wtf-p 0.7.2 → 0.7.4

package/vendors/gemini/workflows/create-poster.md

@@ -21,10 +21,10 @@ Manuscript prose and supporting context, research, plan, review, summary, handof
 
 ## Procedure
 
-1. Confirm audience, dimensions, format, and emphasis, following the confirmation list in `protocol://templates/poster.md`.
-1a. Start from the panel structure and word budgets in `protocol://templates/poster.md`. Delete any panel the manuscript does not support rather than filling it.
-2. Select only claims supported by manuscript and evidence, then design a legible poster with source attribution.
-3. Write the poster source and its assets under the declared deliverable URI without changing project records except through a separately declared action. This action produces poster source, not a rendered image or PDF: WTF-P declares no rendering effect and runs no renderer. If the author asks for a rendered artifact, return a labeled handoff naming the exact command they can run in their own toolchain.
+1. Confirm audience, dimensions, format, emphasis, and the exact author, affiliation, contact, funding, and venue metadata, following the confirmation list in `protocol://templates/poster.md`. Never invent missing metadata; leave the visible placeholder the template names.
+1a. Start from the layout, panel structure, and word budgets in `protocol://templates/poster.md`. Delete any panel the manuscript does not support rather than filling it.
+2. Run the evidence gate in `protocol://templates/poster.md`: build the claim ledger and refuse every statement, comparison, or figure without a cited source record, manuscript passage, or named project file. Derive each diagram from named source files or documents and state their paths beneath it.
+3. Write the poster as laid-out source (the template's HTML skeleton, or the venue's mandated template carrying the same grid and type scale) plus its assets and claim ledger under the declared deliverable URI, without changing project records except through a separately declared action. This action produces poster source, not a rendered image or PDF: WTF-P declares no rendering effect and runs no renderer. If the author asks for a rendered artifact, return a labeled handoff naming the exact command they can run in their own toolchain.
 
 ## Safety and completion
 

package/vendors/gemini/workflows/create-slides.md

@@ -21,9 +21,9 @@ Manuscript prose and supporting context, research, plan, review, summary, handof
 
 ## Procedure
 
-1. Confirm audience, duration, format, and speaking goal, following the confirmation list in `protocol://templates/slides.md`.
+1. Confirm audience, duration, format, speaking goal, and the exact speaker, affiliation, and venue metadata, following the confirmation list in `protocol://templates/slides.md`. Never invent missing metadata; leave a visible placeholder.
 1a. Derive the slide count from the confirmed duration using the budget table in `protocol://templates/slides.md`, not from the manuscript's section count.
-2. Build a narrative arc from supported manuscript claims and include citations or attribution where needed.
+2. Build a narrative arc from supported manuscript claims only, running the evidence gate in `protocol://templates/slides.md`: refuse every statement, comparison, or figure without a cited source record, manuscript passage, or named project file, and derive each diagram from named source files or documents with their paths stated on the slide.
 3. Write slide source and assets under the declared deliverable URI; preview before replacing an existing deliverable. This action produces slide source, not a rendered deck: WTF-P declares no rendering effect and runs no renderer. If the author asks for a rendered artifact, return a labeled handoff naming the exact command they can run in their own toolchain.
 
 ## Safety and completion

package/vendors/gemini/workflows/plan-section.md

@@ -24,8 +24,9 @@ Manuscript prose and supporting context, research, plan, review, summary, handof
 1. Resolve one section record, load its linked context, research, evidence, decisions, and outline constraints, and enumerate the bounded `project://validations/*` collection before any specialist dispatch.
 2. Filter those records to candidates whose `subject_uri` is exactly `project://structure/outline` and whose `action_id` is exactly `create-outline`. A candidate is current only when `executed_at >= outline.updated_at`. Because the v1 validation schema carries no outline revision or content hash, disclose that this timestamp test is a conservative freshness proxy.
 3. Require exactly one current candidate and require its `status` to be `passed`. Separately verify that the current outline and target section are consistent with all current locked and deferred author choices: honor locked choices and do not treat deferred choices as resolved. A missing, stale, ambiguous, or non-passing candidate, or a decision contradiction, blocks all specialist dispatch and every plan, section, state, or validation write. Only a recovery checkpoint may be proposed on this blocked path, and it may be written only after a complete record preview and explicit author approval.
-4. Only after those prerequisites pass, delegate a bounded plan to `section-planner`, then require a fresh `plan-checker` pass over claim coverage, dependencies, file scope, citations, and decision fidelity.
-5. At confirm_plan, preview the plan and validation; on approval link the plan, update section status to planned, and reconcile state. Create a checkpoint for unresolved judgment instead of bypassing the required checker.
+4. For a literature-heavy section, first require a section-specific research artifact plus resolvable source/evidence records that cover the planned claims. If they are absent or insufficient, run `research-gap` with the configured CiteNexus backend when available, verify candidate metadata against the returned records, and stop planning with an explicit research checkpoint if evidence remains insufficient. Never invent citations or treat search candidates as verified sources.
+5. Only after those prerequisites pass, delegate a bounded plan to `section-planner`, then require a fresh `plan-checker` pass over claim coverage, dependencies, file scope, citations, and decision fidelity. Dispatch the exact WTF-P specialist roles; generic coder and verifier roles do not satisfy this workflow.
+6. At confirm_plan, preview the plan and validation; on approval link the plan, update section status to planned, and reconcile state. Create a checkpoint for unresolved judgment instead of bypassing the required checker.
 
 ## Safety and completion
 

package/vendors/gemini/workflows/research-gap.md

@@ -22,7 +22,7 @@ Manuscript prose and supporting context, research, plan, review, summary, handof
 ## Procedure
 
 1. Resolve the research question and section scope against locked/deferred decisions; agree on depth and source constraints.
-2. Search declared scholarly services only after the gate names the providers and bounded query set. When using the bundled dispatcher, `citation-search` may run with `--backend=cite-nexus` and an explicit `--providers` list after this gate. Returned results stay candidates, and this action performs no bibliography write. Verify source identity and inspection depth, and separate source records from claim-level evidence.
+2. Prefer an operator-configured, trusted read-only CiteNexus MCP connection for bounded public metadata searches when the host has already authorized it. In an explicitly selected full-auto host session for this research action, the bundled CiteNexus dispatcher may also search the free no-key public indexes `crossref`, `datacite`, `europe_pmc`, and `arxiv` without a second per-query author gate; use only selected relevant indexes with an explicit `--providers` list. Record provider IDs, queries, date, and result limits; never send unpublished manuscript text or private notes as search terms. For any other route, first obtain explicit author approval naming the providers and bounded query set. Results remain candidates and this action performs no bibliography write. Verify source identity and inspection depth, and separate source records from claim-level evidence.
 3. Synthesize supported, conflicting, and missing evidence into a Markdown research artifact; link new records and disclose limitations.
 
 ## Bundled tool execution
@@ -33,7 +33,7 @@ The declared `tool.execute` effect authorises exactly one command, run from the
 node protocol://tools/wtfp-tool.js [--offline] <command> [arguments]
 ```
 
-Run it with `list` first to read the declared commands, their arguments, their bounds, and the effects each one applies; `protocol://tools/README.md` carries the same table. A command whose effects include `network.*` performs outbound requests. Until network use has been approved for this run, pass `--offline` (or set `WTFP_TOOL_OFFLINE=1`), which makes the dispatcher refuse those commands instead of relying on prose restraint. Never execute another module in this package, never pass a logical `project://` or `wtfp://` URI as a shell argument, and treat every returned record as candidate evidence until it is verified and written to a source or evidence record.
+Run it with `list` first to read the declared commands, their arguments, their bounds, and the effects each one applies; `protocol://tools/README.md` carries the same table. A command whose effects include `network.*` performs outbound requests. Pass `--offline` (or set `WTFP_TOOL_OFFLINE=1`) until the provider/query gate is approved, except for this action's explicit full-auto public-index route. On that route omit `--offline` only for `citation-search --backend=cite-nexus` with bounded queries and `--providers` drawn from `crossref,datacite,europe_pmc,arxiv`; never override an operator-set offline flag or a host refusal. Never execute another module in this package, never pass a logical `project://` or `wtfp://` URI as a shell argument, and treat every returned record as candidate evidence until it is verified and written to a source or evidence record.
 
 ## Safety and completion
 

package/vendors/gemini/workflows/write-section.md

@@ -22,7 +22,7 @@ Manuscript prose and supporting context, research, plan, review, summary, handof
 ## Procedure
 
 1. Require one approved plan and resolve all linked context, research, source/evidence records, decisions, prior summary, existing target, and necessary neighboring prose before choosing create or update.
-2. Draft only the declared manuscript artifact; cite only resolvable sources, preserve author constraints, and stop at blocking decisions.
+2. Before drafting a literature-heavy section, verify that its linked research artifact and source/evidence records cover the plan's factual claims. If coverage is missing, use the declared research workflow and pause at a checkpoint until verified records exist. Draft only the declared manuscript artifact; cite only resolvable sources, preserve author constraints, and stop at blocking decisions. A plausible bibliography entry, search candidate, or model memory is not a verified citation.
 3. Read the persisted manuscript text back and calculate its actual body word count with one deterministic method; never copy a worker self-report, plan target, or summary count into project records. Validate the persisted draft against its plan and word budget.
 4. Create or update the required Markdown summary with that measured count, then read back both manuscript and summary. Missing, empty, or inconsistent output is a failed completion condition, not permission to link a path that does not exist.
 5. Persist the validation, synchronize the manuscript URI in `manifest.artifacts.manuscripts`, and reconcile section/state records only after manuscript, summary, and validation readback succeeds. If blocked, create the declared checkpoint and stop; do not commit or merge automatically.

package/vendors/opencode/.wtfp-generated.json

@@ -2,7 +2,7 @@
   "schema": "wtfp.generated-adapter/v1",
   "generatorVersion": 5,
   "target": "opencode",
-  "sourceHash": "421eb85c954ef0b7dbe38ad33c3379bf331e605b2f6fc657973dbb51c91ca062",
+  "sourceHash": "e4ca25636ced7d6fee6312f9edce382aaa7207945e3280a57fc4bcc561568b63",
   "files": [
     {
       "path": "actions/add-todo.json",
@@ -118,7 +118,7 @@
     },
     {
       "path": "actions/research-gap.json",
-      "sha256": "80659531e18fb60dd46620c8b35aa27ce0f966c467f0d3073ae8c6519084153e"
+      "sha256": "0c26fa663f1d2526cbefcc9750b0a176ddf1ca538a46585a1de48c763fbb1a13"
     },
     {
       "path": "actions/resume-writing.json",
@@ -178,7 +178,7 @@
     },
     {
       "path": "agents/wtfp/research-synthesizer.md",
-      "sha256": "ae63d3170606cf0aa9486e2780cd4fbdcb78aad1abe8dea4caab435e2ca6ed39"
+      "sha256": "72e2c5cfda7e838948e85909829ecf1290a17400cf9beac95b16bd4c03e1e075"
     },
     {
       "path": "agents/wtfp/section-planner.md",
@@ -202,147 +202,147 @@
     },
     {
       "path": "commands/wtfp/add-todo.md",
-      "sha256": "d78797a0e590396b75b972a22e2ee67eead4a3d3ff0b7f36267efc30464fff2e"
+      "sha256": "bcc7e675c99143acf3245bcbd77d528ee4f3bdc0c9b9145b0a14cb19083c551b"
     },
     {
       "path": "commands/wtfp/analyze-bib.md",
-      "sha256": "0c796e23eac32411e3413c212e1e9c1f3cc9292f3f4b179fd0795c3c8ea3f7f2"
+      "sha256": "3b1df0dc04c72c4667616357f97ed6f8ff293075bb3f207e81b604815e489bef"
     },
     {
       "path": "commands/wtfp/audit-milestone.md",
-      "sha256": "b5e41c06424e9576a88cd6a0ac0989475df55f5017a85359d49fbf87f812b6fd"
+      "sha256": "5a4c6f1527dbdd01f9f425f2cd7df4426ab8a74c3f0ff12c49c45939c0f7d941"
     },
     {
       "path": "commands/wtfp/check-refs.md",
-      "sha256": "100044023c2974c61c5522298783939226c1dc7e582f426c7baf0cd585881073"
+      "sha256": "0cd4d2de5dec519ab46de8b7a68984b89c6d8e7156a8bf9691a766420e13d8e2"
     },
     {
       "path": "commands/wtfp/check-todos.md",
-      "sha256": "7bd609d92d9d2dcdfbf84b14e3841f542625909077e1435fd11bec9d824b56c7"
+      "sha256": "c32daaba4fa6eb6634088151884b310e1accc91ce55d21c2c79113dafffa973a"
     },
     {
       "path": "commands/wtfp/checkpoint.md",
-      "sha256": "74c092b50e6903f723ba0d3729eaa8dbc5109068f2f8109a17ac3fd512da064f"
+      "sha256": "7634730a3b7beae58ce0a9ecec352536f7cbed2188ca9426e63ebc1a99598e6f"
     },
     {
       "path": "commands/wtfp/contribute.md",
-      "sha256": "0ec5ba2261aa2da10a7c0c2f80bf391173bf536345c9fcc5df1ad7870a4d7202"
+      "sha256": "209371557e886b0eb1bf042911fb8f398aa1eb38b1cd36d79fffb239d0b9c0ac"
     },
     {
       "path": "commands/wtfp/create-outline.md",
-      "sha256": "110420c7e42fe78d4e90ffca6aadac600f231bce027e1b3c9f11e7480de2df43"
+      "sha256": "b752700d4d9e6c324228c1e5a28919e2ab2c0d16cf70e331ef12541ce5aecacf"
     },
     {
       "path": "commands/wtfp/create-poster.md",
-      "sha256": "9da21f78420055973ceba10dedd962ddb22c98f05a1f80a73e537c5997b772aa"
+      "sha256": "f88921c1596715824dad986acc7aed861add2faa84b3979c625baca193687fd2"
     },
     {
       "path": "commands/wtfp/create-slides.md",
-      "sha256": "a9db098842fb9ecbea04ffec1a7a3da5b1d62f0eee262d7a41a4c946f60c6f52"
+      "sha256": "91d01cb92dca6efa4f0b22ea5f1ca3987fac9e5eab984f3a16c0f93760c43ad8"
     },
     {
       "path": "commands/wtfp/discuss-section.md",
-      "sha256": "fa93985070dfad28116f69b3225d324784418c52392d1b3436760f3d5236b431"
+      "sha256": "a09545263a592269938bd08a22f9bf57eace44b426d6cd0c214eb545b26e5299"
     },
     {
       "path": "commands/wtfp/execute-outline.md",
-      "sha256": "d6327aa5c744ad902bb5c06afcb35f3bda569506b8b9740115091ee834b90593"
+      "sha256": "eeac5d1fc2f103562ed54eedb493f129fb34af076aefa63a76f16cbed20689b1"
     },
     {
       "path": "commands/wtfp/export-latex.md",
-      "sha256": "123c1b7faed043bd289b63e2dc8b658af7000d3304eda3f5be82444fc4381fd9"
+      "sha256": "3280bd91bff665fec94007e1e9823625fa260d720eeb6a34caf5916b6a7a9583"
     },
     {
       "path": "commands/wtfp/help.md",
-      "sha256": "4e8d082925384fd99c7280fa57c73ea5d5620e42cbc0375771f30e197487637e"
+      "sha256": "df3757801ed3f91d7bd377300804809ebfe1f49e6ada33c08147426163892e28"
     },
     {
       "path": "commands/wtfp/insert-section.md",
-      "sha256": "f6fc171c6420a8f8fdf7e04b61b569dba9e6c7ac02dab530cff6d05a63fb6667"
+      "sha256": "573bc5eee9cc0f7e7ac8ae4c64d407d35b48e7488dfec94bc112a1a689409a3b"
     },
     {
       "path": "commands/wtfp/list-assumptions.md",
-      "sha256": "7029e4370ab4dfe9cd1216733947884463c758d07a68e0e4625bba3b3566cda7"
+      "sha256": "fa52b0242206b6eb48fc90da0fa5f9027a2406afadec421f31d7eaf0fdf5af8a"
     },
     {
       "path": "commands/wtfp/map-project.md",
-      "sha256": "c5e1c587abbab6ca5e174ad00b6ec48a79175aaa80929c91b335b91a6bac2958"
+      "sha256": "e1734abbd84b9c2d9d684f2fa4c2356c69e23dba7aabc34d33796cda4dc108f5"
     },
     {
       "path": "commands/wtfp/new-paper.md",
-      "sha256": "0983782f657a8c352d411fa4ce7f0d71cb9eadc9e2a20e6aefa6b630526c593c"
+      "sha256": "c9be1d8fcd36f84a9b1e07a89a91cbc4d2b118336e4edc8495cbade5037ae4c4"
     },
     {
       "path": "commands/wtfp/pause-writing.md",
-      "sha256": "7ccc36b94b01a54937d55407323bc229ab663ce488dfc2b961ad5626e8bc2c15"
+      "sha256": "5dfa80d285bb972f7af0e5a86a52ddfec219b4643425cfbe7226478eb3679c86"
     },
     {
       "path": "commands/wtfp/plan-milestone-gaps.md",
-      "sha256": "c3ba11b021edaadbaaefa37a4840e0a1c5592afa497a7ebaa5e1e9cf33726ce5"
+      "sha256": "6887dc1eb9c3f8b9b298c374a654288a3a8a62fc9a0483b21a905e9e0da4f7a6"
     },
     {
       "path": "commands/wtfp/plan-revision.md",
-      "sha256": "757cd80d5de257f1a743650eda05458b0ae30b7fc55e2a4baa376f6462c3861b"
+      "sha256": "555138157af0ae51850e883ac15953402b0ede8785246079f09f20387a547bb1"
     },
     {
       "path": "commands/wtfp/plan-section.md",
-      "sha256": "79352f41bf2885d59812b398e566f280274d523bd230a665714a998ef0eb0af6"
+      "sha256": "3c11e88eba43b1b970068dfbdb60d76c4fb8d041a0768c535bfbd760d4d3d8ec"
     },
     {
       "path": "commands/wtfp/polish-prose.md",
-      "sha256": "db252e77a87743634607ad8e5dd91a2ff36521cc50a9fb12218cbca6319955a5"
+      "sha256": "5b495adbe8438458cb532c901870a90b5b3ddb88a83f3865c8f0ab568ac39013"
     },
     {
       "path": "commands/wtfp/progress.md",
-      "sha256": "33d6aaf75881ddb9552e3efa12206172df6678cedd042bc0dbe1a3ada7733d80"
+      "sha256": "b3beaaf217639501467ea4dea0f4b553c77e8989a251872c48fe03f7c9f90c32"
     },
     {
       "path": "commands/wtfp/quick.md",
-      "sha256": "c61990951214044de03d0e0ee0a4faead752319181a4e9c9e3afa3e8faef0756"
+      "sha256": "c2d93c2504dbba2aebbcafa2311c628b9173e7c207b2a0133d8323cf8fbe2d2e"
     },
     {
       "path": "commands/wtfp/remove-section.md",
-      "sha256": "4a8457a8a3615c149faa44d24497f7ecfa39c2c92eb62800c09b1f06006a777e"
+      "sha256": "56bd4f966d183dfb1ef9dbaaa5cfb9879ee95ae8cba8e7826adff0d83cdee2cb"
     },
     {
       "path": "commands/wtfp/report-bug.md",
-      "sha256": "4d46e6085500ab9220d3cf8d755d5831d38a269304f5ea7c32208f1ca1c1c436"
+      "sha256": "6d3d02b27e04124dc293598a3627fcc55ef1a8f55510fe12700f64d513491df3"
     },
     {
       "path": "commands/wtfp/request-feature.md",
-      "sha256": "f7485735cfd6183710d9fdaae00afadd083489124876766bcf0cec70efd02f5f"
+      "sha256": "56dd68a3a939da2c0c0b5a13ae7a0980e6817394324cd640073746441df2640b"
     },
     {
       "path": "commands/wtfp/research-gap.md",
-      "sha256": "fc88cf14e990366c480d03dbd950d7458d8e7e4fd08f7758fb8524eb78198cc7"
+      "sha256": "77331d07b378abf80581228493b20e4ec0167acf01f30c88449935fbb7ee3e4b"
     },
     {
       "path": "commands/wtfp/resume-writing.md",
-      "sha256": "fb64be50a71611704694336afcd0193619b8abe1ac647c1dbf73014a229ec204"
+      "sha256": "805a9d48043eda03c4c9d27fdf0c47d9d9c6971aba60b561f21d491be1b49c9f"
     },
     {
       "path": "commands/wtfp/review-section.md",
-      "sha256": "b8bedbcce20ef0f2afc19869a786123012630af8635b953e88521806d884faa1"
+      "sha256": "3814fb4fb5c55d6ca399e5c9eaf6db895a015218ce97d8c495da7cc1f3df8082"
     },
     {
       "path": "commands/wtfp/settings.md",
-      "sha256": "b6cbbdd6619f20a5e56a980fe64c090a553926354184b6381cba02d26857feb8"
+      "sha256": "2b18f5027c2e959ee675d87f687db44c6689c23e8db835823280a86740e633c7"
     },
     {
       "path": "commands/wtfp/submit-milestone.md",
-      "sha256": "c16f736fbbdde570bbc167d3be7ab1916adf91d66df9bd421ba9ff7dbaac2419"
+      "sha256": "29dbaa157b8c663dc9124b90dc9385262f79e69a398fadece5a38b5e5672bf93"
     },
     {
       "path": "commands/wtfp/update.md",
-      "sha256": "a699a447ce9c1e340b5cfd000912b4d5bbbcda16bf808c864ca63ee1ac2d7d88"
+      "sha256": "a3e5151b59f55e4a896adbcc297e473a73307cfed47424a22a1ef1574de5d890"
     },
     {
       "path": "commands/wtfp/verify-work.md",
-      "sha256": "169ab4e5faba71036d5ee8ea9f2632695df3312aa78948db6f0b349e143785eb"
+      "sha256": "6b81afccf743ccf83dcf8d34cdd6be6884878d1d2196e20176cef055f4cee004"
     },
     {
       "path": "commands/wtfp/write-section.md",
-      "sha256": "8070987a5a1b517e2f39bcf236464a01f2670d1ea4384fdeb4dbb4fa2eda0a1c"
+      "sha256": "3e204fe76ce2a3faaf0eac37ad5895a3b1fee1d28247a2e32ccab1dca14b9f9a"
     },
     {
       "path": "compatibility/action-availability.json",
@@ -482,7 +482,7 @@
     },
     {
       "path": "roles/research-synthesizer.md",
-      "sha256": "011feaa1fdb967c267713f4fa4b0c45b27e66a62f71d1f24c4f44360442aef57"
+      "sha256": "7aa6922f5f819918374b1a87dbda5c12fa6d424be64fc13b4019c380e011306c"
     },
     {
       "path": "roles/section-planner.md",
@@ -526,7 +526,7 @@
     },
     {
       "path": "skills/wtfp-deliver-research/references/actions.md",
-      "sha256": "9057d2533d80d7efc317cd74f9fa2dc603ac73a402711ed1309d676fa7f26f8d"
+      "sha256": "ce40d27b14dc32e3cbefa850a4d14480bf55a42811a4894034af3a2955f1bd99"
     },
     {
       "path": "skills/wtfp-deliver-research/SKILL.md",
@@ -550,7 +550,7 @@
     },
     {
       "path": "skills/wtfp-plan-section/references/actions.md",
-      "sha256": "02a9e560970091cde2053fbcd765e68046a828b08bdf8abda2c0e72b0330ad2b"
+      "sha256": "bda6fee21d51a21c0e33d6c149ac5b34ea1569a270d576655953630c750996c0"
     },
     {
       "path": "skills/wtfp-plan-section/SKILL.md",
@@ -562,7 +562,7 @@
     },
     {
       "path": "skills/wtfp-research-literature/references/actions.md",
-      "sha256": "ebe21c6facfa34a6a99e61cbd8b48190164286cf897fdc1179c01dda5702915d"
+      "sha256": "2f88bf10948007f582774275b81c93d0e3836d9819a72d1c69eb578dcb3f8144"
     },
     {
       "path": "skills/wtfp-research-literature/SKILL.md",
@@ -598,7 +598,7 @@
     },
     {
       "path": "skills/wtfp-write-section/references/actions.md",
-      "sha256": "367b9144ce76b4e6116d9a2566c02070e80bbb57325a43bf5aa22447e6cb83f5"
+      "sha256": "1fe6f8d50a1abd7a0b338772560317404942874ddd67be458ca24182ea20f7a4"
     },
     {
       "path": "skills/wtfp-write-section/SKILL.md",
@@ -614,7 +614,7 @@
     },
     {
       "path": "templates/poster.md",
-      "sha256": "c4dfd10bcd4ba7664d99adc0ed3574b6f6f52c99648a8b7465f467cc5a27ca07"
+      "sha256": "5bbabf0adfc6de8f54cc839548f81b35045a7c8ffcc7117ea4008de7946c51d2"
     },
     {
       "path": "templates/README.md",
@@ -622,7 +622,7 @@
     },
     {
       "path": "templates/slides.md",
-      "sha256": "32068d09f1523b0eb5ac3ce5cbf964624117082ffbaa538907bac0db116326f5"
+      "sha256": "fd88d13f02b79a8e69e23dc8a72913cfd1ecb18aaea9013f6a2f2e080f301035"
     },
     {
       "path": "tools.json",
@@ -656,9 +656,13 @@
       "path": "tools/citation/semantic-scholar.js",
       "sha256": "df4c1f3d69a28e06dd5285ba46c116bb2731aa940e16b9438c822846f38646f5"
     },
+    {
+      "path": "tools/package.json",
+      "sha256": "dbf8353f77358bc12169b7bb7301e1978d5b503e002ee927229a8993672818fc"
+    },
     {
       "path": "tools/README.md",
-      "sha256": "997889703a61599a3d6267b1ddbd571ac354b55e7fe3a9dc2ebbf00b6c6d2106"
+      "sha256": "eb99d2ef30209b409e8c0dbfccaabdf301b6bc50f17013cd8fa381c3c1d69ae2"
     },
     {
       "path": "tools/support/cite-nexus-client.js",
@@ -702,11 +706,11 @@
     },
     {
       "path": "workflows/create-poster.md",
-      "sha256": "142d8d332909f6a1828b769eea40d8caa7985d8f17fb932f2d025fe6d8e34b6d"
+      "sha256": "b0fe98c72709b53a0553bb5d9343e112ef042cf2a950fa064108ac66f59d1f14"
     },
     {
       "path": "workflows/create-slides.md",
-      "sha256": "275996a358528cfd35abc096e1041c189de9a36ec163c5d063de8dc82f0fe36d"
+      "sha256": "8ad4189076a7460fb0ec55d2aab4d4898b906c1adfbe9810b293b46192a5622e"
     },
     {
       "path": "workflows/discuss-section.md",
@@ -754,7 +758,7 @@
     },
     {
       "path": "workflows/plan-section.md",
-      "sha256": "02311226aa784dea4a6a5219ef59fcea6c904f92566318e3327aa4e883228446"
+      "sha256": "831c20c8afd147a8ba149a46f54591b6f07732983ee916a56c66701c8c701aa2"
     },
     {
       "path": "workflows/polish-prose.md",
@@ -782,7 +786,7 @@
     },
     {
       "path": "workflows/research-gap.md",
-      "sha256": "a1736edb7e739708a92e5ef11c2d7c7a87fe8e6e4d6586e8ce9b1db3ae5bb428"
+      "sha256": "02ffe236ba7de12e4b3abbac308c0e1cfc409147147d509616b95baec3fef012"
     },
     {
       "path": "workflows/resume-writing.md",
@@ -810,7 +814,7 @@
     },
     {
       "path": "workflows/write-section.md",
-      "sha256": "cfb3a0f9c61830d62cebdf8be5dacd17cef996d99cbab1df18267313ca05aacc"
+      "sha256": "5a2f0efcd11d7f41d941f54b80798ad481773820907fee68bea47f28b7af7bc3"
     }
   ]
 }

package/vendors/opencode/actions/research-gap.json

@@ -96,7 +96,7 @@
     },
     {
       "id": "user.gate",
-      "scope": "the external providers, bounded query set, and research scope and depth"
+      "scope": "unapproved or paid external providers and bounded query set, plus author-owned research scope and depth decisions"
     }
   ]
 }

package/vendors/opencode/agents/wtfp/research-synthesizer.md

@@ -42,7 +42,7 @@ Investigate the literature needed to plan and write a specific section well. The
 ## Boundaries
 
 - This is a `mutation-report` role. It may write only the research and suggestion artifacts authorized by the invoking action.
-- When external literature search is approved, `citation-search` may run with `--backend=cite-nexus` and an explicit `--providers` list after the gate. Returned results stay candidates, and this role never performs a bibliography write.
+- An operator-configured, trusted read-only CiteNexus MCP connection may search bounded public scholarly metadata without a second per-query gate. In an explicitly selected full-auto host session for this research action, `citation-search --backend=cite-nexus` may also search `crossref`, `datacite`, `europe_pmc`, or `arxiv` without another gate. Other providers or modes require explicit network approval naming providers and query bounds. Honor offline flags and host refusals. Returned results stay candidates, and this role never performs a bibliography write.
 - Never fabricate a citation, identifier, quotation, metadata field, source conclusion, or claim of exhaustive coverage.
 - Never overwrite an existing `project://sources/{source}` record. Additions remain provisional until identity and provenance are verified by an authorized action.
 - Do not explore alternatives that author decisions explicitly deferred or rejected.

package/vendors/opencode/commands/wtfp/add-todo.md

@@ -4,8 +4,6 @@ description: "Capture a bounded note or task without disrupting the active resea
 argument-hint: "[arguments]"
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/add-todo; do not edit. -->
-
 # Add a todo
 
 <details data-wtfp-source="protocol://project/README.md" open>
@@ -714,3 +712,5 @@ Treat the following text as the user-supplied input for this action. Preserve it
 <invocation_arguments>
 $ARGUMENTS
 </invocation_arguments>
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/add-todo; do not edit. -->

package/vendors/opencode/commands/wtfp/analyze-bib.md

@@ -3,8 +3,6 @@ name: wtfp:analyze-bib
 description: "Analyze a bibliography and map its evidence to the paper's sections and claims."
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/analyze-bib; do not edit. -->
-
 WTFP_ACTION_UNAVAILABLE
 
 Action: `analyze-bib`
@@ -14,3 +12,5 @@ Unavailable effects: `tool.execute`
 
 No workflow, tool, network request, package operation, external issue, VCS operation, or other effect ran.
 Safe alternative: preserve project state and return a manual, non-executed handoff for the requested operation.
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/analyze-bib; do not edit. -->

package/vendors/opencode/commands/wtfp/audit-milestone.md

@@ -3,8 +3,6 @@ name: wtfp:audit-milestone
 description: "Run readiness checks across section completion, arguments, length, citations, and reviews."
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/audit-milestone; do not edit. -->
-
 WTFP_ACTION_UNAVAILABLE
 
 Action: `audit-milestone`
@@ -14,3 +12,5 @@ Unavailable effects: `tool.execute`
 
 No workflow, tool, network request, package operation, external issue, VCS operation, or other effect ran.
 Safe alternative: preserve project state and return a manual, non-executed handoff for the requested operation.
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/audit-milestone; do not edit. -->

package/vendors/opencode/commands/wtfp/check-refs.md

@@ -3,8 +3,6 @@ name: wtfp:check-refs
 description: "Audit citation integrity and emit a validated corrected-bibliography candidate without mutating source records or manuscript inputs."
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/check-refs; do not edit. -->
-
 WTFP_ACTION_UNAVAILABLE
 
 Action: `check-refs`
@@ -14,3 +12,5 @@ Unavailable effects: `tool.execute`
 
 No workflow, tool, network request, package operation, external issue, VCS operation, or other effect ran.
 Safe alternative: preserve project state and return a manual, non-executed handoff for the requested operation.
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/check-refs; do not edit. -->

package/vendors/opencode/commands/wtfp/check-todos.md

@@ -4,8 +4,6 @@ description: "Review pending tasks and explicitly act on, defer, complete, or di
 argument-hint: "[arguments]"
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/check-todos; do not edit. -->
-
 # Review todos
 
 <details data-wtfp-source="protocol://project/README.md" open>
@@ -572,3 +570,5 @@ Treat the following text as the user-supplied input for this action. Preserve it
 <invocation_arguments>
 $ARGUMENTS
 </invocation_arguments>
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/check-todos; do not edit. -->

package/vendors/opencode/commands/wtfp/checkpoint.md

@@ -4,8 +4,6 @@ description: "Save, list, or restore an exact portable paper-state checkpoint."
 argument-hint: "[arguments]"
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/checkpoint; do not edit. -->
-
 # Manage checkpoints
 
 <details data-wtfp-source="protocol://project/README.md" open>
@@ -1471,3 +1469,5 @@ Treat the following text as the user-supplied input for this action. Preserve it
 <invocation_arguments>
 $ARGUMENTS
 </invocation_arguments>
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/checkpoint; do not edit. -->

package/vendors/opencode/commands/wtfp/contribute.md

@@ -3,8 +3,6 @@ name: wtfp:contribute
 description: "Guide a bounded WTF-P contribution from branch creation through a reviewable change request."
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/contribute; do not edit. -->
-
 WTFP_ACTION_UNAVAILABLE
 
 Action: `contribute`
@@ -14,3 +12,5 @@ Unavailable effects: `external.issue`, `vcs.branch`, `vcs.commit`
 
 No workflow, tool, network request, package operation, external issue, VCS operation, or other effect ran.
 Safe alternative: preserve project state and return a manual, non-executed handoff for the requested operation.
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/contribute; do not edit. -->

package/vendors/opencode/commands/wtfp/create-outline.md

@@ -4,8 +4,6 @@ description: "Build the section structure, argument map, dependencies, and word
 argument-hint: "[arguments]"
 ---
 
-<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/create-outline; do not edit. -->
-
 # Create the paper outline
 
 <details data-wtfp-source="protocol://project/README.md" open>
@@ -1429,3 +1427,5 @@ Treat the following text as the user-supplied input for this action. Preserve it
 <invocation_arguments>
 $ARGUMENTS
 </invocation_arguments>
+
+<!-- Generated by WTF-P adapter compiler v5 from protocol/actions/create-outline; do not edit. -->