Deploy TinyModel1Space from GitHub Actions

scripts/nl_controls.py

@@ -2875,6 +2875,59 @@ def _embedded_postmortem_format(m: str) -> tuple[str, str] | None:
     return instr, "postmortem"
 
 
+def _embedded_sprint_retro(m: str) -> tuple[str, str] | None:
+    """``sprint_retro`` — agile sprint retrospective layout (distinct from incident ``postmortem``)."""
+    if len(m) < 48:
+        return None
+    no_sr = bool(
+        re.search(
+            r"\b(no sprint retro|without (?:a\s+)?sprint retro|not a sprint retro|"
+            r"skip (?:the\s+)?sprint retro|don'?t use sprint retro|"
+            r"avoid sprint retro(?:spective)? (?:format|sections)|"
+            r"no (?:sprint\s+)?retrospective format|"
+            r"skip (?:the\s+)?(?:sprint\s+)?retrospective format)\b",
+            m,
+        )
+    )
+    if no_sr:
+        return None
+    postmortem_only = bool(
+        re.search(
+            r"\b(postmortem format|blameless postmortem|incident postmortem|"
+            r"post[- ]mortem format|postmortem outline)\b",
+            m,
+        )
+    )
+    if postmortem_only:
+        return None
+    want = bool(
+        re.search(
+            r"\b(sprint retro(?:spective)?(?:\s+format)?|"
+            r"sprint retrospective(?:\s+format)?|"
+            r"agile retro(?:spective)?|scrum retro(?:spective)?|"
+            r"retro format|retrospective format|"
+            r"run (?:a\s+)?(?:sprint\s+)?retro(?:spective)?|"
+            r"facilitate (?:a\s+)?(?:sprint\s+)?retro(?:spective)?)\b",
+            m,
+        )
+    )
+    if not want:
+        return None
+    if not re.search(
+        r"\b(sprint|iteration|scrum|agile|team|delivery|release|"
+        r"reflect|review|improve|outline|write|describe|facilitate|discuss)\b",
+        m,
+    ):
+        return None
+    instr = (
+        "The user wants a **sprint retrospective** layout: use markdown headings "
+        "**Sprint / period** (one line), **What went well**, **What didn't go well**, "
+        "**Ideas / experiments**, and **Action items** (concrete next-sprint improvements)—"
+        "stay blameless and team-focused; this is **not** an incident postmortem."
+    )
+    return instr, "sprint_retro"
+
+
 def _embedded_five_whys(m: str) -> tuple[str, str] | None:
     """``five_whys`` — iterative Why chain for root-cause analysis (distinct from full postmortem)."""
     if len(m) < 48:
@@ -3593,7 +3646,7 @@ def analyze_embedded_prompt_signals(message: str) -> tuple[dict[str, str], list[
         ``topic_must``, ``glossary``, ``spelling_uk``, ``spelling_us``, ``risks_mitigations``,
         ``timeline_chron``, ``timeline_reverse``, ``voice_second``, ``voice_third``, ``faq_qa``,
         ``summary_last``, ``decision_matrix``, ``build_vs_buy``, ``one_pager``, ``action_plan``, ``raci``, ``stakeholder_map``, ``swot``, ``pestle``, ``cost_benefit``, ``open_questions``, ``scenario_cases``,
-        ``postmortem``, ``five_whys``, ``fishbone``,
+        ``postmortem``, ``sprint_retro``, ``five_whys``, ``fishbone``,
         ``recommendation_first``,
         ``go_no_go``,
         ``frame_star``, ``frame_prep``, ``frame_irac``). Session-style overrides
@@ -3780,6 +3833,11 @@ def analyze_embedded_prompt_signals(message: str) -> tuple[dict[str, str], list[
         extras.append(pm[0])
         trace_tags.append(pm[1])
 
+    srt = _embedded_sprint_retro(m)
+    if srt:
+        extras.append(srt[0])
+        trace_tags.append(srt[1])
+
     fw = _embedded_five_whys(m)
     if fw:
         extras.append(fw[0])

scripts/universal_brain_chat.py

@@ -112,7 +112,7 @@ from rag_faq_smoke import _pick_model, hybrid_retrieve, load_chunks  # noqa: E40
 from tinymodel_runtime import TinyModelRuntime  # noqa: E402
 
 HELP_TEXT = """**How to use**
-- **Normal language:** ask in plain English (or mixed); the app **infers** what you want (summarize, search FAQ, save a note, etc.). Longer prompts may also **imply** reply shape for that turn only (for example trade-off questions → Pros/Cons layout or flowing prose comparison, “in a table” → markdown table preference, **no tables / tabular format in prose** → table style prefer or avoid, “answer in Spanish” → reply language, **code only** → code-first output, **explain the code / not code only in prose** → code with explanation, **pseudocode vs runnable code in prose** → algorithm layout, **cite your sources / no source links in prose** → citation style, **rank options in priority order in prose** → ranked_options, **decision matrix / criteria-as-rows in prose** → decision_matrix, **build vs buy / make vs buy in prose** → build_vs_buy, **one-pager / single-page executive brief in prose** → one_pager, **action plan with owners and due dates in prose** → action_plan, **RACI matrix / role assignment in prose** → raci, **stakeholder map / influence-interest in prose** → stakeholder_map, **exactly N options/alternatives in prose** → options_n=N, **Mermaid/flowchart vs no diagrams in prose** → diagram layout, **risks/downside vs benefits-first section order in prose** → risks_first / benefits_first, **risks and mitigations / risk register in prose** → risks_mitigations, **rewrite/polish my draft in prose** → revise_draft, **write/draft an email in prose** → email_format, **meeting agenda / timeboxed run-of-show in prose** → meeting_agenda, **before/after or track-changes on my draft in prose** → revise_diff, **don’t mention X / avoid discussing Y in prose** → topic_guard, **must cover / include a section on Z in prose** → topic_must, **STAR / PREP / IRAC format in prose** → frame_star / frame_prep / frame_irac, **SWOT analysis in prose** → swot, **PESTLE macro-environment analysis in prose** → pestle, **cost-benefit / CBA in prose** → cost_benefit, **open questions / TBD section in prose** → open_questions, **best/base/worst case scenario analysis in prose** → scenario_cases, **blameless postmortem format in prose** → postmortem, **five whys / 5 whys root cause in prose** → five_whys, **fishbone / Ishikawa cause-and-effect in prose** → fishbone, **checklist / tick-box format in prose** → checklist layout, **in under N words** → length cap, **be brief / more detail in prose** → verbosity brief or detailed, **hints only / don’t give the full solution** → guided discovery, **give me the full solution in prose** → full_solution (not hints), **red team / sanity check my plan** → challenge-style pushback, **be supportive / assume good intent on my plan** → supportive coaching, **don’t remember this / off the record** → ephemeral hint, **screen reader friendly / WCAG** → accessibility layout hint, **ELI5 / lay audience in a long question** → beginner audience, **assume I'm technical / expert depth in prose** → technical audience, **board-ready / Slack-casual wording** → formal or casual register, **valid JSON / return JSON in prose** → JSON output mode, **plain text only / no JSON in prose** → plain output format, **don’t guess / stick to facts in prose** → strict speculation, **brainstorm freely / wild ideas in prose** → creative speculation, **TLDR first / BLUF in prose** → summary-first open, **lead with your recommendation in prose** → recommendation_first, **go/no-go gate verdict in prose** → go_no_go, **summary at the end / closing recap in prose** → summary_last, **answer directly / skip the summary in prose** → direct opening, **FAQ direct quotes vs paraphrase-only in prose** → quote style for excerpts, **emoji ok vs no emoji in prose** → emoji style, **FAQ-only vs FAQ-plus-general-knowledge in prose** → FAQ grounding, **show work vs final-answer-only in prose** → math detailing, **state assumptions / limitations / caveats** in prose → transparent confidence tone, **be decisive / don’t hedge in prose** → assertive confidence tone, **curl/bash/kubectl in prose** → runnable commands, **conceptual only / no commands in prose** → conceptual actionability, **bullet points vs plain paragraphs in prose** → reply format, **step-by-step vs continuous procedure prose in long prompts** → step style, **concrete / worked / toy example in prose** → richer examples, **example-free / skip examples in prose** → sparser examples, **define terms first / intuition or big-picture first in prose** → explanation order, **no questions at the end / suggest next steps in prose** → closing style, **ask questions before answering / answer without clarifiers in prose** → clarify-first mode, **markdown section headings vs flat prose in long prompts** → section layout, **analogy vs literal-only in long prompts** → analogy style, **bold key terms vs minimal bold in long prompts** → term emphasis, **spell out acronyms vs terse acronyms in long prompts** → acronym style, **err on the side of safety vs ship-fast pragmatism in long prompts** → risk posture, **fenced code blocks vs inline-only snippets in long prompts** → code block style) — see *Brain trace* **`prompt_signals:`** when detected.
+- **Normal language:** ask in plain English (or mixed); the app **infers** what you want (summarize, search FAQ, save a note, etc.). Longer prompts may also **imply** reply shape for that turn only (for example trade-off questions → Pros/Cons layout or flowing prose comparison, “in a table” → markdown table preference, **no tables / tabular format in prose** → table style prefer or avoid, “answer in Spanish” → reply language, **code only** → code-first output, **explain the code / not code only in prose** → code with explanation, **pseudocode vs runnable code in prose** → algorithm layout, **cite your sources / no source links in prose** → citation style, **rank options in priority order in prose** → ranked_options, **decision matrix / criteria-as-rows in prose** → decision_matrix, **build vs buy / make vs buy in prose** → build_vs_buy, **one-pager / single-page executive brief in prose** → one_pager, **action plan with owners and due dates in prose** → action_plan, **RACI matrix / role assignment in prose** → raci, **stakeholder map / influence-interest in prose** → stakeholder_map, **exactly N options/alternatives in prose** → options_n=N, **Mermaid/flowchart vs no diagrams in prose** → diagram layout, **risks/downside vs benefits-first section order in prose** → risks_first / benefits_first, **risks and mitigations / risk register in prose** → risks_mitigations, **rewrite/polish my draft in prose** → revise_draft, **write/draft an email in prose** → email_format, **meeting agenda / timeboxed run-of-show in prose** → meeting_agenda, **before/after or track-changes on my draft in prose** → revise_diff, **don’t mention X / avoid discussing Y in prose** → topic_guard, **must cover / include a section on Z in prose** → topic_must, **STAR / PREP / IRAC format in prose** → frame_star / frame_prep / frame_irac, **SWOT analysis in prose** → swot, **PESTLE macro-environment analysis in prose** → pestle, **cost-benefit / CBA in prose** → cost_benefit, **open questions / TBD section in prose** → open_questions, **best/base/worst case scenario analysis in prose** → scenario_cases, **blameless postmortem format in prose** → postmortem, **sprint retrospective / retro format in prose** → sprint_retro, **five whys / 5 whys root cause in prose** → five_whys, **fishbone / Ishikawa cause-and-effect in prose** → fishbone, **checklist / tick-box format in prose** → checklist layout, **in under N words** → length cap, **be brief / more detail in prose** → verbosity brief or detailed, **hints only / don’t give the full solution** → guided discovery, **give me the full solution in prose** → full_solution (not hints), **red team / sanity check my plan** → challenge-style pushback, **be supportive / assume good intent on my plan** → supportive coaching, **don’t remember this / off the record** → ephemeral hint, **screen reader friendly / WCAG** → accessibility layout hint, **ELI5 / lay audience in a long question** → beginner audience, **assume I'm technical / expert depth in prose** → technical audience, **board-ready / Slack-casual wording** → formal or casual register, **valid JSON / return JSON in prose** → JSON output mode, **plain text only / no JSON in prose** → plain output format, **don’t guess / stick to facts in prose** → strict speculation, **brainstorm freely / wild ideas in prose** → creative speculation, **TLDR first / BLUF in prose** → summary-first open, **lead with your recommendation in prose** → recommendation_first, **go/no-go gate verdict in prose** → go_no_go, **summary at the end / closing recap in prose** → summary_last, **answer directly / skip the summary in prose** → direct opening, **FAQ direct quotes vs paraphrase-only in prose** → quote style for excerpts, **emoji ok vs no emoji in prose** → emoji style, **FAQ-only vs FAQ-plus-general-knowledge in prose** → FAQ grounding, **show work vs final-answer-only in prose** → math detailing, **state assumptions / limitations / caveats** in prose → transparent confidence tone, **be decisive / don’t hedge in prose** → assertive confidence tone, **curl/bash/kubectl in prose** → runnable commands, **conceptual only / no commands in prose** → conceptual actionability, **bullet points vs plain paragraphs in prose** → reply format, **step-by-step vs continuous procedure prose in long prompts** → step style, **concrete / worked / toy example in prose** → richer examples, **example-free / skip examples in prose** → sparser examples, **define terms first / intuition or big-picture first in prose** → explanation order, **no questions at the end / suggest next steps in prose** → closing style, **ask questions before answering / answer without clarifiers in prose** → clarify-first mode, **markdown section headings vs flat prose in long prompts** → section layout, **analogy vs literal-only in long prompts** → analogy style, **bold key terms vs minimal bold in long prompts** → term emphasis, **spell out acronyms vs terse acronyms in long prompts** → acronym style, **err on the side of safety vs ship-fast pragmatism in long prompts** → risk posture, **fenced code blocks vs inline-only snippets in long prompts** → code block style) — see *Brain trace* **`prompt_signals:`** when detected.
 - **Session controls (say it in chat, no slash command):**
   - *What is my current scope?*, *Show my session settings* -> prints scope + toggles (FAQ context, routing, trace)
   - *Start a new private session*, *Begin a fresh scope* -> generates a **new memory scope key** so notes are isolated from the shared default demo scope
@@ -205,7 +205,7 @@ These behaviors apply when your line is handled as **normal chat** (not a short
 **How to test (two sends):**
 1. Send **Show the brain trace** as its **own short line** (do **not** combine it with your question in one message).
 2. Send your **long** test prompt as a **separate** message.
-3. Scroll to the bottom of the assistant reply and look for **`prompt_signals:`** in the *Brain trace* footer (e.g. **`prompt_signals:stakeholder_map`**).
+3. Scroll to the bottom of the assistant reply and look for **`prompt_signals:`** in the *Brain trace* footer (e.g. **`prompt_signals:sprint_retro`** or **`prompt_signals:stakeholder_map`**).
 
 **If you only see** `classify:…` / `RAG:…` **without** `prompt_signals:…`, the live Space may be running an older build — redeploy via GitHub Actions **Deploy versioned space artifact to Hugging Face** after merging, then hard-refresh the Space.
 
@@ -274,6 +274,7 @@ These behaviors apply when your line is handled as **normal chat** (not a short
 | UK vs US spelling | In a **long** message, ask for **British English** / **UK spelling** (e.g. colour, organise) **or** **American English** / **US spelling** (e.g. color, organize). Avoid mixing both locales in one line. | **`spelling_uk`** or **`spelling_us`** in **`prompt_signals:`**; reply should use that spelling convention throughout |
 | Chronological timeline | In a **long** history or incident question, ask for **chronological order**, **timeline format**, **what happened when**, or **earliest → latest** (oldest first). **Or** ask for **reverse chronological**, **newest first**, or **most recent event first** (avoid mixing both explicit orders in one line). | **`timeline_chron`** or **`timeline_reverse`** in **`prompt_signals:`**; reply should list dated/phased milestones in that time order |
 | Blameless postmortem | In a **long** incident or outage write-up, ask for **postmortem format**, a **blameless postmortem**, or a **postmortem outline** with summary, impact, timeline, root cause, lessons learned, and action items (avoid mixing with **no postmortem format** / **skip postmortem** in the same line). | **`postmortem`** in **`prompt_signals:`**; reply should use standard postmortem section headings |
+| Sprint retrospective (retro) | In a **long** agile team reflection, ask for a **sprint retro**, **sprint retrospective format**, **retro format**, or **facilitate a retrospective** for an iteration (avoid mixing with **no sprint retro** / **skip retrospective format**; use **Postmortem** for incident/outage write-ups). | **`sprint_retro`** in **`prompt_signals:`**; reply should use **What went well**, **What didn't go well**, **Ideas / experiments**, **Action items** |
 | 5 Whys root-cause analysis | In a **long** incident or defect question, ask for a **five whys**, **5 whys analysis**, **root cause using 5 whys**, or **ask why five times** (avoid mixing with **no five whys** / **skip the why chain** in the same line). | **`five_whys`** in **`prompt_signals:`**; reply should use **Problem statement**, **Why 1–5**, and **Root cause** |
 | Fishbone / Ishikawa diagram | In a **long** quality or incident question, ask for a **fishbone diagram**, **Ishikawa analysis**, **cause-and-effect diagram**, or **fishbone format** with categorized causes (avoid mixing with **no fishbone** / **skip fishbone** in the same line). | **`fishbone`** in **`prompt_signals:`**; reply should use **Problem / Effect** plus category headings (People, Process, Technology, etc.) with sub-causes |
 | Second vs third person voice | In a **long** how-to or doc draft, ask to **address the reader as you**, **use second person**, or **speak directly to me**. **Or** ask for **third person**, **impersonal tone**, or **avoid second person** / **don't use you throughout** (avoid mixing both in one line). | **`voice_second`** or **`voice_third`** in **`prompt_signals:`**; reply should use you/your or neutral third-person phrasing accordingly |