b46d75cafb3bf5ae9d6e71d09490e6f18d58c0313bbf39fc0df85b8fe5801` |
-| `agent_onboarding/default/engineer/AGENTS.MD` | PACKAGE | `0fd909bafc157c059b2ba2c33b6582fdcdebb1651c07aa96279038510de5dc1a` |
+| `agent_onboarding/default/engineer/AGENTS.MD` | PACKAGE | `ad431350f713f0e3a6c084ae4fc71886eca6a985d77b169e369c3f44800485c6` |
 | `agent_onboarding/default/engineer/behavioral_guidelines/engineer_workflow.md` | PACKAGE | `591262fe58d4d832c678a466dd2692aa905df7711b451be57320a7b10baa9661` |
-| `agent_onboarding/default/engineer/behavioral_guidelines/task_execution_and_validation.md` | PACKAGE | `2dbfdcbbb8da4d16733f26f3b99bdc45437282e7c8562e82ad492dab31ce8ac8` |
+| `agent_onboarding/default/engineer/behavioral_guidelines/task_execution_and_validation.md` | PACKAGE | `fa50dfc2d126f742ac0d99717314df1cd496f38c597ddca055296017cc1f7648` |
 | `agent_onboarding/default/engineer/examples/artifact_workflow.md` | PACKAGE | `c879058f7f61aa1d33f16f2276ccf792a6d835b2e5017098e776f2d9f0edf85b` |
 | `agent_onboarding/default/engineer/examples/eng_task_flow.md` | PACKAGE | `a5f38f4a9d858eabdf66a4a465887a9e83845f30b6f3c0d1eed7ee1b8d621984` |
 | `agent_onboarding/default/engineer/policies/ctx_autonomy_policy.md` | PACKAGE | `af66fa71612ae763b2b54d4f0e574956c3e151dcd38526000f53bf83a2e4df19` |
@@ -136,39 +136,39 @@ Everything outside them is STRICT: an upgrade sweeps what is not listed here.
 | `agent_onboarding/default/engineer/skills/technical_expertise.md` | PACKAGE | `07f2979c10673b405581017aab541790153b66424a3e75ea0a841a5f832b9adf` |
 | `agent_onboarding/default/engineer/WORKFLOWS.MD` | PACKAGE | `2804d7032d8a718304193ad9fc237e75537e3f778360703b34a3f0383d5c2599` |
 | `agent_onboarding/default/engineer/workflows/README.md` | PACKAGE | `b242a08fc1ff33ca4c63e300bfd89ebf72088169aa9b9afaed731bc5d14ec1b5` |
-| `agent_onboarding/default/general/AGENTS.MD` | PACKAGE | `d940dc21774146243d3399ab078907bca807122894c23ddb5c4799cc1b6f3b73` |
-| `agent_onboarding/default/general/behavioral_guidelines/agent_lifecycle_and_heartbeat.md` | PACKAGE | `7b1f437708ec0ff69123c37d256565ddbdc1ff8a81050bbbcc07fd4b9adf9f16` |
+| `agent_onboarding/default/general/AGENTS.MD` | PACKAGE | `f5007245f000c1e36e8d9e07e5f427dace97bc8f93a6fa673ace9dce6d39d0fa` |
+| `agent_onboarding/default/general/behavioral_guidelines/agent_lifecycle_and_heartbeat.md` | PACKAGE | `f0f2bfa601181aae1d28faa082a35881703b8f383a1455c93853932dda7e78fd` |
 | `agent_onboarding/default/general/behavioral_guidelines/onboarding_summary.md` | PACKAGE | `f44f530b09b8bb2dce40891aee43ca7e0d0b07bcfc61f68e8e96c05aba71b5e9` |
 | `agent_onboarding/default/general/behavioral_guidelines/README.md` | PACKAGE | `4fc03023bb404a1cc141e818855797aece8c67ddd07ea3324fd042cf0ec71629` |
-| `agent_onboarding/default/general/behavioral_guidelines/work_intake_and_execution.md` | PACKAGE | `0ab1110e36047e772e4c0babd50a34b13bc2a3a8b5945df496b94d4722d0f7ff` |
-| `agent_onboarding/default/general/policies/policy_skills.md` | PACKAGE | `337c11ae46d95133df51513b1866414dc21c4dc78375da003376705c8bec97c2` |
+| `agent_onboarding/default/general/behavioral_guidelines/work_intake_and_execution.md` | PACKAGE | `84b91a3e414e2c1d528be970604b8a950e16943e4ade7896efac7bca7ff3572b` |
+| `agent_onboarding/default/general/policies/policy_skills.md` | PACKAGE | `8bb02cbf1157ae9ad578fb4f000daf5a24d7276a05d3a945259d838b2e00f4d0` |
 | `agent_onboarding/default/general/README.md` | PACKAGE | `405ecd65632a0b05cf4d251f76c8ff135fdfb12fe6d460d6ea4d5082efda1cdc` |
 | `agent_onboarding/default/general/SKILLS.MD` | PACKAGE | `2303e4c9225e988bfb15d9541c979c69a498c54b8971a4fbfabac8bc3afd835b` |
-| `agent_onboarding/default/general/skills/active_documentation.md` | PACKAGE | `2822e6fa9841ba6ecc0b06cd4007e3a695d20159892d150691a097ac2b8b8c02` |
+| `agent_onboarding/default/general/skills/active_documentation.md` | PACKAGE | `e982fe2bacd1d4c403e423435bba7ef93afd91f3db3b01f19a1e5fab9edef060` |
 | `agent_onboarding/default/general/skills/active_pointerboard.md` | PACKAGE | `caceb81ace03dc804c38934d11fe7e324e47505c3006894344f1949da1f7bf7e` |
 | `agent_onboarding/default/general/skills/agent_communication_backend.md` | PACKAGE | `cbe8c2dffd6e9e9915f1601463e2bf8fb5805fbbf279ede5ea189e91393d3429` |
-| `agent_onboarding/default/general/skills/agent_identity.md` | PACKAGE | `212bcb6a0a69ebb3244bd06df3321f6b483750b538983b4945d178db4e2c2e1b` |
-| `agent_onboarding/default/general/skills/agent_lifecycle.md` | PACKAGE | `a25b4f0d9e6b2ae02ac5c009b976319d719f3a1bd7fee04ffa2769ff625930c2` |
+| `agent_onboarding/default/general/skills/agent_identity.md` | PACKAGE | `0e313f6c053b697f7c6bf32ef613ece738a62b806791ba03e521788a1e89f620` |
+| `agent_onboarding/default/general/skills/agent_lifecycle.md` | PACKAGE | `88cb4d3009615f01818c58ea317d2c0b6a1a8f859608321bb891ac97c63741a3` |
 | `agent_onboarding/default/general/skills/agent_session_state.md` | PACKAGE | `3124dbfdadb14cdf55a42790a16aafe7b926f6078cf3490e2b83affc50b68046` |
-| `agent_onboarding/default/general/skills/agent_stance.md` | PACKAGE | `912ee9e5651e8f573f89634d32d964afc6cc96d1a38f4bddc0ec14f8ae0bbbca` |
+| `agent_onboarding/default/general/skills/agent_stance.md` | PACKAGE | `6d259f4e79ff30b12af0914319b85206e13a273f4b741db2760f1a4447f48344` |
 | `agent_onboarding/default/general/skills/career_selection.md` | PACKAGE | `f6848776d7fdf1082f0b3da66cf781f0bede746b181c8006214106d718c153fe` |
-| `agent_onboarding/default/general/skills/codex_mcp.md` | PACKAGE | `a9e48c7205565fb6da82e6dedd88979b2b465180accad10fc2212605f5754d73` |
+| `agent_onboarding/default/general/skills/codex_mcp.md` | PACKAGE | `8ef7f5975922bd59b438376ee21f0c7ce49fe9e4e9f13ce821d71d837dd02fb5` |
 | `agent_onboarding/default/general/skills/compaction_requirements.md` | PACKAGE | `ec65f1f98b0292b154e57ce1e379b950143320420701945631228853c2108506` |
 | `agent_onboarding/default/general/skills/configuration_standards.md` | PACKAGE | `abf610ca6633c14d309fe088dd1e6da793d7a8c8c2afd72b5a66c26a826b1276` |
-| `agent_onboarding/default/general/skills/context_compaction.md` | PACKAGE | `060c248e8b64f46d3b63e667bf9fa7e7a72d4a94702142f56b5806ba7f8b5bdc` |
+| `agent_onboarding/default/general/skills/context_compaction.md` | PACKAGE | `2d1b72abad44a3cbae80a06e61932fdcf3b5d780660b0b943de27106ec683889` |
 | `agent_onboarding/default/general/skills/context_gold.md` | PACKAGE | `1203682dbe6ed0311811b5034e8589a4eb3cf8a71b129ea76984ab89b3f3d0cc` |
 | `agent_onboarding/default/general/skills/context_management.md` | PACKAGE | `cfc9f0cf1873720130714e331259b443ec7031f77a83b4db2a129b1be1987cca` |
-| `agent_onboarding/default/general/skills/context_window_budget.md` | PACKAGE | `47cb807557d4e6b48e0546f5c87a9df4a4cc1a24fa1de24dddcc2fed6a0dd5cb` |
+| `agent_onboarding/default/general/skills/context_window_budget.md` | PACKAGE | `d3188124914b8ea1f5d2fb488207ca0720a02e5e61f6f54355a4db4693bf2346` |
 | `agent_onboarding/default/general/skills/execution_contract.md` | PACKAGE | `92b61c0d6c39e3eb49fa89fe972c1774b1f7dbc3ad0e3c6d50ed6a7742e6219a` |
 | `agent_onboarding/default/general/skills/general.md` | PACKAGE | `cb43e243d879bfb30e70d03685449a3f25cbd54b5491e9a45c150b9234c66081` |
 | `agent_onboarding/default/general/skills/github/check_setup.py` | PACKAGE | `5180b19d6ff25dfb23a5d8361a916fc361f95d68b28e7acc2031b280fe67a1b3` |
-| `agent_onboarding/default/general/skills/github/codex_plugin.md` | PACKAGE | `9fee6f1d6eeea57576a48dec2829f8b96db3c204ab880803253c77e2cdd62b0d` |
+| `agent_onboarding/default/general/skills/github/codex_plugin.md` | PACKAGE | `ce35d7a89d5b57eb02ac5b9328d2f727d654a93e42e7df63756c6c51091bee84` |
 | `agent_onboarding/default/general/skills/github/commands.md` | PACKAGE | `f966014768ffe94334ed009013463cf986cf1180b8c859671040e55cb60417fd` |
 | `agent_onboarding/default/general/skills/github/migration.md` | PACKAGE | `1f3eb34fd97e70adefdcf4fef7442eca72b598cfc19733781a633a3273c11c0a` |
 | `agent_onboarding/default/general/skills/github/README.md` | PACKAGE | `a288aeb73a1ad3d3fcb91c6b0d33d59cac1dc2f7d9deac42fc6d5efe43571e07` |
 | `agent_onboarding/default/general/skills/github/setup.ps1` | PACKAGE | `7c19a462c053ecc8c0ac8a1d7dc7da860e7537d124847210ec200ceaa50f9c06` |
 | `agent_onboarding/default/general/skills/github/setup.sh` | PACKAGE | `c215cdf40e2265a0e84be71db604963350e3efd142e9741f7fafe205c5c54db8` |
-| `agent_onboarding/default/general/skills/github/workflow.md` | PACKAGE | `297a27cf2f0cf6dc75748beb8acc9cd287b85a911772d19a839b62ee065d9e09` |
+| `agent_onboarding/default/general/skills/github/workflow.md` | PACKAGE | `d47844b15c86afa4034b1fe559e250574eb7d0220f090886b063d64ca728ca67` |
 | `agent_onboarding/default/general/skills/harness_custom_instructions.md` | PACKAGE | `8c1e4f2949e092785ed35117ac5239c619ab64c791a6c2a749a575a95482dc9f` |
 | `agent_onboarding/default/general/skills/llm_full_usage.md` | PACKAGE | `00cf47f3eda35e3a3ab3506d7eba5ef31e35384c5902425c9d6286502c84273c` |
 | `agent_onboarding/default/general/skills/mailbox_protocol.md` | PACKAGE | `fb2eafebbdbfa578df0b5b83a253eca43a63426fbfdece09d08e2c96b9465b76` |
@@ -180,15 +180,15 @@ Everything outside them is STRICT: an upgrade sweeps what is not listed here.
 | `agent_onboarding/default/general/skills/role_local_workflows.md` | PACKAGE | `b0634d08a2164981779ba3a3ccdf5f254509eeff624a3c0e6133e9eec0da1d84` |
 | `agent_onboarding/default/general/skills/security_and_secrets.md` | PACKAGE | `bd58e29bce07c500a3678ba6571c7955d61309a9ea53f909e8ec9527a98c0cbd` |
 | `agent_onboarding/default/general/skills/self_certification.md` | PACKAGE | `f52b2d367fdbca0f6eb687be935235ba2e7566b6ebfa9fb6bb1f54995ba31aab` |
-| `agent_onboarding/default/general/skills/ticketing.md` | PACKAGE | `951b02cc16058159148e471859f6bc6a518fff45d2581fc1aa058e69aa287e83` |
+| `agent_onboarding/default/general/skills/ticketing.md` | PACKAGE | `f767c8b27cbd7a77fdac029aaf99193b72b3ebfd39b3d650789941763b1f5210` |
 | `agent_onboarding/default/general/skills/ticketing_skill_contract.md` | PACKAGE | `86154f6068b36af47999b50300a7760c628dfb1ea670a1bd8b78e774b20e309b` |
 | `agent_onboarding/default/general/skills/ticket_closure_attention_sync.md` | PACKAGE | `001ebf4aa2c927421c94beb93eb84d4d07878d3d1ab121c66b6a4671268d6937` |
-| `agent_onboarding/default/general/skills/ticket_design.md` | PACKAGE | `8833c5e79755990fa4029d9d955316eb96b1b21ed7a99ad6382a7e1286d46bc6` |
-| `agent_onboarding/default/general/skills/ticket_microcycle.md` | PACKAGE | `7a394001f5aa79e32bd44455a6189836e4fbfad70e6f52b9a653635a21b3f264` |
+| `agent_onboarding/default/general/skills/ticket_design.md` | PACKAGE | `7a42efda34866fe68d604ef35b71e478b2153ea1e34013d9421b30ad8ac8e902` |
+| `agent_onboarding/default/general/skills/ticket_microcycle.md` | PACKAGE | `381c397d9dfebe0d1ba6682a17e3a9960e991ebfbe05d06188c4b31402b1a12a` |
 | `agent_onboarding/default/general/skills/unknowns_gate_reference.md` | PACKAGE | `d68cb2ded95de832d0ebb2f32fbcdae01168a783d5f9fe75047ef2ec84af8d12` |
 | `agent_onboarding/default/general/skills/user_approved_certification.md` | PACKAGE | `6aeac190ac39f22120937b1e4d0cb6384a02a2f800cea3eaf4224ea056bba37c` |
-| `agent_onboarding/default/general/skills/workflow.md` | PACKAGE | `e4fc21b6ba5b8e1bedb8abe05f7bd410241d01383f9953373e5a100923956c7c` |
-| `agent_onboarding/default/general/skills/work_tracking_backend.md` | PACKAGE | `d0d84d9e709ca437c998051e410b427b2f8eded73b1eed8b7e948386515c3ba2` |
+| `agent_onboarding/default/general/skills/workflow.md` | PACKAGE | `a7a87420f0aa08cc7c04d7d320d8855b3837150fbb34d19f2cba35c7f01ef3bd` |
+| `agent_onboarding/default/general/skills/work_tracking_backend.md` | PACKAGE | `0044695e4d44fcf383fe6e12d53b8bbcf4db857370dfca20d58ccd48c0bd3c45` |
 | `agent_onboarding/default/general/WORKFLOWS.MD` | PACKAGE | `5df69d8d7fb9d8094d7765eacc58772d74113729da5235293968dce86365c23f` |
 | `agent_onboarding/default/general/workflows/cleanup_context_compass.md` | PACKAGE | `284c857fd829d9f183d9e555676ddcea87609bdf91db22a6ebb2ab14b15f402b` |
 | `agent_onboarding/default/general/workflows/README.md` | PACKAGE | `9376b5753db22c7b4264a17229b74cef6e684aa647aae8546b589ce367d10c35` |
@@ -408,7 +408,7 @@ Everything outside them is STRICT: an upgrade sweeps what is not listed here.
 | `artifacts/README.md` | RESET | `196e2022e5d708af65d39b7e434c792f5c1374d5eb8b542f4d18ee534bbb4ad3` |
 | `artifact_board.md` | LIVE | `45fa4083b4bb7a25f25cbbcf0e7304fd15d98a8ae7a7a8e492ccd0cd3a3edc93` |
 | `attention_board.md` | LIVE | `3148067306419a7f802960fe2704acafee1c4683bed9f1d7baf775574db79bdc` |
-| `config/context_compass_config.yaml` | CONFIG | `4d5a1e4404aa5e1e974fdd4bf1e1780da22df3108aef6410325049b6b9774f04` |
+| `config/context_compass_config.yaml` | CONFIG | `955b2038b584c1b74855ab226101ec34e0e49d86e2bd0ba25fb0c1c96e01900d` |
 | `CONTEXT_COMPACTION.md` | PACKAGE | `439b20cebd57305a0de0cad051364525ab0e6139ca11e815ddd04ea36fd2747a` |
 | `context_management/artifacts/.gitkeep` | RESET | `01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b` |
 | `context_management/context_artifact_template.md` | RESET | `9a57525f3160d21612da41c4f371d6ba4f50cf681b0e9009e266c67458187b9e` |
@@ -471,10 +471,10 @@ Everything outside them is STRICT: an upgrade sweeps what is not listed here.
 | `system_docs/patches/active/_template_patch_id/code_description_patch_TEMPLATE_COMPONENT.md` | RESET | `262130e44568da2ce6720095b9ab9956ab9787d81a5e2daa73ba3300e3c04d13` |
 | `system_docs/patches/active/_template_patch_id/component_patch_TEMPLATE_COMPONENT.md` | RESET | `fedc2095f94e5be8f11bed1fae34faee05730d78c435819e907970356ecebd1c` |
 | `system_docs/system_docs_read_first.md` | RESET | `792b745c1eb7947c135f188ee2a055408bff9e0a39f7ff4432f25468b32cc61b` |
-| `templates/epic_template.md` | PACKAGE | `8cd7ff15ca237456211a632bde4680fa5edc380e73918a8913ff6c524c7fca4c` |
-| `templates/story_template.md` | PACKAGE | `26bdbb21c7d6d9bc79f2a23e54fceeb53d62629fa08433eabed7cece8d7292ff` |
-| `templates/task_template.md` | PACKAGE | `36695623c0e4502babd1ca3578c8c4981baa972bbbb8a743b35ad040f20aac2e` |
-| `templates/ticket_contract.json` | PACKAGE | `609b85839735d487dafa2c162b1022f7386d89b08435a8319ab8551948d89928` |
+| `templates/epic_template.md` | PACKAGE | `560344360d3579b90dda1f6a26dea5c6d375316f1f7d1fb6f726dab0d21f6708` |
+| `templates/story_template.md` | PACKAGE | `f9ef141e45be40f671b4a4b3ec703ef968a794d4695e6c438fcd7b75efbd786a` |
+| `templates/task_template.md` | PACKAGE | `bc10fe7364dc2ee16403905e94f05b6e1315e4d6a61235aa3b5d64dadfddc71c` |
+| `templates/ticket_contract.json` | PACKAGE | `e7e530971f481c17f09a94c5af1bb1da98a6c0d572242d735ccf093a32918300` |
 | `templates/workflow_advanced_template.md` | PACKAGE | `312aa2e4e2f17a04959419e7f4af29a4e199239c9d9c453688b7025e56bf1a74` |
 | `templates/workflow_simple_template.md` | PACKAGE | `b78e8c24260030735d2d9558fc33f5f31d737a3accc19f71645d373fcbd80492` |
 | `tickets/epics/archive/.gitkeep` | RESET | `e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855` |

{contextcompass-2.19.0 → contextcompass-2.19.3}/src/context_compass/agent_onboarding/default/engineer/AGENTS.MD

@@ -42,8 +42,8 @@ as top-priority bootstrap enforcement rules.
 
 ## 4) Critical Rule Always Enforced
 
-If you do not know, **find out, then ask what is still open** - and **get explicit
-confirmation before acting**.
+If you do not know, **find out, then ask what is still open**. Reuse actual authorization
+for included work; escalate genuinely missing decisions or permissions before dependent action.
 
 The order matters and the two halves are different.
 
@@ -52,8 +52,9 @@ The order matters and the two halves are different.
   is written down somewhere in this repository, go and read it. An agent that asks
   "should I look at the component map?" has converted a five-second lookup into a
   round-trip and learned nothing in the meantime.
-- **Editing is acting.** File changes, state-changing commands, scope expansion:
-  those need explicit confirmation, every time, per section 8.
+- **Editing is acting.** File changes and state-changing commands need actual authority,
+  not fresh confirmation for each already-authorized step. Material scope expansion or a
+  reserved decision retains its approval gate, per section 8.
 - **Ask about what reading could not settle** - a decision between compliant
   options, a genuine ambiguity in intent, which of several subsystems the user
   means. Bring what you already found; a question that shows you looked first is
@@ -77,7 +78,8 @@ Before acting on anything **outside the explicitly agreed architectural plan**,
 * **Challenge questionable ideas** respectfully and explain why (risks, inconsistencies, or conflicts).
 * **Push back when direction appears technically wrong**; do not default to agreement.
 * **Ask clarifying questions**; if anything is unclear or you are unsure, investigate briefly and then stop and ask.
-* **Keep me in the loop and get explicit approval before any change** (file edits, state-changing commands, or scope expansions).
+* **Keep me in the loop** and obtain missing authority for material expansion or reserved actions;
+  do not request another approval for ordinary included edits or commands.
 * Follow `agent_onboarding/default/engineer/skills/technical_expertise.md`: diagnose root cause with depth and breadth before implementing; do not add blanket defensive guards without contract evidence.
 * Use `SKILLS.MD`, shared `ticketing.md`, and the selected backend's general
   workflow skill for Epic/Story/Task ticketing and formatting.
@@ -152,7 +154,8 @@ This is not optional. For **all public classes and public methods**, write docst
 * Before making edits, read and follow existing repository conventions:
   `README`, `CONTRIBUTING`, `docs/`, and any architecture/design notes.
 * Do not invent new conventions if the repo already has a pattern.
-* If repo docs conflict with these instructions (or with each other), **stop and ask** before proceeding.
+* Record actual source conflicts. Resolve an already-authorized correction within scope;
+  ask for unresolved material policy/authority decisions rather than routine file selection.
 
 ### 7.4) No Drive-By Refactors
 
@@ -209,7 +212,7 @@ For repo-wide mechanical edits (e.g., "add this import everywhere", "add a class
 
 ## 8) Operating Protocol How You Should Work
 
-### 8.1) Propose Confirm Implement
+### 8.1) Plan Implement Within Authority
 
 Before making non-trivial edits:
 
@@ -217,13 +220,15 @@ Before making non-trivial edits:
 2. List the constraints you will obey (especially docstrings/comments and no-drive-by refactors).
 3. List the **exact files / symbols** you will modify.
 
-If any of the above is uncertain, **stop and ask** before editing.
-For this repo, treat **all** edits as requiring explicit confirmation, even if they seem trivial.
+Investigate implementation uncertainty within authorized scope. There is no per-step approval
+for ordinary included edits, tests, peer coordination or ticket maintenance. Preserve reserved
+decisions, security/action permissions, owner STOPs and required tests/reviews.
 
 ### 8.2) Scope Control
 
 * Stay within the declared files/symbols.
-* If you believe the change requires touching more than the declared scope, **ask first**.
+* Record related files needed for the complete authorized outcome. Ask for material scope expansion,
+  not another admission for ordinary included multi-file work.
 
 ### 8.3) Documentation Ritual
 
@@ -260,7 +265,7 @@ As a ritual, after implementing a change:
 
 ## 9) Stop Conditions Ask Before Proceeding
 
-Ask for explicit confirmation if any of these are true:
+Ask for a missing decision/permission when these actions are outside current authorization:
 
 * You want to touch **many files** (repo-wide sweeps) and no codemod approach was approved.
 * You want to rename/move files or symbols.

{contextcompass-2.19.0 → contextcompass-2.19.3}/src/context_compass/agent_onboarding/default/engineer/behavioral_guidelines/task_execution_and_validation.md

@@ -10,7 +10,10 @@ Story steps
    - Confirm scope, acceptance criteria, and files in scope.
    - Treat unknowns as UNKNOWN by default.
 2) Investigate and document
-   - Investigate until one meaningful finding, then append a `## Notes` entry before more investigation.
+   - Record each meaningful finding before dependent work in supported Notes, attributed
+     comments or authorized linked evidence under shared `ticketing.md`.
+   - Multiple meaningful comments may carry findings directly; no forced body copy is
+     required before ordinary continuation. Preserve historical Notes and author attribution.
    - Include evidence (`path:start_line-end_line`; use `start=end` for single-line evidence) and a concrete NEXT action.
 3) Implement
    - Make minimal, reviewable changes.
@@ -22,8 +25,11 @@ Story steps
    - Summarize changes and reference relevant files.
    - List remaining risks or follow-ups.
 6) Close
-   - Ask whether acceptance criteria are met before closing the ticket in the
-     selected backend.
+   - Authorized agents close routine completed work after criteria, required tests and required
+     reviews are satisfied, without another owner ping. Reserved owner decisions still wait.
+   - Review is proportionate to actual consequence, uncertainty and contract; self-checks are
+     not independent review. Use shared `ticketing.md` for qualified reviewer acceptance and
+     the selected backend's verified closure sequence.
 
 References
 - `AGENTS.MD`

{contextcompass-2.19.0 → contextcompass-2.19.3}/src/context_compass/agent_onboarding/default/general/AGENTS.MD

@@ -92,7 +92,7 @@ Ask the user for **guidance** when you cannot tell where to look. Never for
 
 ## Operating Protocol (How You Should Work)
 
-### 2) Propose -> Confirm -> Implement
+### 2) Plan -> Implement Within Authority
 
 Before making non-trivial edits:
 
@@ -100,13 +100,16 @@ Before making non-trivial edits:
 2. List the constraints you will obey.
 3. List the **exact files / symbols** you will modify.
 
-If any of the above is uncertain, **stop and ask** before editing.
-For this repo, treat **all** edits as requiring explicit confirmation, even if they seem trivial.
+Investigate uncertain implementation details within authorized scope. There is no per-step approval
+for ordinary edits, tests, peer coordination or ticket maintenance already covered by that scope.
+Escalate a genuinely missing decision, material scope expansion, reserved acceptance or security/
+action permission. Planning and ticket creation do not grant authority for new consequential actions.
 
 ### 3) Scope Control
 
 * Stay within the declared files/symbols.
-* If you believe the change requires touching more than the declared scope, **ask first**.
+* Select and record related files needed for the complete authorized outcome; ordinary in-scope
+  file selection and focused repair need no new coordinator admission. Escalate material expansion.
 
 ### 4) Documentation Ritual
 
@@ -124,37 +127,48 @@ As a ritual, after implementing a change:
 
 ### 6) context_compass Ticket Planning (Required)
 
-* Before starting any planned work beyond answering questions, create a structured
+* Before starting any planned work beyond answering questions, search/reuse or create a structured
   Epic/Story/Task ticket in the selected backend. Local mode uses the `tickets/`
   lanes; plugin mode uses an Issue body in the configured repository.
-* Treat `attention_board.md` as routing-only state and the active ticket `## Notes` section as canonical durable execution memory.
+* Document useful discoveries, including outside the currently managed workstream, in an authorized
+  repository/audience. Self-accept eligible work within actual authority, tools, capacity and custody,
+  or return its ticket with an exact help request. Ticket creation does not grant new access.
+* Own the complete authorized outcome, including coordination, tests, applicable review, records
+  and routine closure. Do not wait for approval between ordinary included steps.
+* Treat `attention_board.md` as routing-only state and the selected ticket as the durable record.
+  Multiple meaningful comments or authorized linked documents may hold attributed findings directly.
+  No forced body copy is required before ordinary continuation. Preserve historical Notes/comments.
 * Hard execution gate (mandatory):
   - Do not implement or validate unless an active ticket exists for the work.
   - Do not implement or validate unless `attention_board.md` has an active row routing to that ticket.
   - If the active ticket sets `CONTEXT_MANAGEMENT_REQUIRED: true`, do not
     implement or validate until every linked context artifact has been read.
-  - Do not start a new investigation tranche, code edit tranche, or validation tranche until the current meaningful finding is written in ticket `## Notes` with evidence.
+  - Record meaningful findings with evidence before work that depends on them, using Notes,
+    supported attributed comments or authorized linked evidence under `skills/ticketing.md`.
   - If any gate above is missing, stop and repair ticket/board/notes state before continuing.
 * Default every new claim to `UNKNOWN` until source evidence proves otherwise.
 * Ticket Microcycle enforcement defaults to strict and is configurable in `config/context_compass_config.yaml`.
 * Follow a strict Ticket Microcycle while working:
   1. Route from `attention_board.md` to one active ticket.
   2. Investigate until one meaningful finding (fact, blocker, decision, measure, or hypothesis worth testing).
-  3. Immediately append a `## Notes` entry before any further investigation.
-  4. Continue only after the note includes evidence and a concrete next step.
+  3. Record the finding once in a supported durable contribution, not a duplicate body report.
+  4. Continue under the existing scope after evidence and the next action are clear.
 * If `workflow.ticket_microcycle.enabled` is `false`, use relaxed mode:
   - still document each meaningful finding,
-  - still update notes before implementation and validation,
+  - still record evidence before dependent implementation and validation,
   - still require evidence for `FACT` and `DECISION` claims.
-* No second investigation tranche is allowed before documenting the current meaningful finding in the ticket.
+* Evidence timing is not a body-writer permission gate on another agent's independent contribution.
 * Do not implement from `UNKNOWN` or `HYPOTHESIS`; promote to `FACT` or `DECISION` with evidence first.
 * If investigation must expand beyond the current subsystem or exceed
   `workflow.ticket_microcycle.expansion_gate_max_files` in one pass, append a
   `DECISION` note and ask the user for scope confirmation before continuing.
 * Follow `SKILLS.MD`, shared `ticketing.md`, and the selected backend's
   workflow for the deep descriptive format and tracking model.
-* The ticket must define scope, steps, and intended deliverables; share it and wait for approval.
-* Maintain a `## Notes` section in active tickets and append in-flight findings with `path:start_line-end_line` evidence pointers as they occur, not in end-of-pass batches.
+* The ticket defines scope, deliverables, actual authority and observable completion. Reuse existing
+  authorization; ask only for a genuinely missing decision or action permission.
+* Maintain the required `## Notes` section and preserve history. Findings may be in supported
+  comments/documents with exact evidence pointers; current state/decisions/handoff stay coherent
+  at material transitions. Do not copy every report into Notes.
 * Evidence ranges in notes must include both start and end lines. If the evidence is one line, repeat it (`path:42-42`).
 * Context management is optional:
   - use it only when the ticket explicitly opts in
@@ -167,10 +181,20 @@ As a ritual, after implementing a change:
   (`SCORE_0_TO_10`); if score is below
   `workflow.ticket_microcycle.minimum_note_score`, improve the note before
   proceeding.
-* Before closing any ticket, walk through what was achieved and ask if the acceptance criteria are met.
-* Only after explicit confirmation, complete the ticket in its selected backend:
+* The assigned agent owns current status, evidence, requested scoped review and final closure.
+  Review is proportionate to actual consequence, uncertainty and the contract, not an automatic
+  full-code-review parking state. Self-checks are not independent review.
+* Authorized agents close routine completed work after criteria, required tests and required reviews
+  are satisfied, without another owner ping. Reserved owner decisions still wait for explicit acceptance.
+  Missing authority or an unmet gate is a concrete blocker, not inferred approval.
+* Record delegated acceptance or reserved-owner disposition, then complete the selected backend:
   move local tickets to matching completed folders, or verify the Issue body
   has `Status: done`, completion summary, and reason, then close through the plugin.
+* Record each meaningful changed finding once at appropriate task/story/epic depth. Keep concise claim,
+  impact, material limits and next action inline with exact retrievable supporting links; do not copy
+  full linked reports or create substantive Notes for unchanged checks/ACKs. Preserve required in-body
+  state/evidence, prior Notes and custom regions. Parent owners reconcile child outcomes and remaining
+  work; child completion does not accept the parent.
 * Immediately after completing any ticket, run deterministic `attention_board.md` sync:
   - remove/replace active rows that reference the closed ticket,
   - prune stale attention details tied only to the closed ticket,
@@ -199,7 +223,7 @@ As a ritual, after implementing a change:
 
 ## Stop Conditions (Ask Before Proceeding)
 
-Ask for explicit confirmation if any of these are true:
+Ask for a missing decision/permission when these actions are outside current authorization:
 
 * You want to touch **many files** (repo-wide sweeps) and no codemod approach was approved.
 * You want to rename/move files or symbols.
@@ -220,7 +244,9 @@ resolved role `SKILLS.MD` files.
 - It enforces evidence-first reasoning and blocks assumption-driven claims.
 - It defines ticket-first execution so work is durable and resumable.
 - It preserves context through active notes, board routing, and compaction flow.
-- It enforces explicit approval gates before meaningful execution.
+- It enforces actual scope/action authority and reserved acceptance without serial routine approval.
+- Qualified independent reviewers may accept and close through shared `ticketing.md` when
+  all current ticket criteria are met; this does not require a reviewer on every task.
 - It sets escalation discipline for scope/risk changes.
 - It keeps security posture strict, especially around secret handling.
 - It preserves process quality across handoffs and context resets.
@@ -265,13 +291,14 @@ explicitly instead of bypassing general rules.
 
 ### 13) Expected Operator Discipline
 
-- Keep one active problem boundary at a time.
+- Keep the current authorized outcome and actual source/resource boundaries clear.
 - Make each transition explicit (investigate, decide, implement, validate).
 - Keep uncertainty visible until it is resolved with evidence.
 - Surface blockers early with concrete impact and next-step asks.
 - Preserve a clean audit trail through notes and state transitions.
-- Represent yourself in responses and authored ticket posts/Notes using the
-  assigned name and actual role/function under `skills/agent_identity.md`.
+- Identify ticket bodies, Notes and ticket comments using the assigned name
+  and actual role/function under `skills/agent_identity.md`. Ordinary chat
+  messages do not require a name/role prefix.
 - At onboarding, check the effective personal custom instructions using
   `skills/harness_custom_instructions.md`. Only offer its setup form when the
   Context Compass integration is absent. Preserve existing user preferences.

{contextcompass-2.19.0 → contextcompass-2.19.3}/src/context_compass/agent_onboarding/default/general/behavioral_guidelines/agent_lifecycle_and_heartbeat.md

@@ -14,10 +14,12 @@ Story steps
    - Ensure `attention_board.md` reflects active routing and open the linked active ticket.
 3) Work loop
    - Use tickets in the selected backend for planning and execution.
-   - Keep ticket checklists current and append findings as they occur in `## Notes`.
+   - Own the complete authorized outcome and keep current checklists/state coherent.
+   - Save attributed findings in supported Notes/comments/documents under shared `ticketing.md`.
 4) Check-out
    - Summarize what changed, what remains, and what to do next.
-   - Complete tickets only after user confirmation: move local tickets to
+   - Complete routine authorized tickets after actual criteria/tests/reviews; reserved owner
+     decisions retain their acceptance gate. Record the disposition, then move local tickets to
      matching completed folders, or record and verify Issue-body `Status: done`
      and completion summary, then close through the GitHub plugin.
 

contextcompass-2.19.3/src/context_compass/agent_onboarding/default/general/behavioral_guidelines/work_intake_and_execution.md

@@ -0,0 +1,52 @@
+
+
+# work_intake_and_execution
+
+Purpose
+- Define how we intake work and execute it using `tickets/epics/`, `tickets/stories/`, and `tickets/tasks/` tickets.
+
+Story steps
+1) Capture intent
+   - Restate the goal, constraints, and scope.
+   - Investigate unknown details within authorized scope; record a useful discovery even when
+     implementation knowledge is incomplete. Ask for a genuinely missing scope/authority decision.
+2) Create tickets
+   - Search/reuse first, then use the selected templates and work backend.
+   - Eligible discoveries outside the managed workstream may be ticketed in an authorized
+     repository/audience. Self-accept when authority/custody permit, or return an exact help request.
+   - Keep tickets deep and descriptive for handoff durability.
+3) Establish the execution boundary
+   - Share the plan and files to touch.
+   - Reuse actual authority within authorized scope; no per-step approval for ordinary included
+     work. Preserve reserved decisions, security/action permissions and actual owner STOPs.
+4) Execute
+   - Follow ticket steps and update checklists as work progresses.
+   - Own the complete authorized outcome, including peer coordination, tests, review and records.
+   - Use the configured microcycle and supported durable evidence under shared `ticketing.md`.
+   - Keep changes scoped and reviewable.
+5) Close out
+   - Walk through what was delivered.
+   - Authorized agents close routine completed work after criteria, required tests and required
+     reviews are satisfied, without another owner ping. Reserved owner decisions still wait.
+   - Review is proportionate to actual consequence, uncertainty and contract; self-checks are not
+     independent review. Failed/unrun required checks stay visible and do not become a pass.
+   - Record delegated acceptance or reserved-owner disposition, complete the selected backend,
+     then reconcile actual routing/artifact state without altering unrelated history.
+
+Artifacts touched
+- `templates/`
+- `tickets/epics/`
+- `tickets/epics/completed/`
+- `tickets/stories/`
+- `tickets/stories/completed/`
+- `tickets/tasks/`
+- `tickets/tasks/completed/`
+
+References
+- `SKILLS.MD`
+- `agent_onboarding/default/general/skills/workflow.md`
+
+
+
+
+

{contextcompass-2.19.0 → contextcompass-2.19.3}/src/context_compass/agent_onboarding/default/general/policies/policy_skills.md

@@ -6,7 +6,8 @@ Purpose
 - Enforce the policy chain so edits stay deterministic and reviewable.
 
 When to use
-- At the start of every session and before editing in a new directory.
+- At actual startup/recovery or when applicable directory/source policy changes. Reuse valid
+  reads in intact context; an ordinary comment is not another full-policy read trigger.
 
 Canonical Contract (from AGENTS.MD)
 This repository is a public library. Code quality and documentation are
@@ -69,7 +70,7 @@ Required flow
   `context_compass/agent_onboarding/default/general/skills/execution_contract.md`
   and apply its active-partner + performance-engineering rules.
 - Route active work from `context_compass/attention_board.md` and keep detailed
-  state in ticket `## Notes`.
+  current state in the ticket. Supported attributed comments/documents may hold detailed evidence.
 - Use the Ticket Microcycle with meaningful-finding note gates during
   execution.
 - Use Epic/Story/Task tickets in the selected work backend for all planned
@@ -96,7 +97,8 @@ Documentation and Convention Precedence
   `README`, `CONTRIBUTING`, `docs/`, and any architecture/design notes.
 - Do not invent new conventions if the repo already has a pattern.
 - If repo docs conflict with these instructions (or with each other), stop and
-  ask before proceeding.
+  record the actual conflict. Resolve an already-authorized source correction within its scope;
+  ask only for an unresolved material policy/authority decision, not routine file selection.
 
 Unknowns Gate
 - Apply the canonical policy in
@@ -109,17 +111,19 @@ Unknowns Gate
   requesting user resolution.
 
 Operating Protocol (How You Should Work)
-A) Propose - Confirm - Implement
+A) Plan - Implement Within Authority
 Before making non-trivial edits:
 1. Restate the goal in 3-5 bullets.
 2. List the constraints you will obey (scope, policy, and workflow gates).
 3. List the exact files / symbols you will modify.
-   If any of the above is uncertain, stop and ask before editing.
+   Investigate implementation uncertainty within authorized scope. There is no per-step approval
+   for ordinary work already covered by the outcome. Preserve reserved decisions, security/action
+   permissions, owner STOPs and required tests/reviews; no ticket grants new access.
 
 B) Scope Control
 - Stay within the declared files/symbols.
-- If you believe the change requires touching more than the declared scope, ask
-  first.
+- Record related files required for the complete authorized outcome. Ask for materially expanded
+  scope or a consequential owner decision, not another admission for an ordinary included step.
 
 C) Documentation Ritual
 As a ritual, after implementing a change:
@@ -127,7 +131,7 @@ As a ritual, after implementing a change:
 - Ensure state, evidence, and next actions are accurate and current.
 
 Stop Conditions (Ask Before Proceeding)
-Ask for explicit confirmation if any of these are true:
+Ask for a missing decision/permission when these actions are outside current authorization:
 - You want to touch many files (repo-wide sweeps) and no codemod approach was
   approved.
 - You want to rename/move files or symbols.
@@ -179,8 +183,9 @@ Operational guidance (enriched)
 - Do not improvise conventions; mirror the skills and examples.
 - Treat skills as the executable version of policy.
 - Use examples as canonical style references, not suggestions.
-- Keep scope minimal and reviewable; do not widen without approval.
-- If a change implies touching many files or renames, ask first.
+- Keep scope coherent and reviewable; do not silently widen the authorized outcome.
+- Ordinary related multi-file selection/repair is not a new approval stage. Unapproved renames,
+  dependencies, public-API changes or security/action changes retain their actual permission gates.
 
 Workflow
 1) Check for AGENTS.override.md in the target directory.